WACV 2026 Schedule

Filter Events

SUN 9 MAR

8 a.m.

Registration

(ends 5:00 PM)

9:30 a.m.

Break:

Courtesy Break

(ends 9:45 AM)

noon

Break:

Lunch

(ends 1:30 PM)

Doctoral Consortium:

DC Event

(ends 2:00 PM)

2:30 p.m.

Break:

Courtesy Break

(ends 2:45 PM)

3:45 p.m.

Meeting:

PAMI-TC meeting

(ends 4:30 PM)

MON 10 MAR

8 a.m.

Registration

(ends 2:00 PM)

9:30 a.m.

Break:

Courtesy Break

(ends 9:45 AM)

noon

Break:

Lunch

(ends 1:30 PM)

FRI 6 MAR

8 a.m.

Poster Pickup 1 [8:00-2:00]

(ends 2:00 PM)

SAT 7 MAR

8 a.m.

Poster Pickup 2 [8:00-2:00]

(ends 2:00 PM)

SUN 8 MAR

8 a.m.

Registration

(ends 5:00 PM)

8:30 a.m.

Remarks:

Opening Remarks and Paper Awards

(ends 9:00 AM)

9 a.m.

Keynote:

Sparse View Synthesis

Ravi Ramamoorthi

(ends 10:00 AM)

Poster Pickup 3 [9:00-4:00]

(ends 4:00 PM)

10 a.m.

Break:

Coffee Break

(ends 10:15 AM)

10:15 a.m.

Oral Session 1B [10:15-11:15]

Orals -

brat: Aligned Multi-View Embeddings for Brain MRI Analysis

CalibBEV: LiDAR-Camera Calibration via BEV Alignment

LASER: Lip Landmark Assisted Speaker Detection for Robustness

Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models

(ends 11:15 AM)

Oral Session 1A [10:15-11:15]

Orals -

ENCORE : A Neural Collapse Perspective on Out-of-Distribution Detection in Deep Neural Networks

MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination

SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection

Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score

(ends 11:15 AM)

11:15 a.m.

Poster Session 1 [11:15-1:00]

Posters -

4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos

Accelerated Dose Generation in Gamma Knife Radiosurgery Using a Wavelet Diffusion Model for Sparse Representation

Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?

AdaptViG: Adaptive Vision GNN with Exponential Decay Gating

A Fast, Simple, and Flexible Scale Informative Feature Transform Module for Arbitrary Scale Image Super-Resolution

AFL-PRF: Adaptive Federated Learning for Low-Quality Data: Enhancing Performance, Robustness, and Fairness

AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent

A framework for real-time Surgical Phase Recognition with application to Robot-Assisted Partial Nephrectomy

A Multi-Agent Diffusion Approach for MRI Anomaly Segmentation via Modality-Specific LoRA Specialization

Analysis of Text Accuracy and Visual Alignment in Vision-Language Models for Artistic Text Generation

ART: Actor-Related Tubelet for Detecting Complex-shaped Action Tubes

A Universal Self-Attention Enhancement for Bridging Low-bit Quantization and Vision Transformers

AUTOCORRELATION-BASED FIDUCIAL MARKERS FOR TRACEABILITY

AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks

A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions

BanglaProtha: Evaluating Vision Language Models in Underrepresented Long-tail Cultural Contexts

Beyond Realism: Learning the Art of Expressive Composition with StickerNet

Beyond Real Weights: Hypercomplex Representations for Stable Quantization

Beyond the Encoder: Joint Encoder-Decoder Contrastive Pre-Training Improves Dense Prediction

BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

Boosting Medical Vision-Language Pretraining via Momentum Self-Distillation under Limited Computing Resources

CAAC: Confidence-Aware Attention Calibration to Reduce Hallucinations in Large Vision-Language Models

CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles

Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?

ChameleonTuner: Automatic ISP Color Tuning in Subjective Scenarios

Cluster-based Pseudo-labeling for Semi-Supervised LiDAR Semantic Segmentation

Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning

CommonForms: A Large, Diverse Dataset for Form Field Detection

Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis

Contrastive Integrated Gradients: A Feature Attribution-Based Method for Explaining Whole Slide Image Classification

CountingDINO: A Training-free Pipeline for Class-Agnostic Counting using Unsupervised Backbones

Data-Driven Lipschitz Continuity: A Cost-Effective Approach to Improve Adversarial Robustness

Deepfake Detection that Generalizes Across Benchmarks

DermEVAL: A Dermatologist-Reviewed Benchmark for Multimodal Large Language Models

DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models

Distilling Diversity and Control in Diffusion Models

DiT-VTON: Diffusion Transformer Framework for Unified Multi-Category Virtual Try-On and Virtual Try-All with Integrated Image Editing

Diverse Sketch Colorization with Content-Enhanced Style Representation and Recolorization Distillation

Do generative video models understand physical principles?

DreamAnywhere: Object-Centric Panoramic 3D Scene Generation

DreamMakeup: Face Makeup Customization using Latent Diffusion Models

Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers

EmojiDiff: Advanced Facial Expression Control with High Identity Preservation in Portrait Generation

Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts

End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards

Enhanced Back-Projection of Vision Features for 3D Symmetry Detection

Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters

FAE-Net: Fashion Attribute Editing via Disentangled Latent Conditioning in Diffusion Models

FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs

Feature-Disentangling RGB-NIR Fusion Network for Remote Driver Physiological Measurement

Federated Model Synchronization for Diagnostic Redefinition through a Novel Selective Parameter Unlearning

Forget Less by Learning Together through Concept Consolidation

From Lightweight CNNs to SpikeNets: Benchmarking Accuracy–Energy Tradeoffs with Pruned Spiking SqueezeNet

From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance

Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models

GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

Gaussian Representations for Video

GenHSI: Controllable Generation of Human-Scene Interaction Videos

GrounDiff: Diffusion-Based Ground Surface Generation from Digital Surface Models

How to Design and Train Your Implicit Neural Representation for Video Compression

Human Pose Aggregation for Multi-View Temporal Video Alignment

HyperPose: Hyper-pose Embeddings for 3D-Aware Generative Models with Self-Supervised Disentangling of Pose and Scene

IDEAL-M3D: Instance Diversity-Enriched Active Learning for Monocular 3D Detection

ImageNet-sES: A First Systematic Study of Sensor–Environment Simulation Anchored by Real Recaptures

Inpaint360GS: Efficient Object-Aware 3D Inpainting via Gaussian Splatting for 360° Scenes

Interleaved Vision-and-Language Generation via Generative Voken

Joint Modeling of Corruption-Driven and Information-Limited Uncertainty for Robust 3D Gaussian Splatting

Learning Mask-Aware Offsets: Two-branch Deformable Attention Networks for Inpainting with Masked Region Avoidance

Learning to Animate Images from A Few Videos to Portray Delicate Human Actions

Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion

LiDAR-DHMT: LiDAR-Adaptive Dual Hierarchical Mask Transformer for Robust Freespace Detection and Semantic Segmentation

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization

M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models

MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data

MARS: a Multimodal Alignment and Ranking System for Few-Shot Segmentation

Marshaled Learning: Bridging Large Neural Networks with Memory-Constrained Trusted Execution Environments in Federated Learning

MBTI: Metric-Based Textual Inversion for Fine-Grained Image Generation

MDUNet: Multimodal Decoding UNet for Passive Occluder-Aided Non-line-of-sight 3D Imaging

MEDAL: multi-modal MEta-space Distillation and ALignment for Visual Compatibility Learning

M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening

MIX-based Foreground and Background Patch Augmentation Guided by Physics and Material Properties for X-ray Detection

Mixed Diffusion for 3D Indoor Scene Synthesis

Model-free Domain Adaptation for Concealed Multimodal Large-Language Models

MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval

MooTrack360: A Novel Fisheye Camera Dataset for Robust Multi Diary Cow Detection and Tracking

Morphing Through Time: Diffusion-Based Bridging of Temporal Gaps for Robust Alignment in Change Detection

MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models

MSRTrack: LLM-Powered Object Tracking with Motion and Semantic Reasoning

Narrating For You: Prompt-guided Audio-visual Narrating Face Generation Employing Multi-entangled Latent Space

Network-agnostic distortion-robust projections for wide-angle image understanding

No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts

Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping

One-Shot Fine-Grained Re-Identification of Paint Marked Honey Bees using Vision Foundation Models

OracleGS: Training-Free Sparse-View Gaussian Splatting

Overcoming Fine-Grained Visual Challenges in Animal Re-Identification via Semantic Feature Alignment

OW-Rep: Open World Object Detection with Instance Representation Learning

PaRaChute: Pathology-Radiology Cross-Modal Fusion for Missing-Modality-Robust Survival Prediction

PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models

Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation

PS3: Part level instance segmentation in 3D

PSA-MIL: A Probabilistic Spatial Attention-Based Multiple Instance Learning for Whole Slide Image Classification

QuadraNet V2: Efficient and Sustainable Training of High-Order Neural Networks with Quadratic Adaptation

RAT4D: Rig and Animate Objects without Surface Templates in 4D

Referring Change Detection in Remote Sensing Imagery

Reinforcement Learning-based Adaptive Control of Classifier-Free Guidance and Timestep Embeddings in Diffusion Models

Reverse Personalization

Revisiting Layer Normalization for Point Cloud Test Time Adaptation

Root Completion from Intraoral Scans of Tooth Crowns using Diffusion with Patch Perturbation

SaccadeX: Directed Acyclic Graph-based Semi-Supervised Learning of Continuous Ocular Dynamics from Sparse Neuromorphic Streams

Salience-SGG: Enhancing Unbiased Scene Graph Generation with Iterative Salience Estimation

Saliency-Guided DETR for Moment Retrieval and Highlight Detection

SCORP: Scene-Consistent Object Refinement via Proxy Generation and Tuning

SGPMIL: Sparse Gaussian Process Multiple Instance Learning

SilverLining: Data-First Mitigation of Spatial and Spectral Shortcuts Without Introducing New Confounders

SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection

SpikeRain: Towards Energy-Efficient Single Image Deraining with Spiking Neural Networks

SymNet: A Multi-Task Network for Joint Radio Map Reconstruction and Transmitter Localization

SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perception

Systematic Analysis of the Unintentional CSAM-Generation-Potential of Text-to-Image Models

TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors

Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters

Towards Fast and Scalable Normal Integration using Continuous Components

Training-free Multimodal Embedding for Structure-Aware Retrieval of Scalable Vector Graphics and Images

Training-free Multi-view 4D Human Motion Reconstruction Virtual Reality System

TS-PCI: Point Cloud Frame Interpolation with Time-Aware Point Cloud Sampling and Self-Supervised Learning Strategy

Understanding Human-Like Biases in VLMs via Subjective Face Analytics

UnderWater SLAM with Laser-light sectioning method using ST-GAT

Unified Video Anomaly Detection Model for Detecting Different Anomaly Types

ViGG: Robust RGB-D Point Cloud Registration using Visual-Geometric Mutual Guidance

Visibility guided Self-Supervised Occlusion Resilient Human Pose Estimation

VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models

Zero-Shot Video Deraining with Video Diffusion Models

ZonUI-3B: Competitive GUI Grounding with a 3B VLM Trained on a Single Consumer GPU

(ends 1:00 PM)

Exhibits + Demos 1 [11:15-5:45]

(ends 5:45 PM)

noon

Break:

Lunch

(ends 1:30 PM)

12:30 p.m.

Panel Discussion:

Bridging the Gap Between Academic Benchmarks and Real-World Deployment in Computer Vision: The Path to Translation.

(ends 1:30 PM)

1:45 p.m.

Oral Session 2A [1:45-2:45]

Orals -

Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization

Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients

QCFace: Image Quality Control for boosting Face Representation & Recognition

TS-PCI: Point Cloud Frame Interpolation with Time-Aware Point Cloud Sampling and Self-Supervised Learning Strategy

Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising

(ends 2:45 PM)

Oral Session 2B [1:45-2:45]

Orals -

Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training

Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance

Extreme Amodal Face Detection

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data

You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction

(ends 2:45 PM)

2:45 p.m.

Break:

Courtesy Break

(ends 3:00 PM)

3 p.m.

Oral Session 3A [3:00-4:00]

Orals -

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing

MarineEval: Assessing the Marine Intelligence of Vision-Language Models

OpenCowID: Zero-Shot Visual Identification of Dairy Cows

Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery

(ends 4:00 PM)

Oral Session 3B [3:00-4:00]

Orals -

Advancing Player Identification and Tracking with Global ID Fusion (GIF)

DreamAnywhere: Object-Centric Panoramic 3D Scene Generation

MageBench: Bridging Large Multimodal Models to Agents

UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations

X-JEPA: A Novel Joint Learning Cross-Modal Predictive Alignment Framework for Remote Sensing Image Retrieval

(ends 4:00 PM)

4 p.m.

Poster Session 2 + Refreshments [4:00-5:45]

Posters -

1LoRA: Summation Compression for Very-Low Rank Adaptation

3D Gaussian Point Encoders

3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting

AD$^2$: Analysis and Detection of Adversarial Threats in Visual Perception for End-to-End Autonomous Driving Systems

Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation

AnyBald: Toward Realistic Diffusion-Based Hair Removal In-The-Wild

ArchitectHead: Continuous Level of Detail Control for 3D Gaussian Head Avatars

ASC: Learning Augmentation Severity-Consistent Representations Improves Generalization via Augmentation Search

A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization

BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models

Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts

BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities

BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity

BrandFusion: Aligning Image Generation with Brand Styles

BrightRate: Quality Assessment for User-Generated HDR Videos

CAMP-VQA: Caption-Embedded Multimodal Perception for No-Reference Quality Assessment of Compressed Video

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition

Color Bind: Exploring Color Perception in Text-to-Image Models

Conditional Text-to-Image Generation with Reference Guidance

ConsensusXAI: A framework to examine class-wise agreement in medical imaging

Cosine Similarity is Almost All You Need (for Prototypical-Part Models)

CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusion

CURIO: Curvature-Aligned and Efficient OCR for Low-Resource Historical Manuscripts

CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning

CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning

DenseBEV: Transforming BEV Grid Cells into 3D Objects

Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions

Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting

Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models

Diffusion-Based Authentication of Copy Detection Patterns: A Multimodal Framework with Printer Signature Conditioning

DiRe: Diversity-promoting Regularization for Dataset Condensation

Discrete Facial Encoding: A Framework for Data-driven Facial Display Discovery

Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation

DMAT: An End-to-End Framework for Joint Atmospheric Turbulence Mitigation and Object Detection

DOODLE: Diffusion-based Out-of-Distribution Learning for Open-set LiDAR Semantic Segmentation

DoTA: Latent Distribution Conditioned Data Attribution for Diffusion Models

Dressing the Imagination: A Dataset for AI-Powered Translation of Text into Fashion Outfits and A Novel NeRA Adapter for Enhanced Feature Adaptation

DRWKV: Focusing on Object Edges for Low-Light Image Enhancement

DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenes

EllipssianNet: Image-guided Sampling of 2D Gaussians for Gaussian Splatting

Enhancing Object Detection Training via Joint Image-Annotation Generation

Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fr\'echet Distance

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning

False Alarm Rectification for Early Smoke Segmentation

FARF-Net: Frequency-guided Adaptive Receptive Field Network for Edge-enhanced Polyp Segmentation

FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy

FlowMorph: Revealing an Optimizable Flow Latent Space for Controlled Image Morphing

From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2

From Few-Shot to Zero-Shot Pallet Load Recognition: A Deployed Embedding-Based Vision System for Industrial Logistics

From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation

GeoHSAF: Geometric Hippocampus Shape Analysis Framework for Longitudinal Alzheimer's Disease Classification

Graph-Based Spectral Attention with Multi-Spectral Images for Illuminant Estimation

GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction

Harnessing Object Grounding for Time-Sensitive Video Understanding

HumanGuideNet: Adapter-Based Alignment of Deep Neural Networks with Human Similarity Judgments

Human knowledge integrated multi-modal learning for single source domain generalization

HyPCA-Net: Advancing Multimodal Fusion in Medical Image Analysis

Identity Verification from Human Scent using Channel Representation of 2D Gas Chromatography-Mass Spectrometry Data

Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild

Imitating the Functionality of Image-to-Image Models Using a Single Example

iMotion-LLM: Instruction-Conditioned Trajectory Generation

Improved Next-Day Wildfire Spread Prediction and the WSTS+ Benchmark

InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation

Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space

Intra-Class Probabilistic Embeddings for Uncertainty Estimation in Vision-Language Models

ITSELF: Attention Guided Fine-Grained Alignment for Vision–Language Retrieval

Knowledge to Sight: Reasoning over Visual Attributes via Knowledge Decomposition for Abnormality Grounding

Layout Anything: One Transformer for Universal Room Layout Estimation

Learnable Query-Enhanced Pose Transformation

LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset

Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identification

MageBench: Bridging Large Multimodal Models to Agents

MarineEval: Assessing the Marine Intelligence of Vision-Language Models

Matching Semantically Similar Non-Identical Objects

MEGA-PCC: A Mamba-based Efficient Approach for Joint Geometry and Attribute Point Cloud Compression

Memory-Augmented Representation for Efficient Event-based Visuomotor Policy Learning with Adaptive Perception and Control

milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion

Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimation

MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction

MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions

mmWeaver: Environment-Specific mmWave Signal Synthesis from a Photo and Activity Description

Moiré Zero: An Efficient and High-Performance Neural Architecture for Moiré Removal

MorphXAI: An Explainable Framework for Morphological Analysis of Parasites in Blood Smear Images

Multimodal Medical Image Binding via Shared Text Embeddings

NerVast: Compression-Efficient Scaling of Implicit Neural Video Representations via Scene-based Parameter-sharing

Non‑Contact Blood Pressure Estimation from Face Videos via Physiology‑Aware Contrastive Learning

Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model

ObjectMeshDeform : Towards recovering precise 3D geometry of real objects via image-guided mesh deformation of 3D generative priors

OpenCowID: Zero-Shot Visual Identification of Dairy Cows

OpenLVLM-MIA: A Controlled Benchmark Revealing the Limits of Membership Inference Attacks on Large Vision-Language Models

Orca: Object Recognition and Comprehension for Archiving Marine Species

Ordinal-Aware Multimodal Engagement Recognition for Collaborative Learning

PADM: A Physics-aware Diffusion Model for Attenuation Correction

Personalized Image Privacy Advisors via Federated Daisy-Chaining

PHYSPLAT: a Framework for Photorealistic Hybrid Simulation of Real and Synthetic Elements using 3D Gaussian Splatting

PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs

PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Pyramidal Spectrum: Frequency-based Hierarchically Vector Quantized VAE for Videos

QCFace: Image Quality Control for boosting Face Representation & Recognition

RapidMV: Leveraging Spatio-Angular Representations for Efficient and Consistent Text-to-Multi-View Synthesis

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph

Real-Time Tracking of Flexible Markers in Low-Contrast Fluoroscopy Using a Deep Neural Network Trained Solely on Synthetic Data

Reconstructing Realistic and Relightable Eyes

Revisiting Retentive Networks for Fast Range-View 3D LiDAR Semantic Segmentation

Reviving Unsupervised Optical Flow: Concept Reevaluation, Multi-Scale Advances and Full Open-Source Release

Roadside Monocular 3D Detection Prompted by 2D Detection

Robust and scalable visual out-of-distribution detection via label name mining using CLIP models

RobustFormer: Noise-Robust Pre-training for Images and Videos

RobustGait: Robustness Analysis for Appearance Based Gait Recognition

SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense

SasMamba: A Lightweight Structure-Aware Stride State Space Model for 3D Human Pose Estimation

ScoliGaitX: A Deep Multi-Modal Fusion Network for Scoliosis Assessment via Gait Video Analysis

SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization

Seeing is Believing (and Predicting): Context-Aware Multi-Human Behavior Prediction with Vision Language Models

Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary Delineation

Semi-Supervised Hierarchical Open-Set Classification

Shift-Equivariant Complex-Valued Convolutional Neural Networks

Sketch2Stitch: GANs for Abstract Sketch-Based Dress Synthesis

Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars

SPAR-Det: Segmentation-guided and Prior-Aided Routing for Small Object Detection

SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification

STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences

Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling

SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities

Tables Decoded: DELTA for Structure, TARQA for Understanding

Tables Guide Vision: Learning to See the Heart through Tabular Data

TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning

Temporal Object Captioning for Street Scene Videos from LiDAR Tracks

Test-Time Adaptation through Semantically-guided Feature Decomposition for Few-shot Chest X-ray Diagnosis

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs

Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature

UI-Styler: Ultrasound Image Style Transfer with Class-Aware Prompts for Cross-Device Diagnosis Using a Frozen Black-Box Inference Network

Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts

Understanding Generative AI Capabilities in Everyday Image Editing Tasks

UniCalib: Targetless LiDAR-camera Calibration via Probabilistic Flow on Unified Depth Representations

UniCoRN: Latent Diffusion-based Unified Controllable Image Restoration Network across Multiple Degradations

UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learning

Vision-informed Semantic Text Alignment for Open-set Recognition in Remote Sensing

What Happens When: Learning Temporal Order of Events in Videos

WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement

You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction

Zero-Shot Coreset Selection via Iterative Subspace Sampling

Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention

(ends 5:45 PM)

MON 9 MAR

8:30 a.m.

Keynote:

Applications of Computer Vision in Healthcare: The Road to Autonomy

Dorin Comaniciu

(ends 9:30 AM)

9 a.m.

Poster Pickup [9:00-4:00]

(ends 4:00 PM)

9:45 a.m.

Oral Session 4A [9:45-10:45]

Orals -

BrightRate: Quality Assessment for User-Generated HDR Videos

Layout Anything: One Transformer for Universal Room Layout Estimation

milliMamba: Specular-Aware Human Pose Estimation via Dual mmWave Radar with Multi-Frame Mamba Fusion

VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping

(ends 10:45 AM)

Oral Session 4B [9:45-10:45]

Orals -

ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks

DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy

Deep Image Decomposition for Medical Imaging Anonymization and Curation

Spec-Gloss Surfels and Normal–Diffuse Priors for Relightable Glossy Objects

(ends 10:45 AM)

10:45 a.m.

Poster Session 3 [10:45-1:30]

Posters -

2S-CEDiff: A Two-Stage Diffusion Framework for Generating High-Fidelity Contrast-Enhanced CT Images from Non-Contrast Scans

AGENet: Adaptive Edge-aware Geodesic Distance Learning for Few-Shot Medical Image Segmentation

AirLock+: Scaling UAV-to-Satellite Image Registration for Target Geolocalization and Geospatial Augmented Reality

A Little More Like This: Text-to-Image Retrieval with Vision-Language Models Using Relevance Feedback

A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis

AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM

ART-ASyn: Anatomy-aware Realistic Texture-based Anomaly Synthesis Framework for Chest X-Rays

Augmenting with NeRFs: Fast Relocalization on Densified Datasets

Autoregressive Styled Text Image Generation, but Make it Reliable

Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings

Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement

CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding

CaRS: A Causal Intervention Segmentation Framework and Benchmark Dataset for Autonomous Driving under Transitional Weather Conditions

CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading

CLIP-IT: CLIP-based Pairing of Histology Images with Privileged Textual Information

CLIP’s Visual Embedding Projector is a Few-shot Cornucopia

CLUE: Bringing Machine Unlearning to Mobile Devices

Codebook Knowledge with Mamba-Transformer For Low-Light Image Enhancement

Comp4D: Compositional 4D Scene Generation

Crafting Descriptive Information for a Zero-shot Method to Improve Knowledge-Based Visual Question Answering Performance

Cross-Modal Event Encoder: Bridging Image–Text Knowledge to Event Streams

Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image

DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition

DCSHARP: 3D Gaussian Splatting with Direction Cosine Spherical Harmonics and Shape-Aware Pruning

Decomposition Sampling for Efficient Region Annotations in Active Learning

Decoupling Shape and Texture in SAM-2 via Controlled Texture Replacement

Delta-LLaVA: Base-then-Specialize Alignment for Token-Efficient Vision-Language Models

Detecting Social Engagement of Elderly From Lifelog Image-streams to Identify Effective Cues for Autobiographic Recall

DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation

Domain Generalizing DINO for Visual Regression via Latent Distractor Subspace Consistency

DOTGraph: CLIP-Driven Feature Disentanglement and Optimal Transport based Graph Learning for Few-Shot Segmentation

Dragonite: Single-Step Drag-based Image Editing with Geometric-Semantic Guidance

DTMIR-Pro: Domain Translation with Prompt-based Latent-Space Generalization for Multi-Weather Image Restoration

Dual-Domain Multimodal Hyperbolic Fusion for Cardiopulmonary Disease Diagnosis in Emergency Care

Efficient Text-Guided Convolutional Adapter for the Diffusion Model

Efficient Vision Transformers via Token Merging with Head-wise Attention Correction

Empowering Source-Free Domain Adaptation via MLLM-Guided Reliability-Based Curriculum Learning

ENCORE : A Neural Collapse Perspective on Out-of-Distribution Detection in Deep Neural Networks

Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction

Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation

Event-based Graph Representation with Spatial and Motion Vectors for Asynchronous Object Detection

ExDDV: A New Dataset for Explainable Deepfake Detection in Video

Extreme Amodal Face Detection

FairScene: Learning Class-Disentangled 2D/3D Representations for Semantic Scene Completion

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing

Feature Inversion as a Lens on Vision Encoders

FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation

Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning

FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation

FLoMo-Net: A Novel Task-Adaptive Mixture of Experts Routing Framework with Frequency and Uncertainty Correction for Medical Image Segmentation

FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation

Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training

From Detection to Anticipation: Online Understanding of Struggles across Various Tasks and Activities

Fused Similarity Measure Based Alignment with Dual-Scale Adaptive Selection for Weakly Supervised Video Anomaly Detection

GAITGen: Disentangled Motion-Pathology Impaired Gait Generative Model -- Bringing Motion Generation to the Clinical Domain

GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving

Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy

Gradient-Free Classifier Guidance for Diffusion Model Sampling

Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models

Guided Texture Segmentation via Coordinate-Aware Class-Ratio Mapping

HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization

HistoMILKD: A Multiple Instance Learning based Multi-Teacher Knowledge Distillation Framework for Whole Slide Image Classification

HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models

JOCA: Task-Driven Joint Optimisation of Camera Hardware and Adaptive Camera Control Algorithms

KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird’s-Eye-View Segmentation

KMOPS: Keypoint-Driven Method for Multi-Object Pose and Metric Size Estimation from Stereo Images

Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression

Large Sign Language Models: Toward 3D American Sign Language Translation

Latent Uncertainty-Aware Multi-View SDF Scan Completion

Learning Action Hierarchies via Hybrid Geometric Diffusion

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models

Learning from Unknown for Open-Set Test-Time Adaptation

Learning Group Actions In Disentangled Latent Image Representations

LightGazeNet: A Lightweight GNN-based Architecture for Gaze Estimation

LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Captures

MAFM³: Modular Adaptation of Foundation Models for Multi-Modal Medical AI

MANTA: Physics-Informed Generalized Underwater Object Tracking

Masked Pre-training Meets Multi-Modal Reasoning for Soccer Scene Understanding

Mitigating Object and Action Hallucinations in Multimodal LLMs via Self-Augmented Contrastive Alignment

MixER: From Cross-Modal to Mixed-Modal Visible-Infrared Re-Identification

Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning

MuSACo: Multimodal Subject-Specific Selection and Adaptation for Expression Recognition with Co-Training

MuseDance: A Diffusion-based Music-Driven Image Animation System

NERVE: Neighbourhood & Entropy-Guided Random-Walk for Training Free Open-Vocabulary Segmentation

ObjectCore -– Efficient Few-shot Logical Anomaly Detection using Object Representations

One Model, Many Behaviors: Training-Induced Effects on Out-of-Distribution Detection

Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory

OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding

Perception-Inspired Color Space Design for Photo White Balance Editing

Perceptually Guided 3DGS Streaming and Rendering for Mixed Reality

Performance of Conformal Prediction in Capturing Aleatoric Uncertainty

PointNet4D: A lightweight 4D Point Cloud Video Backbone for Online and Offline Perception in Robotic Applications

Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image via Diffusion Transformer

Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues

PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment

ReBrain: Brain MRI Reconstruction from Sparse CT Slice via Retrieval-Augmented Diffusion

RegionAligner: Bridging Ego-Exo Views for Object Correspondence via Unified Text-Visual Learning

Rethinking Real Image Editing: Unleashing Diverse Editing Operators via Multi-Objective Optimization

SAIL: Self-supervised Learning of Lighting-Invariant Representations from Real Images with Latent Diffusion

SCALEX: Scalable Concept and Latent Exploration for Diffusion Models

Scalpel: Fine-Grained Alignment of Attention Activation Manifolds via Mixture Gaussian Bridges to Mitigate Multimodal Hallucination

SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropout

Sea-CLIP: Mining Semantic-Aware Representations for Few-Shot Anomaly Detection with CLIP

Self-Supervised Compression and Artifact Correction for Streaming Underwater Imaging Sonar

Self-Supervised Visual Prompting for Cross-Domain Road Damage Detection

SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology

Show Me: Unifying Instructional Image and Video Generation with Diffusion Models

SimForce: Force and Surface Electromyography from Full Body Video with Graph Neural Nets

SkelSplat: Robust Multi-view 3D Human Pose Estimation with Differentiable Gaussian Rendering

Sketch-guided Cage-based 3D Gaussian Splatting Deformation

SOAF: Scene Occlusion-aware Neural Acoustic Field

SPOC: Spatially-Progressing Object State Change Segmentation in Video

STEG-AIW: Spatio-Temporal Gating and Adaptive-Timestep Inference for Efficient Spiking Neural Networks

StreetView-Waste: A Multi-Task Dataset for Urban Waste Management

Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

Structure-Aware Feature Rectification with Region Adjacency Graphs for Training-free Open-Vocabulary Semantic Segmentation

TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection

TalkingPose: Efficient Face and Gesture Animation with Feedback-guided Diffusion Model

TiCLS : Tightly Coupled Language Text Spotter

Towards High-Fidelity, Identity-Preserving Real-Time Makeup Transfer: Decoupling Style Generation

Towards Reliable Test-Time Adaptation: Style Invariance as a Correctness Likelihood

Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences

Training-free Detection of Text-to-video Generations via Over-coherence

Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models

Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains

Universal Neural Architecture Space: Covering ConvNets, Transformers and Everything in Between

Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting

Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries

Unsupervised Modular Adaptive Region Growing and RegionMix Classification for Wind Turbine Segmentation

Visual Detector Compression via Location-Aware Discriminant Analysis

VOCAL: Visual Odometry via ContrAstive Learning

WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusion

Workzone3D: A Multimodal Dataset for 3D Work Zone Perception in Autonomous Driving

(ends 1:30 PM)

Exhibits + Demos 2 [10:45-6:00]

(ends 6:00 PM)

1:30 p.m.

Oral Session 5A [1:30-2:30]

Orals -

Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos

Orca: Object Recognition and Comprehension for Archiving Marine Species

Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval

T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis

VideoSketcher: A Training-Free Approach for Coherent Video Sketch Transfer

(ends 2:30 PM)

Oral Session 5B [1:30-2:30]

Orals -

Confidence Through Parallel Attention for Depth and Uncertainty Estimation in Dynamic Environments

DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors

DREAM: Dynamic Prompts and GuidedMix for Efficient Continual Adaptation of Visual-Language Models

Feedback Alignment Meets Low-Rank Manifolds: A Structured Recipe for Local Learning

(ends 2:30 PM)

2:45 p.m.

Oral Session 6A [2:45-3:45]

Orals -

Automated Suturing Skill Assessment in Robot-assisted Surgery from Endoscopic Videos using Clinically-guided Evaluation Criteria

Cycle-consistent Multi-graph Matching for Self-supervised Annotation of C. Elegans

Enhanced Back-Projection of Vision Features for 3D Symmetry Detection

Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning

VAST-ReID: A Low-Light Benchmark Dataset for Person Re-Identification with Visual and Attribute-Rich Semantic Tracking

(ends 3:45 PM)

Oral Session 6B [2:45-3:45]

Orals -

BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities

Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs

Fine-grained Defocus Blur Control for Generative Image Models

VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models

VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

(ends 3:45 PM)

4:30 p.m.

Poster Session 4 + Reception [4:30-6:15]

Posters -

$\mathbf{R}^3$: Reconstruction, Raw, and Rain: Deraining Directly in the Bayer Domain

3D Superquadric Splatting

4D Multimodal Co-attention Fusion Network with Latent Contrastive Alignment for Alzheimer's Diagnosis

A Dataset and Framework for Learning State-invariant Object Representations

AEON: Adaptive Embedding Optimized Noise for Robust Watermarking in Diffusion Models

Anatomically-guided masked autoencoder pre-training for aneurysm detection

An Efficient Multi-Rater Setup Towards Personalized and Diversified Medical Image Segmentation

An improved architecture for part-based animal re-identification through semantic segmentation distillation

Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection

Automated Pore Detection from In-Situ FDM 3D Printing Video: A Comparative Evaluation of Modern Segmentation Models

Better Safe Than Sorry? Overreaction Problem of Vision Language Models in Visual Emergency Recognition

Beyond Faces: A Multimodal Person Clustering for Unconstrained Environments

BiNAR: A Bi-Modal Framework for Non-Aligned RGB-IR 3D Reconstruction via Gaussian Splatting

BlendCLIP: Bridging Synthetic and Real Domains for Zero-Shot 3D Object Classification with Multimodal Pretraining

BREEN: Bridge Data-Efficient Encoder-Free Multimodal Learning with Learnable Queries

Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos

CalibBEV: LiDAR-Camera Calibration via BEV Alignment

CoL2A: Convolution-free Local Linear Attention for SpatioTemporal Event Processing

Color Preserving CMOS-SPAD Fusion for Multi-Frame HDR

CONCORD: Concept-Informed Diffusion for Dataset Distillation

Confidence Through Parallel Attention for Depth and Uncertainty Estimation in Dynamic Environments

CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

Context-Preserving Dermoscopic Editing: Mask-Guided Lesion-Aware Diffusion for Attribute Modification

ControlEvents: Controllable Synthesis of Event Camera Data with Foundational Prior from Image Diffusion Models

Controllable Long-term Motion Generation with Extended Joint Targets

ControlVP: Interactive Geometric Refinement of AI-Generated Images with Consistent Vanishing Points

Countering Multi-modal Representation Collapse through Rank-targeted Fusion

CRISP: Cylindrical Rendering for In-Stream Point Clouds

CropAT: Leveraging Diffusion-Generated Target-Like Cropped Objects for Pseudo-Label Refinement in Domain-Adaptive Object Detection

Curve Skeletonization in Continuous domain for Meshes and Point Clouds

DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions

DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy

DF-Mamba: Deformable State Space Modeling for 3D Hand Pose Estimation in Interactions

Direct Visual Grounding by Directing Attention of Visual Tokens

DMS2F-HAD: A Dual-branch Mamba-based Spatial–Spectral Fusion Network for Hyperspectral Anomaly Detection

DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion

DPBridge: Latent Diffusion Bridge for Dense Prediction

Dronaquatics: Real-time Swimming Analytics Using Drone Captured Imagery

Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss

Ego-EXTRA: video-language Egocentric Dataset for EXpert-TRAinee assistance

EndoPBR: Photorealistic Synthetic Data for Surgical 3D Vision via Physically-based Rendering

Enhancing Vision Language Corruption Robustness using Cross Distribution & Prompted Denoisers

Eye-for-an-eye: Appearance Transfer with Dense Semantic Correspondence in Diffusion Models

FB-4D: Spatial-Temporal Coherent Dynamic 3D Content Generation with Feature Banks

FCC: Fully Connected Correlation for One-Shot Segmentation

Fine-grained Defocus Blur Control for Generative Image Models

Food Image Generation on Multi-Noun Categories

FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting

FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection

FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility

F-ViTA: Foundation Model Guided Visible to Infrared Translation

GAEA: A Geolocation Aware Conversational Assistant

Gated Temporal Fusion Transformers for Robust Multi-Object Tracking

Gaussian Swaying: Surface-Based Framework for Aerodynamic Simulation with 3D Gaussians

Gene-DML: Dual-Pathway Multi-Level Discrimination for Gene Expression Prediction from Histopathology Images

Generalization of Real World Video Deblurring By Image-to-Image Translation

Geo3DVQA: Evaluating Vision-Language Models for 3D Geospatial Reasoning from Aerial Imagery

Global Focal and Radial Distortion Averaging from Radial Fundamental Matrices for Robust Self-Calibration

Grounding Degradations in Natural Language for All-In-One Video Restoration

Grounding Descriptions in Images informs Zero-Shot Visual Recognition

GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search

Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction

Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation

HiGlassRM: Learning to Remove High-prescription Glasses via Synthetic Dataset Generation

HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation

Histopath-C: Towards Realistic Domain Shifts for Histopathology Vision-Language Adaptation

How I Met Your Bias: Investigating Bias Amplification in Diffusion Models

ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large Language Models

Improving Animal Pose Estimation through Species Similarity Measures and Rigorous Label Definition

Improving Out-of-Distribution Detection Using Segmented Images and Cross-View Attention Fusion

Inpainting of Sparse Depth Maps from Monocular Depth-from-Focus on Pixel Processor Arrays

INRetouch: Context Aware Implicit Neural Representation for Photography Retouching

KFS-Bench: Comprehensive Evaluation of Key Frame Sampling in Long Video Understanding

LASOR: Towards Clinically Transparent and Explainable Ophthalmic Report Generation via Lesion-Aware Segmentation

Learning spatio-temporal feature representations for video-based gaze estimation

Learning Subglacial Bed Topography from Sparse Radar with Physics-Guided Residuals

Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding

Line Art Colorization with Offset Prior-based Diffusion Model

Lorentz Entailment Cone for Semantic Segmentation

Lose Your Self (LoYS): an adversarial entropy-based unsupervised approach for model debiasing

LVM-Lite: Training Large Vision Models with Efficient Sequential Modeling

MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes

MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images

MoRe: Monocular Geometry Refinement via Graph Optimization for Cross-View Consistency

More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning

Multi-view stereo with multiple projectors for oneshot entire shape scan based on Neural SDF and DSSS demultiplexing

Occlusion Boundary and Depth: Mutual Enhancement via Multi-Task Learning

OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction

One-Cycle Structured Pruning via Stability-Driven Subnetwork Search

One-shot Portrait Stylizaiton via Geometric Alignment

Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation

PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection

Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching

PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction

PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction

PrevMatch: Revisiting and Maximizing Temporal Knowledge in Semi-Supervised Semantic Segmentation

PromptGAR: Flexible Promptive Group Activity Recognition

ProSkill: Segment-Level Skill Assessment in Procedural Videos

ProtoGMVAE: A Variational Auto-Encoder with True Gaussian Mixture Prior for Prototypical-based Self-Explainability

QC-SF: Improving Computer Vision for Airborne LiDAR Point Clouds of Boreal Forests with Quebec Simulated Forest Dataset

Quantifying the Limits of Segmentation Foundation Models: Modeling Challenges in Segmenting Tree-Like and Low-Contrast Objects

Rank-based Geographical Regularization: Revisiting Contrastive Self-Supervised Learning for Multispectral Remote Sensing Imagery

RemEdit: Efficient Diffusion Editing with Riemannian Geometry

Restora-Flow: Mask-Guided Image Restoration with Flow Matching

Revisiting Vision–Language Foundations for No-Reference Image Quality Assessment

RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions

Robust Multimodal Emotion Recognition from Incomplete Modalities via Query-Based Unimodal and Cross-Modal Learning

RPT-SR: Regional Prior attention Transformer for infrared image Super-Resolution

Safe Vision-Language Models via Unsafe Weights Manipulation

SeaClips: A Video Dataset for Maritime Object Detection

SegMango: Early Deep Mango Yield Prediction based on Flower Segmentation and Weather Data

Semi-supervised Domain Adaptation via Mutual Alignment through Joint Error

Semi-supervised Key-Point Estimation for Echocardiography Video

SIAM: Synchronous Interaction Attention for Human Mesh Recovery

Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval

SOPHY: Generating Simulation-Ready Objects with Physical Materials

Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains

Spec-Gloss Surfels and Normal–Diffuse Priors for Relightable Glossy Objects

SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection

Structured Context Learning for Generic Event Boundary Detection

ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos

Style-Friendly SNR Sampler for Style-Driven Generation

Subspace-Guided Knowledge Distillation for Efficient Model Transfer

Sun-E: Dataset and Benchmark for Event-Based Sun Sensing

SurfDist: Interpretable Three-Dimensional Instance Segmentation Using Curved Surface Patches

Surgical Gaussian Surfels: Highly Accurate Real-time Surgical Scene Rendering using Gaussian Surfels

SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding

TimeRefine: Temporal Grounding with Time Refining Video LLM

Timestamp Query Transformer for Temporal Action Segmentation

Towards Egocentric 3D Hand Pose Estimation in Unseen Domains

Towards Photorealistic Style Transfer with Multimodal Guidance and Robustness to Content Images in Arbitrary Styles

Transformer-Based Inpainting for Real-Time 3D Streaming in Sparse Multi-Camera Setups

UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets

UniDiff: Parameter-Efficient Adaptation of Diffusion Models for Land Cover Classification with Multi-Modal Remotely Sensed Imagery and Sparse Annotations

Unified Control for Inference-Time Guidance of Denoising Diffusion Models

Unsupervised Segmentation by Diffusing, Walking and Cutting

VFace: A Training-Free Approach for Diffusion-Based Video Face Swapping

VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

VLMs Guided Interpretable Decision Making in Autonomous Driving

WarpRF: Multi-View Consistency for Training-Free Uncertainty Quantification and Applications in Radiance Fields

WiSE-OD: Benchmarking Robustness in Infrared Object Detection

WSSSP-Net: Weakly Supervised Semantic Segmentation Plugin Network for Face Anti-Spoofing

X-JEPA: A Novel Joint Learning Cross-Modal Predictive Alignment Framework for Remote Sensing Image Retrieval

Zero-Shot Table Extraction in Business Documents: A Unified Benchmark with Error Taxonomy and Ecological Analysis

(ends 6:15 PM)

TUE 10 MAR

8:30 a.m.

Keynote:

A short history of video Understanding - Past, Present, and Future

Hilde Kühne

(ends 9:30 AM)

9 a.m.

Poster Pickup 4 [9:00-2:00]

(ends 2:00 PM)

9:45 a.m.

Oral Session 7A [9:45-10:45]

Orals -

DRWKV: Focusing on Object Edges for Low-Light Image Enhancement

Learning from Unknown for Open-Set Test-Time Adaptation

OracleGS: Training-Free Sparse-View Gaussian Splatting

Spacewalk-18: A Benchmark for Multimodal and Long-form Procedural Video Understanding in Novel Domains

UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training

(ends 10:45 AM)

Oral Session 7B [9:45-10:45]

Orals -

BiNAR: A Bi-Modal Framework for Non-Aligned RGB-IR 3D Reconstruction via Gaussian Splatting

Cosine Similarity is Almost All You Need (for Prototypical-Part Models)

Motion-Aware Graph Fusion NetWork for 3D Human Pose Estimation

Odo: Depth-Guided Diffusion for Identity-Preserving Body Reshaping

SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer

(ends 10:45 AM)

10:45 a.m.

Exhibits + Demos 3 [10:45-2:00]

(ends 2:00 PM)

Poster Session 5 [10:45-12:15]

Posters -

Adaptive Residual Graph Attention for Contrastive Multimodal Representation Learning

A Deep Network for Object Detection on Inland Waters

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation

Alignment and Distillation: A Robust Framework for Multimodal Domain Generalizable Human Action Recognition

Align Video Diffusion Model with Online Video-Centric Preference Optimization

ATM: Enhanced Alignment for Text-to-Motion Generation

A Unified Diffusion-Based Framework for Multi-Agent Trajectory Prediction Integrating Structured Multi-Modal Representations

AuthGuard: Generalizable Deepfake Detection via Language Guidance

AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization

BAFLE-DCT: Bypassing Adversarial Filters via Frequency-Selective Embedding in the DCT Domain

brat: Aligned Multi-View Embeddings for Brain MRI Analysis

Can Image Splicing and Copy-Move Forgery Be Detected by the Same Model? Forensim: An Attention-Based State-Space Approach

Causality-Driven Audits of Model Robustness

ChartQA-X: Generating Explanations for Visual Chart Reasoning

Clear Sights on Site: A Spatial-Adaptive Channel Network for Deblurring Construction Site Images

CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering

CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs

CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation

CoreCaption: Core Caption based Text-to-Video Retrieval

Correcting and Quantifying Systematic Errors in 3D Box Annotations for Autonomous Driving

CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting

D2Mamba: Dual Domain Guided Informed Search in State Space Model for Underwater Image Enhancement

Denoise, Divide, Distill, and Predict ($D^3P$): Towards Forecasting Long-horizon Real-world Anomaly from Normalcy

DexAvatar: 3D Sign Language Reconstruction with Hand and Body Pose Priors

Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning

Diffusion-Based Action Recognition Generalizes to Untrained Domains

Diffusion Noise Optimization for Synthetic VLM Training

Digital Forensic AI You Can Explain: A Case Study on Video Source Camera Identification

Distilling Offline Action Detection Models into Real-Time Streaming Models

Distribution Highlighted Reference-based Label Distribution Learning for Facial Age Estimation

DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning

DREAM: Dynamic Prompts and GuidedMix for Efficient Continual Adaptation of Visual-Language Models

Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors

Equivariant Sampling for Improving Diffusion Model-based Image Restoration

EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models

Exploring Automated Recognition of Instructional Activity and Discourse from Multimodal Classroom Data

Exploring the Boundaries of Diffusion Models for Offline Writer Identification with Sparse and Intra-Variable Data

FAIR-SIGHT: Fairness Assurance in Image Recognition via Simultaneous Conformal Thresholding and Dynamic Output Repair

FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding

F-INR: Functional Tensor Decomposition for Implicit Neural Representations

FlowCLAS: Enhancing Normalizing Flow-Based Anomaly Segmentation Via Contrastive Learning

FNOPT: Resolution-Agnostic, Self-Supervised Cloth Simulation using Meta-Optimization with Fourier Neural Operators

FocalComm: Hard Instance-Aware Multi-Agent Perception

ForestSplats: Deformable transient field for Gaussian Splatting in the Wild

From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision

From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models

Gaussian Splatting Map Registration with Orthographic Bird's-Eye-View Renderings

GDoFS: Gaussian DoF Separation for Plausible 3D Geometry in Sparse-View 3DGS

GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts

GFT-GCN: Privacy-Preserving 3D Face Mesh Recognition with Spectral Diffusion

GHOST: Getting to the Bottom of Hallucinations with A Multi-round Consistency Benchmark

Graph Query Networks for Object Detection with Automotive Radar

GroupPortrait: Multi-ID Portrait Generation with High Identity Preservation and Fine-Grained Control

Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment

HABIT: Human Action Benchmark for Interactive Traffic in CARLA

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

High-Level Semantics and Low-Level Features Fusion for Multi-Scale Object Detection in Dynamic Construction Environments

Histogram Assisted Quality Aware Generative Model for Resolution Invariant NIR Image Colorization

HodgeFormer: Transformers for Learnable Operators on Triangular Meshes through Data-Driven Hodge Matrices

Hybrid State Representation for Video Procedure Planning

Hymavi : A Hybrid Mamba-Attention Network in Multi-View Framework for Volumetric Medical Image Segmentation

Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detection

IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion

IPCD: Intrinsic Point-Cloud Decomposition

Isolating the Role of Temporal Information in Video Saliency: A Controlled Experimental Analysis

Learning Beyond Labels: Self-Supervised Handwritten Text Recognition

LogicCBMs: Logic-Enhanced Concept-Based Learning

Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance

MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding

Mean-Shift Distillation for Diffusion Mode Seeking

Memoire: Learning User Personas from Gallery Tags for Personalized Photo Curation

Modeling and Learning Multiple Hypotheses for Monocular 3D Object Detection

MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training

Motion-Aware Graph Fusion NetWork for 3D Human Pose Estimation

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships

MUSE: Model-based Uncertainty-aware Similarity Estimation for zero-shot 2D Object Detection and Segmentation

MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection

Neural Geometry Image-Based Representations with Optimal Transport (OT)

NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining

Non-Aligned Reference Image Quality Assessment for Novel View Synthesis

ODEt(ODEl): Shortcutting the Time and the Length in Diffusion and Flow Models for Faster Sampling

Optimal Transport for Rectified Flow Image Editing: Unifying Inversion-Based and Direct Methods

OSEG: Improving Diffusion sampling through Orthogonal Smoothed Energy Guidance

Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation

PALMS+: Modular Image-Based Floor Plan Localization Leveraging Depth Foundation Model

PerVL-Bench: Benchmarking Multimodal Personalization for Large Vision–Language Models

Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis

Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded Devices

PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit

Predicting Task fMRI Contrasts from Resting-State fMRI Using Sparse 3D Convolutions

Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport

QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain

RealDroneVision: Dataset and Architecture Advancements for Small-Object Drone Detection

R-MMA: Enhancing Vision-Language Models with Recurrent Adapters for Few-Shot and Cross-Domain Generalization

RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding

S2O: Static to Openable Enhancement for Articulated 3D Objects

SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance

SceneEdited: A City-Scale Benchmark for 3D HD Map Updating via Image-Guided Change Detection

SceneProp: Combining Neural Network and Markov Random Field for Scene-Graph Grounding

ScoreNet: Netting Lightweight Quality Scores for Better Visual Assessment with Large Multi-Modality Models

SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning

See, Record, Do: Automated Generation of UI Workflows from Tutorial Videos

SegMo: Segment-aligned Text to 3D Human Motion Generation

SFMNet: Sparse Focal Modulation for 3D Object Detection

SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation

Single-step Diffusion for Image Compression at Ultra-Low Bitrates

SSMT-Net: A Semi-Supervised Multitask Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images

Synthesizing Compositional Videos from Text Description

T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation

TacticalCalib: End-to-End 6-DoF Camera Pose Regression for Tactical Camera Calibration

TED-4DGS: Temporally Activated and Embedding-based Deformation for 4DGS Compression

Test-Time Adaptation for Video Highlight Detection Using Meta-Auxiliary Learning and Cross-Modality Hallucinations

Test Time Adaptation Using Adaptive Quantile Recalibration

TM-Adapter: Temporal Merge Adapter for Efficient Global Temporal Modeling

Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score

TRACE: Confounder-free Adversarial Fine-tuning for Robust Object Detection

Training-Free Few-Shot Segmentation via Vision-Language Guided Prompting

Understanding the Visual Projection Space of Multimodal LLMs

UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training

UniTabBank: A Large Scale Multi-Lingual, Multi-Layout, Multi-Type, Multi-Format Dataset for Table Detection

UniVid: Unifying Vision Tasks with Pre-trained Video Generation Models

Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities

V2XScene: Multi-View Consistent 3D Scene Simulation for Collaborative Perception

VAST-ReID: A Low-Light Benchmark Dataset for Person Re-Identification with Visual and Attribute-Rich Semantic Tracking

VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics

Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control

Virtually Unrolling the Herculaneum Papyri by Diffeomorphic Spiral Fitting

VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion

WiSAR3D - Aerial LiDAR dataset for 3D object detection

ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data

Zero-LEAD: Source-Free Universal Domain Adaptation for Abdominal Multi-Organ Segmentation

Zero‑Shot Domain Generalisation via Prompt-Driven Feature Refinement

(ends 12:15 PM)

1:30 p.m.

Oral Session 8A [1:30-2:45]

Orals -

CONSTANT: Towards High-Quality One-Shot Handwriting Generation with Patch Contrastive Enhancement and Style-Aware Quantization

Performance of Conformal Prediction in Capturing Aleatoric Uncertainty

Reviving Unsupervised Optical Flow: Concept Reevaluation, Multi-Scale Advances and Full Open-Source Release

Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling

Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains

(ends 2:45 PM)

2:45 p.m.

Oral Session 9B [2:45-3:45]

Orals -

CLIP-UP: CLIP-Based Unanswerable Problem Detection for Visual Question Answering

IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers

PromptGAR: Flexible Promptive Group Activity Recognition

Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities

(ends 3:45 PM)

Oral Session 9A [2:45-3:45]

Orals -

Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation

InteracTalker: Prompt-Based Human-Object Interaction with Co-Speech Gesture Generation

ITSELF: Attention Guided Fine-Grained Alignment for Vision–Language Retrieval

OMeGa: Joint Optimization of Explicit Meshes and Gaussian Splats for Robust Scene-Level Surface Reconstruction

SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis

(ends 3:45 PM)

Oral Session 8B [2:45-3:45]

Orals -

BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

CAST: Evaluating Multi-Object Trackers with Context-Aware Switch and Transfer Scores

Identity Verification from Human Scent using Channel Representation of 2D Gas Chromatography-Mass Spectrometry Data

Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion

UnderWater SLAM with Laser-light sectioning method using ST-GAT

(ends 3:45 PM)

3:45 p.m.

Poster Session 6 + Refreshments [3:45-5:30]

Posters -

3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence

ACuRE: Accurate Continuity-Regularized SpO2 Estimation Using Liquid Time-Constant Networks

Advancing Player Identification and Tracking with Global ID Fusion (GIF)

Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning

Any Detector Can Detect Anything

AortaDiff: A Unified Multitask Diffusion Framework for Contrast-Free AAA Imaging

AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Construction

AusSmoke meets MultiNatSmoke: a fully-labelled diverse smoke segmentation dataset

Automated Suturing Skill Assessment in Robot-assisted Surgery from Endoscopic Videos using Clinically-guided Evaluation Criteria

Being Positive about Negative Queries: Exclusion Aware Multimodal Retrieval using Disentangled Representations

Beyond Paired Data: Self-Supervised UAV Geo-Localization from Reference Imagery Alone

Boosting Unsupervised Video Instance Segmentation with Automatic Quality-Guided Self-Training

Bridging the Domain Gap in Small Multimodal Models: A Dual-level Alignment Perspective

CaFlow: Enhancing Long-Term Action Quality Assessment with Causal Counterfactual Flow

CanKD: Cross-Attention-based Non-local operation for Feature-based Knowledge Distillation

CAST: Evaluating Multi-Object Trackers with Context-Aware Switch and Transfer Scores

Chain-of-Look Spatial Reasoning for Dense Surgical Instrument Counting

Conversational Image Generation: Towards Multi-Round Personalized Generation with Multi-Modal Language Models

Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation

Crash2DocAI: Automated Integration of Post-Crash Car Part Images into Technical Reports

CSF-Net: Context-Semantic Fusion Network for Large Mask Inpainting

Cycle-consistent Multi-graph Matching for Self-supervised Annotation of C. Elegans

Deep Image Decomposition for Medical Imaging Anonymization and Curation

DiffRegCD: Integrated Registration and Change Detection with Diffusion Features

DirectDrag: High-Fidelity, Mask-Free, Prompt-Free Drag-based Image Editing via Readout-Guided Feature Alignment

Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization

Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs

Diversity Preserving Coresets for Image Quality Assessment

DM$^3$Net: Dual-Camera Super-Resolution via Domain Modulation and Multi-scale Matching

DocWaveDiff: A Predict-and-Refine approch for Document Image Enhancement with Wavelet U-Nets and Diffusion models

Dual-Prompt Vision-Language Model for Universal Medical Image Segmentation and Prognosis

DualRes: Production-ready Dynamic Object Detection

DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation

Enhancing Reverse Distillation with Core Exemplar Learning for Unified Multi-Class Anomaly Detection

Exploiting Label-Independent Regularization from Spatial Dependencies for Whole Slide Image Analysis

FairVLM: Enhancing Fairness and Prompt Sensitivity in Vision Language Models for Medical Image Segmentation

FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation

FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels

Fetal and Neonatal Cortical Surface Reconstruction with Anatomical Normal-guidance and Perceptual Enhancements

FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation

Flood-LDM: Generalizable Latent Diffusion Models for rapid and accurate zero-shot High-Resolution Flood Mapping

FlyPose: Towards Robust Human Pose Estimation From Aerial Views

From Cognitive Priors to Instance Semantics: A Unified Framework for Multi-task Affective Computing

FuLLaMa: Training-free Diffusion-based Object Removal with Context Preservation

GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting

General and Domain-Specific Zero-shot Detection of Generated Images via Conditional Likelihood

Generalized Category Discovery for LiDAR Semantic Segmentation

Generalizing Sports Feedback Generation by Watching Competitions and Reading Books: A Rock Climbing Case Study

GFT: Graph Feature Tuning for Efficient Point Cloud Analysis

GorillaWatch: An Automated System for In-the-Wild Gorilla Re-Identification and Population Monitoring

GRAPE (Gaussian Rendering for Accelerated Pixel Enhancement) Brings Fast and Lightweight Arbitrary Super-Resolution

HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion

HOLO: Holistic Lightweight Optimization for Scene Understanding with Auto-Annotation and Multimodal Learning

ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research

IMPACT: Interpretable Most Important Person Analysis and Classification using Transformer-based Models

Improvise, Adapt, Overcome — Telescopic Adapters for Efficient fine-tuning of Vision Language Models in Medical Imaging

Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification

Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization

IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers

ISALux: Illumination and Semantics-Aware Transformer Employing Mixture of Experts for Low Light Image Enhancement

Joint Optimization of Camera Model and Deep Neural Network for Image Recognition

LangPose: Language-Aligned Motion for Robust 3D Human Pose Estimation

LASER: Lip Landmark Assisted Speaker Detection for Robustness

Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models

Leveraging Sparsity for Privacy in Collaborative Inference

Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients

MapleGrasp: Mask-guided Feature Pooling for Language-driven Efficient Robotic Grasping

MapVerse: A Benchmark for Geospatial Question Answering on Diverse Real-World Maps

MedPEFT-CL: Dual-Phase Parameter-Efficient Continual Learning with Medical Semantic Adapter and Bidirectional Memory Consolidation

MedROV: Towards Real-Time Open-Vocabulary Detection Across Diverse Medical Imaging Modalities

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

Mem-MLP: Real-Time 3D Human Motion Generation from Sparse Inputs

Meta-YOLO: Metadata-Guided Real-Time Object Detector in Aerial Imagery

MIST: Multilingual Incidental Dataset for Scene Text Detection

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data

Multi-Grained Text-Guided Image Fusion for Multi-Exposure and Multi-Focus Scenarios

NAPP: Noise-Adaptive Prototype Perturbation for Few-Shot Learning

NavMapFusion: Diffusion-based Fusion of Navigation Maps for Online Vectorized HD Map Construction

NeuroBridge: Few-Shot Cross-Modal Neuron Re-identification via Dual-Channel Deep Metric Learning

NRGMark: Localized Watermarking for Energy Transparency in Images

Optimization-Free Style Transfer for 3D Gaussian Splats

Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology

Patch Your Matcher: Correspondence-Aware Image-to-Image Translation Unlocks Cross-Modal Matching via Single-Modality Priors

PDV: Prompt Directional Vectors for Zero-shot Composed Image Retrieval

PEaRL: Pathway-Enhanced Representation Learning for Gene and Pathway Expression Prediction from Histology

Photo Dating by Facial Age Aggregation

PhysEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education

PointSt3R: Point Tracking through 3D Ground Correspondence

Pre-Training Helps When Capacity Allows: Evidence from Ultra-Small ConvNets

QAL : A Loss for Recall–Precision Balance in 3D Reconstruction

Q-Former Autoencoder: A Modern Framework for Medical Anomaly Detection

QuEENet: Quantum-Enhanced Expressive Network for Image Classification

RampWatch: An In-the-Wild Dataset and Text-Guided Detection Framework for Recreational Vessels

Reciprocal Teaching: Dynamic Multi-Model Teacher-Student Learning for Multiple Noisy Annotations

ReFineVQA: Iterative Refinement of Video Description via Feedback Generation for Video Question Answering

Relevance-aware Multi-context Contrastive Decoding for Retrieval-augmented Visual Question Answering

Remote Sensing Forestry Similarity Convolution

Rethinking Latent Variable in Learned Image Compression

Revisiting an Old Perspective Projection for Monocular 3D Morphable Models Regression

Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors

SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destruction

SAVE: Sparse Autoencoder‑Driven Visual Information Enhancement for Mitigating Object Hallucination

SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer

Scalable Video Action Anticipation with Cross Linear Attentive Memory

SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis

SceneShine: Illumination-aware Human Scene Gaussian Re-Splatting from Mobile Device Video

SDT-6D: Fully Sparse Depth-Transformer for Staged End-to-End 6D Pose Estimation in Industrial Multi-View Bin Picking

See, Think, Learn: A Self-Taught Multimodal Reasoner

Semantic Map Guided Bird's-Eye View Learning for Online HD Map Construction

SeqFeedNet: Sequential Feature Feedback Network for Background Subtraction

SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition

Sketch3R: Rapid and Realistic 3D VR Sketch Creation to Shape Retrieval

SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache

SOLAR: Switchable Output Layer for Accuracy and Robustness in Once-for-All Training

SpecGen: Neural Spectral BRDF Generation via Spectral-Spatial Tri-plane Aggregation

SphereEdit: Spherical Semantic Editing in Diffusion Models

Splannequin: Freezing Monocular Mannequin-Challenge Footage with Dual-Detection Splatting

Splatter Layout: Geometry-embedded 3D Reconstruction via Surface Unfolding

Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient

START: Spatial and Textual Learning for Chart Understanding

STRinGS: Selective Text Refinement in Gaussian Splatting

SuperRivolution: Fine-Scale Rivers from Coarse Temporal Satellite Imagery

SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

SVD-Det: A Lightweight Framework for Video Forgery Detection Using Semantic and Visual Defect Cues

SVS-GAN for Semantic Synthesis of Traffic Videos for Autonomous Driving

T2LF: LLM-Guided Multimodal Diffusion for Text-to-Light Field Synthesis

Test-Time Consistency in Vision Language Models

TopoRec: Point Cloud Recognition Using Topological Data Analysis

Towards Unconstrained Cross-View Pose Estimation

Training-free Conditional Image Embedding Framework Leveraging Large Vision Language Models

TriaGS: Differentiable Triangulation-Guided Geometric Consistency for 3D Gaussian Splatting

UltraClean: A Simple Framework to Train Robust Neural Networks against Backdoor Attacks

Uncertainty-Aware Vision-Language Segmentation for Medical Imaging

Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation

VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models

VideoSketcher: A Training-Free Approach for Coherent Video Sketch Transfer

View-aware Cross-modal Distillation for Multi-view Action Recognition

VitaGlyph: Vitalizing Artistic Typography with Flexible Dual-branch Diffusion Models

VIZOR: Viewpoint-Invariant Zero-Shot Scene Graph Generation for 3D Scene Reasoning

VRAgent: Self-Refining Agent for Zero-Shot Multimodal Video Retrieval

Where is the Watermark? Interpretable Watermark Detection at the Block Level

Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising

(ends 5:30 PM)