WACV 2026 Papers

Layout:

mini compact topic detail

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

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

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

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

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

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

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

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

3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting

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

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

Grounding Descriptions in Images informs Zero-Shot Visual Recognition

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

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

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

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs

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

DICE: Discrete Inversion Enabling Controllable Editing for Masked Generative Models

Procedure Learning via Regularized Gromov-Wasserstein Optimal Transport

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

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

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

Diffusion Noise Optimization for Synthetic VLM Training

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

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

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

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

1LoRA: Summation Compression for Very-Low Rank Adaptation

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

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

SGPMIL: Sparse Gaussian Process Multiple Instance Learning

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

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

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

Subspace-Guided Knowledge Distillation for Efficient Model Transfer

Unified Control for Inference-Time Guidance of Denoising Diffusion Models

SIAM: Synchronous Interaction Attention for Human Mesh Recovery

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

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

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

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

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

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

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

Evaluating the Capability of Video Question Generation for Expert Knowledge Elicitation

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

BrandFusion: Aligning Image Generation with Brand Styles

Structured Context Learning for Generic Event Boundary Detection

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

Gaussian Representations for Video

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

PS3: Part level instance segmentation in 3D

Generalized Category Discovery for LiDAR Semantic Segmentation

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

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

TiCLS : Tightly Coupled Language Text Spotter

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

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

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

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

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

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

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

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

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

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

Optimizing against Infeasible Inclusions from Data for Semantic Segmentation through Morphology

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

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

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

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

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

AUTOCORRELATION-BASED FIDUCIAL MARKERS FOR TRACEABILITY

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

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

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

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

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

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

CONCORD: Concept-Informed Diffusion for Dataset Distillation

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

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

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

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

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

Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers

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

Guided Texture Segmentation via Coordinate-Aware Class-Ratio Mapping

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

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

Semi-supervised Domain Adaptation via Mutual Alignment through Joint Error

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

Distilling Diversity and Control in Diffusion Models

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

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

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

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

Latent Uncertainty-Aware Multi-View SDF Scan Completion

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

SCALEX: Scalable Concept and Latent Exploration for Diffusion Models

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

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

START: Spatial and Textual Learning for Chart Understanding

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

Unified Video Anomaly Detection Model for Detecting Different Anomaly Types

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

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

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

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

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

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

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

Zero-Shot Coreset Selection via Iterative Subspace Sampling

Beyond Faces: A Multimodal Person Clustering for Unconstrained Environments

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

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

FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation

SPOC: Spatially-Progressing Object State Change Segmentation in Video

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

Mean-Shift Distillation for Diffusion Mode Seeking

CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning

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

Understanding Generative AI Capabilities in Everyday Image Editing Tasks

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

S2O: Static to Openable Enhancement for Articulated 3D Objects

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

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

Style-Friendly SNR Sampler for Style-Driven Generation

Align Video Diffusion Model with Online Video-Centric Preference Optimization

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

Conditional Text-to-Image Generation with Reference Guidance

Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance

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

DualRes: Production-ready Dynamic Object Detection

Leveraging Pretrained Representations for Cross-Modal Point Cloud Completion

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

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

TimeRefine: Temporal Grounding with Time Refining Video LLM

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

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

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

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

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

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

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

Ordinal-Aware Multimodal Engagement Recognition for Collaborative Learning

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

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

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

HABIT: Human Action Benchmark for Interactive Traffic in CARLA

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

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

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

INRetouch: Context Aware Implicit Neural Representation for Photography Retouching

Optimization-Free Style Transfer for 3D Gaussian Splats

Streaming Real-Time Trajectory Prediction Using Endpoint-Aware Modeling

Performance of Conformal Prediction in Capturing Aleatoric Uncertainty

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

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

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

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

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

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

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

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

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

Sketch2Stitch: GANs for Abstract Sketch-Based Dress Synthesis

Forget Less by Learning Together through Concept Consolidation

SuperRivolution: Fine-Scale Rivers from Coarse Temporal Satellite Imagery

Mixed Diffusion for 3D Indoor Scene Synthesis

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

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

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

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

Semi-Supervised Hierarchical Open-Set Classification

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

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

ForestSplats: Deformable transient field for Gaussian Splatting in the Wild

Reconstructing Realistic and Relightable Eyes

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

Learning Group Actions In Disentangled Latent Image Representations

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

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

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

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

Trajectory Tactics: When Transformers Learn Exploration to Generate Online Signature

DoTA: Latent Distribution Conditioned Data Attribution for Diffusion Models

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

ChameleonTuner: Automatic ISP Color Tuning in Subjective Scenarios

Sketch-guided Cage-based 3D Gaussian Splatting Deformation

Gradient-Free Classifier Guidance for Diffusion Model Sampling

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

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

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

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

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

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

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

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

Uncertainty-Aware Vision-Language Segmentation for Medical Imaging

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

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

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

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

HyPCA-Net: Advancing Multimodal Fusion in Medical Image Analysis

Causality-Driven Audits of Model Robustness

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

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

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

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

What Happens When: Learning Temporal Order of Events in Videos

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

SmokeBench: Evaluating Multimodal Large Language Models for Wildfire Smoke Detection

Hybrid State Representation for Video Procedure Planning

Anatomically-guided masked autoencoder pre-training for aneurysm detection

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

SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer

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

AuthGuard: Generalizable Deepfake Detection via Language Guidance

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

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

3D Cell Oversegmentation Correction via Geo-Wasserstein Divergence

Photo Dating by Facial Age Aggregation

Distilling Offline Action Detection Models into Real-Time Streaming Models

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

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

DenseBEV: Transforming BEV Grid Cells into 3D Objects

MIST: Multilingual Incidental Dataset for Scene Text Detection

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

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

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

GenHSI: Controllable Generation of Human-Scene Interaction Videos

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

Autoregressive Styled Text Image Generation, but Make it Reliable

Perception-Inspired Color Space Design for Photo White Balance Editing

Enhancing Visual Planning with Auxiliary Tasks and Multi-token Prediction

RobustGait: Robustness Analysis for Appearance Based Gait Recognition

SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition

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

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

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

M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models

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

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

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

OSEG: Improving Diffusion sampling through Orthogonal Smoothed Energy Guidance

Test Time Adaptation Using Adaptive Quantile Recalibration

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

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

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

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

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

A Dataset and Framework for Learning State-invariant Object Representations

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

Learning from Unknown for Open-Set Test-Time Adaptation

3D Gaussian Point Encoders

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

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

Matching Semantically Similar Non-Identical Objects

PointSt3R: Point Tracking through 3D Ground Correspondence

False Alarm Rectification for Early Smoke Segmentation

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

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

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

OracleGS: Training-Free Sparse-View Gaussian Splatting

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

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

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

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

Saliency-Guided DETR for Moment Retrieval and Highlight Detection

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

Countering Multi-modal Representation Collapse through Rank-targeted Fusion

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

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

Fine-grained Defocus Blur Control for Generative Image Models

Lorentz Entailment Cone for Semantic Segmentation

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

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

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

Beyond Realism: Learning the Art of Expressive Composition with StickerNet

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

WiSAR3D - Aerial LiDAR dataset for 3D object detection

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

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

Distilling What and Why: Enhancing Driver Intention Prediction with MLLMs

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

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

Towards Streaming LiDAR Object Detection with Point Clouds as Egocentric Sequences

DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation

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

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

QuEENet: Quantum-Enhanced Expressive Network for Image Classification

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

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

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

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

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

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

Modeling and Learning Multiple Hypotheses for Monocular 3D Object Detection

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

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

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

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

CADE: Continual Weakly-supervised Video Anomaly Detection with Ensembles

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

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

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

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

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

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

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

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

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

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

Decomposition Sampling for Efficient Region Annotations in Active Learning

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

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

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

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

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

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

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

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

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

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

Synthesizing Compositional Videos from Text Description

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

Semi-supervised Key-Point Estimation for Echocardiography Video

CLUE: Bringing Machine Unlearning to Mobile Devices

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

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

Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars

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

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

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

Towards Egocentric 3D Hand Pose Estimation in Unseen Domains

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

FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility

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

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

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

Curve Skeletonization in Continuous domain for Meshes and Point Clouds

CommonForms: A Large, Diverse Dataset for Form Field Detection

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

Beyond Low-Light Enhancement: A Machine Vision Framework for Low-Light Remote Sensing Object Detection

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

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

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

Learning Action Hierarchies via Hybrid Geometric Diffusion

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

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

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

3D Superquadric Splatting

Learnable Query-Enhanced Pose Transformation

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

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

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

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

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

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

Roadside Monocular 3D Detection Prompted by 2D Detection

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

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

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

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

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

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

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

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

ZebraPose: Zebra Detection and Pose Estimation using only Synthetic Data

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

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

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

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

Perceptually Guided 3DGS Streaming and Rendering for Mixed Reality

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

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

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

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

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

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

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

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

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

Reverse Personalization

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

DiffRegCD: Integrated Registration and Change Detection with Diffusion Features

Color Preserving CMOS-SPAD Fusion for Multi-Frame HDR

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

FSP-DETR: Few-Shot Prototypical Parasitic Ova Detection

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

Controllable Long-term Motion Generation with Extended Joint Targets

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

A Deep Network for Object Detection on Inland Waters

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

Domain Generalizing DINO for Visual Regression via Latent Distractor Subspace Consistency

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

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

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

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

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

Enhancing Vision Language Corruption Robustness using Cross Distribution & Prompted Denoisers

FCC: Fully Connected Correlation for One-Shot Segmentation

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

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

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

Learning Unified Spatio-temporal Representations for Efficient Compressed Video Understanding

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

Enhancing Object Detection Training via Joint Image-Annotation Generation

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

OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding

Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors

SphereEdit: Spherical Semantic Editing in Diffusion Models

NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining

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

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

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

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

MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction

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

Understanding the Visual Projection Space of Multimodal LLMs

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

LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization

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

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

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

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

PromptGAR: Flexible Promptive Group Activity Recognition

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

Augmenting with NeRFs: Fast Relocalization on Densified Datasets

Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts

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

iMotion-LLM: Instruction-Conditioned Trajectory Generation

DreamMakeup: Face Makeup Customization using Latent Diffusion Models

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

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

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

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

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

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

VLMs Guided Interpretable Decision Making in Autonomous Driving

Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors

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

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

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

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

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

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

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

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

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

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

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

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

AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM

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

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

PADM: A Physics-aware Diffusion Model for Attenuation Correction

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

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

TopoRec: Point Cloud Recognition Using Topological Data Analysis

AdaptViG: Adaptive Vision GNN with Exponential Decay Gating

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

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

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

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

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

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

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

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

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

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

Overcoming Small Data Limitations in Video-Based Infant Respiration Estimation

SUGAR: A Sweeter Spot for Generative Unlearning of Many Identities

One-shot Portrait Stylizaiton via Geometric Alignment

RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions

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

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

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

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

SOAF: Scene Occlusion-aware Neural Acoustic Field

DiRe: Diversity-promoting Regularization for Dataset Condensation

SOPHY: Generating Simulation-Ready Objects with Physical Materials

Diversity Preserving Coresets for Image Quality Assessment

SeaClips: A Video Dataset for Maritime Object Detection

Tables Decoded: DELTA for Structure, TARQA for Understanding

Virtually Unrolling the Herculaneum Papyri by Diffeomorphic Spiral Fitting

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

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

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

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

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

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

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

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

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

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

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

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

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

PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Non-Aligned Reference Image Quality Assessment for Novel View Synthesis

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

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

Beyond Real Weights: Hypercomplex Representations for Stable Quantization

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

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

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

Efficient Text-Guided Convolutional Adapter for the Diffusion Model

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

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

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

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

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

FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels

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

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

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

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

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

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

Deepfake Detection that Generalizes Across Benchmarks

WiSE-OD: Benchmarking Robustness in Infrared Object Detection

Gated Temporal Fusion Transformers for Robust Multi-Object Tracking

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

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

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

Learning Beyond Labels: Self-Supervised Handwritten Text Recognition

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

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

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

Referring Change Detection in Remote Sensing Imagery

Orca: Object Recognition and Comprehension for Archiving Marine Species

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

VOCAL: Visual Odometry via ContrAstive Learning

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

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

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

Do generative video models understand physical principles?

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

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening

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

SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification

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

Broadcast2Pitch: Game State Reconstruction from Unconstrained Soccer Videos

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

Dronaquatics: Real-time Swimming Analytics Using Drone Captured Imagery

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

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

Similarity-aware Probabilistic Embeddings Modeling for Video-Text Retrieval

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

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

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

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

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

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

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

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

Revisiting Layer Normalization for Point Cloud Test Time Adaptation

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

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

LogicCBMs: Logic-Enhanced Concept-Based Learning

SurgXBench: Explainable Vision-Language Model Benchmark for Surgery

Deep Image Decomposition for Medical Imaging Anonymization and Curation

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

Personalized Image Privacy Advisors via Federated Daisy-Chaining

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

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

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

SFMNet: Sparse Focal Modulation for 3D Object Detection

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

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

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

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

Scalable Video Action Anticipation with Cross Linear Attentive Memory

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

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

ChartQA-X: Generating Explanations for Visual Chart Reasoning

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

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

NRGMark: Localized Watermarking for Energy Transparency in Images

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

DPBridge: Latent Diffusion Bridge for Dense Prediction

F-ViTA: Foundation Model Guided Visible to Infrared Translation

Graph Query Networks for Object Detection with Automotive Radar

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

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

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

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

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

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

FocalComm: Hard Instance-Aware Multi-Agent Perception

F-INR: Functional Tensor Decomposition for Implicit Neural Representations

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

Understanding Human-Like Biases in VLMs via Subjective Face Analytics

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

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

VectorSynth: Fine-Grained Satellite Image Synthesis with Structured Semantics

Feature Inversion as a Lens on Vision Encoders

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

Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

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

CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition

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

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

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

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

MANTA: Physics-Informed Generalized Underwater Object Tracking

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

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

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

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

Visual Detector Compression via Location-Aware Discriminant Analysis

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

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

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

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

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

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

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

Shift-Equivariant Complex-Valued Convolutional Neural Networks

Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis

Test-Time Consistency in Vision Language Models

ExDDV: A New Dataset for Explainable Deepfake Detection in Video

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

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

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

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

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

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

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

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

Interleaved Vision-and-Language Generation via Generative Voken

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

Direct Visual Grounding by Directing Attention of Visual Tokens

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

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

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

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

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

BrightRate: Quality Assessment for User-Generated HDR Videos

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

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

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

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

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

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

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

Safe Vision-Language Models via Unsafe Weights Manipulation

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

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

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

Unsupervised Segmentation by Diffusing, Walking and Cutting

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

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

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

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

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

Comp4D: Compositional 4D Scene Generation

Layout Anything: One Transformer for Universal Room Layout Estimation

GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction

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

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

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

Line Art Colorization with Offset Prior-based Diffusion Model

STRinGS: Selective Text Refinement in Gaussian Splatting

Remote Sensing Forestry Similarity Convolution

DreamAnywhere: Object-Centric Panoramic 3D Scene Generation

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

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

RemEdit: Efficient Diffusion Editing with Riemannian Geometry

Food Image Generation on Multi-Noun Categories

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

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

Equivariant Sampling for Improving Diffusion Model-based Image Restoration

FlowEO: Generative Unsupervised Domain Adaptation for Earth Observation

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

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

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

HiMix : Hierarchical Visual-Textual Mixing Network for Lesion Segmentation

Visibility guided Self-Supervised Occlusion Resilient Human Pose Estimation

MageBench: Bridging Large Multimodal Models to Agents

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

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

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

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

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

Fast Vision Mamba: Pooling Spatial Dimensions for Accelerated Processing

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

OpenCowID: Zero-Shot Visual Identification of Dairy Cows

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

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

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

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

CoreCaption: Core Caption based Text-to-Video Retrieval

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

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

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

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

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

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

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

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

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

CRISP: Cylindrical Rendering for In-Stream Point Clouds

Cluster-Guided Adversarial Perturbations for Robust Contrastive Learning

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

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

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

MarineEval: Assessing the Marine Intelligence of Vision-Language Models

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

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

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

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

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

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

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

Hierarchical Adaptive networks with Task vectors for Test-Time Adaptation

GFT: Graph Feature Tuning for Efficient Point Cloud Analysis

IPCD: Intrinsic Point-Cloud Decomposition

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

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

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

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

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

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

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

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

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

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

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

Extreme Amodal Face Detection

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

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

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

Harnessing Object Grounding for Time-Sensitive Video Understanding

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

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

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

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

DreamCatcher: Efficient Multi-Concept Customization via Representation Finetuning

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

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

FlyPose: Towards Robust Human Pose Estimation From Aerial Views

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

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

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

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

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

Zero-Shot Video Deraining with Video Diffusion Models

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

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

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

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

GAEA: A Geolocation Aware Conversational Assistant

Leveraging Sparsity for Privacy in Collaborative Inference

Optimizing LVLMs with On-Policy Data for Effective Hallucination Mitigation

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

Any Detector Can Detect Anything

Diffusion-Based Action Recognition Generalizes to Untrained Domains

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

Multimodal Medical Image Binding via Shared Text Embeddings

ATM: Enhanced Alignment for Text-to-Motion Generation

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

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

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

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

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

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

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

SeqFeedNet: Sequential Feature Feedback Network for Background Subtraction

Locally Explaining Prediction Behavior via Gradual Interventions and Measuring Property Gradients

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

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

Human Pose Aggregation for Multi-View Temporal Video Alignment

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

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

Timestamp Query Transformer for Temporal Action Segmentation

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

Adaptive Residual Graph Attention for Contrastive Multimodal Representation Learning

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

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

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

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

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

Towards Unconstrained Cross-View Pose Estimation

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

ProSkill: Segment-Level Skill Assessment in Procedural Videos

Towards Fast and Scalable Normal Integration using Continuous Components

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

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

QCFace: Image Quality Control for boosting Face Representation & Recognition

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

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

LightGazeNet: A Lightweight GNN-based Architecture for Gaze Estimation

CalibBEV: LiDAR-Camera Calibration via BEV Alignment

High-Rate Mixout: Revisiting Mixout for Robust Domain Generalization

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

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

RAVU: Retrieval Augmented Video Understanding with Compositional Reasoning over Graph

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

Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory

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

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

LASER: Lip Landmark Assisted Speaker Detection for Robustness

Temporal Object Captioning for Street Scene Videos from LiDAR Tracks

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

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

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

Zero‑Shot Domain Generalisation via Prompt-Driven Feature Refinement

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

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

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

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

brat: Aligned Multi-View Embeddings for Brain MRI Analysis

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

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

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

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

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

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

Rethinking Latent Variable in Learned Image Compression

One-Cycle Structured Pruning via Stability-Driven Subnetwork Search

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

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

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

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

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

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

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