Keynote Tue, Mar 10, 2026 • 8:30 AM – 9:30 AM PDT

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

Hilde Kühne

Abstract

Understanding human actions and events from video has long been a central challenge in computer vision, driven by the fundamental difficulty of making sense of images over time over time. This keynote covers the history of action recognition and video understanding through the lens of the field’s most persistent obstacles. It begins with early approaches that relied on carefully engineered spatiotemporal features, where the core challenge was how to represent motion, dynamics, and temporal structure in a form suitable for learning. After that we will cover how the rise of CNNs brought the shift from handcrafted features to data-driven representations but also how progress became coupled to the availability, scale, and diversity of video datasets and the practical limits this imposed on training deep models. The talk concludes with the current challenges of the field—aligning video with language—where the problem extends beyond recognition to semantic grounding, multimodal representation learning, and reasoning across visual, temporal, and linguistic abstractions. It shows that while video understanding matured the challenge of making sense of visual data over time persisted. By revisiting the history of these challenges, this keynote aims to clarify how past constraints influence today’s solutions and to provide perspective on the open problems that will define the next generation of video understanding systems.

Speaker

Hilde Kühne

Prof. Dr. Hilde Kuehne is a Professor of Multimodal Learning at the Tübingen AI Center and an affiliated professor at the MIT–IBM Watson AI Lab. Previously, she was a Professor of Computer Vision and Multimodal Learning at the University of Bonn. She received her PhD from the cv:hci lab at the Karlsruhe Institute of Technology (KIT), where she was supervised by Rainer Stiefelhagen, and subsequently held postdoctoral positions at Fraunhofer FKIE and in the Computer Vision Group led by Prof. Jürgen Gall. Her research focuses on video understanding, with a particular emphasis on learning without labels and multimodal video understanding. She has created several highly cited datasets and foundational works for analyzing large collections of untrimmed video data, including HMDB51, which was awarded both the ICCV 2021 Helmholtz Prize and the PAMI Mark Everingham Prize. Prof. Kuehne currently serves as an Associate Editor for IEEE Transactions on Pattern Analysis and Machine Intelligence. She was Program Chair for WACV 2024, General Chair for ICCV 2025, and regularly serves as an Area Chair for major conferences such as CVPR, ICCV, ECCV, and WACV. She is strongly committed to increasing diversity in the field and is an active supporter of the Women in Computer Vision initiative.