Abstract Video Anomaly Detection (VAD) is crucial for applications such as security
surveillance and autonomous driving. However, existing VAD methods provide little …

Temporal Action Localization (TAL) involves localizing and classifying action snippets in an
untrimmed video. The emergence of large video foundation models has led RGB-only video …

In this work, we introduce (a) the new problem of anticipating object state changes in images
and videos during procedural activities,(b) new curated annotation data for object state …

This paper presents the first-ever study of adapting compressed image latents to suit the
needs of downstream vision tasks that adopt Multimodal Large Language Models (MLLMs) …

Accurate prediction of human behavior is crucial for AI systems to effectively support real-
world applications, such as autonomous robots anticipating and assisting with human tasks …

Predicting future human behavior is an increasingly popular topic in computer vision, driven
by the interest in applications such as autonomous vehicles, digital assistants and human …

Egocentric vision captures the scene from the point of view of the camera wearer while
exocentric vision captures the overall scene context. Jointly modeling ego and exo views is …

Our work addresses the problem of stochastic long-term dense anticipation. The goal of this
task is to predict actions and their durations several minutes into the future based on …

We have witnessed impressive advances in video action understanding. Increased dataset
sizes, variability, and computation availability have enabled leaps in performance and task …