Understanding human behavior and activity facilitates advancement of numerous real-world
applications, and is critical for video analysis. Despite the progress of action recognition …

Derived from rapid advances in computer vision and machine learning, video analysis tasks
have been moving from inferring the present state to predicting the future state. Vision-based …

Abstract We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm
for online action detection, which employs a long-and short-term memory mechanism to …

Most existing forecasting systems are memory-based methods, which attempt to mimic
human forecasting ability by employing various memory mechanisms and have progressed …

Spatio-temporal video grounding aims to localize the aligned visual tube corresponding to a
language query. Existing techniques achieve such alignment by exploiting dense boundary …

Human activity recognition (HAR) is a complex and multifaceted problem. The research
community has reported numerous approaches to perform HAR. Along with HAR …

We present a novel method for weakly-supervised action segmentation and unseen error
detection in anomalous instructional videos. In the absence of an appropriate dataset for this …

Automatically predicting the emotions of user-generated videos (UGVs) receives increasing
interest recently. However, existing methods mainly focus on a few key visual frames, which …

Video anomaly detection (VAD) has been extensively studied for static cameras but is much
more challenging in egocentric driving videos where the scenes are extremely dynamic …

Online action detection is the task of predicting the action as soon as it happens in a
streaming video. A major challenge is that the model does not have access to the future and …