Zero-shot video action recognition has advanced significantly due to the adaptation of visual-
language models, such as CLIP, to video domains. However, existing methods attempt to …

The video recognition community is undergoing a significant change in backbone shifting
from CNNs to transformers. However, due to the temporal information existing in the video …

Recognizing video actions in the wild is challenging for visual control systems. In-the-wild
videos show actions not seen in training data, recorded from various angles and scenes with …

As a focal point of research in various fields, human body language understanding has long
been a subject of intense interest. Within this realm, the exploration of emotion recognition …

Skeleton-based multi-entity action recognition is a challenging task aiming to identify
interactive actions or group activities involving multiple diverse entities. Existing models for …

The automatic recognition and quantitative analysis of abnormal behavior in mice play a
crucial role in behavioral observation experiments in neuroscience, pharmacology, and …

Current approaches using sequential networks have shown promise in estimating field
variables for dynamical systems, but they are often limited by high rollout errors. The …

This paper describes an innovative methodology for predicting penalty kicks in football
based on the pose estimation of the kicker. Our proposal starts with the construction of a …

Recent breakthroughs in video models have achieved remarkable success by integrating
vision transformers into the video domain through adaptation. However, prevalent …

Understanding human actions through the analysis of egocentric videos is a desirable
capability of intelligent agents, and is a research area that has gained popularity recently …