Although action recognition systems can achieve top performance when evaluated on in-
distribution test points, they are vulnerable to unanticipated distribution shifts in test data …

Self-supervised approaches for video have shown impressive results in video
understanding tasks. However, unlike early works that leverage temporal self-supervision …

Video Foundation Models (ViFMs) aim to develop general-purpose representations for
various video understanding tasks by leveraging large-scale datasets and powerful models …

Temporal action detection (TAD) aims to locate action positions and recognize action
categories in long-term untrimmed videos. Although many methods have achieved …

Recognizing and comprehending human actions and gestures is a crucial perception
requirement for robots to interact with humans and carry out tasks in diverse domains …

Video self-supervised learning (VSSL) has made significant progress in recent years.
However, the exact behavior and dynamics of these models under different forms of …

Test-time adaptation (TTA) aims at boosting the generalization capability of a trained model
by conducting self-/un-supervised learning during testing in real-world applications. Though …

Abstract Human Action Recognition (HAR) is a challenging domain in computer vision,
involving recognizing complex patterns by analyzing the spatiotemporal dynamics of …

The performance of trained deep neural network (DNN) models relies on the assumption
that the test data has largely the same feature distribution as the training data. In deployed …

With the growth of high-quality data and advancement in visual pre-training paradigms,
Video Foundation Models (VFMs) have made significant progress recently, demonstrating …