In this competitive world, the supervision and monitoring of human resources are primary
and necessary tasks to drive context-aware applications. Advancement in sensor and …

Contrastive language-image pretraining has shown great success in learning visual-textual
joint representation from web-scale data, demonstrating remarkable “zero-shot” …

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP
model. Since training on a similar scale for videos is infeasible, recent approaches focus on …

An integral part of video analysis and surveillance is temporal activity detection, which
means to simultaneously recognize and localize activities in long untrimmed videos …

Adopting contrastive image-text pretrained models like CLIP towards video classification has
gained attention due to its cost-effectiveness and competitive performance. However, recent …

Video action recognition is one of the representative tasks for video understanding. Over the
last decade, we have witnessed great advancements in video action recognition thanks to …

Zero-shot learning strives to classify unseen categories for which no data is available during
training. In the generalized variant, the test samples can further belong to seen or unseen …

Video classification has achieved remarkable success in recent years, driven by advanced
deep learning models that automatically categorize video content. This paper provides a …

The growing number of action classes has posed a new challenge for video understanding,
making Zero-Shot Action Recognition (ZSAR) a thriving direction. The ZSAR task aims to …

Analyzing videos of human actions involves understanding the temporal relationships
among video frames. State-of-the-art action recognition approaches rely on traditional …