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

Self-attention based Transformer models have demonstrated impressive results for image
classification and object detection, and more recently for video understanding. Inspired by …

Image-based visual-language (I-VL) pre-training has shown great success for learning joint
visual-textual representations from large-scale web data, revealing remarkable ability for …

Abstract Temporal Action Detection (TAD) aims to accurately capture each action interval in
an untrimmed video and to understand human actions. This paper comprehensively surveys …

While large-scale image-text pretrained models such as CLIP have been used for multiple
video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos …

Weakly-supervised temporal action localization aims to localize and recognize actions in
untrimmed videos with only video-level category labels during training. Without instance …

Temporal action proposal generation is an challenging and promising task which aims to
locate temporal regions in real-world videos where action or event may occur. Current …

Temporal action detection is a fundamental yet challenging task in video understanding.
Video context is a critical cue to effectively detect actions, but current works mainly focus on …

Most state-of-the-art action localization systems process each action proposal individually,
without explicitly exploiting their relations during learning. However, the relations between …

Temporally locating and classifying action segments in long untrimmed videos is of
particular interest to many applications like surveillance and robotics. While traditional …