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 …

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 …

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 …

Temporal action proposal generation is an important and challenging task in video
understanding, which aims at detecting all temporal segments containing action instances of …

Temporal action proposal generation is an important yet challenging problem, since
temporal proposals with rich action content are indispensable for analysing real-world …

We propose TAL-Net, an improved approach to temporal action localization in video that is
inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key …