Skip to main content

and
  1. No Access

    Chapter and Conference Paper

    Weakly-Supervised Temporal Action Localization with Regional Similarity Consistency

    The weakly-supervised temporal action localization task aims to train a model that can accurately locate each action instance in the video using only video-level class labels. The existing methods take into ac...

    Haoran Ren, Hao Ren, Hong Lu, Cheng ** in MultiMedia Modeling (2023)

  2. No Access

    Chapter and Conference Paper

    Weakly-Supervised Temporal Action Localization with Multi-Head Cross-Modal Attention

    Weakly-supervised temporal action localization seeks to localize temporal boundaries of actions while concurrently identifying their categories using only video-level category labels during training. Among the...

    Hao Ren, Haoran Ren, Wu Ran, Hong Lu in PRICAI 2022: Trends in Artificial Intellig… (2022)