Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos.
, , , , , and .
(2019)cite arxiv:1901.06829Comment: AAAI 2019.

The task of video grounding, which temporally localizes a natural language description in a video, plays an important role in understanding videos. Existing studies have adopted strategies of sliding window over the entire video or exhaustively ranking all possible clip-sentence pairs in a pre-segmented video, which inevitably suffer from exhaustively enumerated candidates. To alleviate this problem, we formulate this task as a problem of sequential decision making by learning an agent which regulates the temporal grounding boundaries progressively based on its policy. Specifically, we propose a reinforcement learning based framework improved by multi-task learning and it shows steady performance gains by considering additional supervised boundary information during training. Our proposed framework achieves state-of-the-art performance on ActivityNet'18 DenseCaption dataset and Charades-STA dataset while observing only 10 or less clips per video.
  • @nmatsuk
  • @dblp

rating distribution
average user rating3.0 out of 5.0 based on 1 review
  • userPicture
    18 days ago
Please log in to take part in the discussion (add own reviews or comments).