你即將離開本站

並前往https://papers.nips.cc/paper/2021/hash/792dd774336314c3c27a04bb260cf2cf-Abstract.html

Look at What I'm Doing: Self-Supervised Spatial Grounding of ...

We demonstrate the effectiveness of our approach by self-training on the HowTo100M instructional video dataset and evaluating on a newly collected dataset ...

確定！ 回上一頁

查詢 「HowTo100M」的人也找了：

  1. HowTo100M
    2.
  2. HowTo100M github
    3.
  3. Youcook2
    4.
  4. End to end learning of visual representations from uncurated instructional videos
    5.
  5. Video feature extraction
    6.
  6. MSR-VTT
    7.
  7. Kinetics dataset
    8.
  8. Video retrieval
    9.