你即將離開本站

並前往http://www.joonseok.net/papers/maqa.pdf

MAQA: A Multimodal QA Benchmark for Negation

This benchmark is created from labeled videos in the music-related portion of AudioSet (Gemmeke et al., 2017). While the original benchmarks features 5000 hours ...

確定！ 回上一頁

查詢 「Audioset benchmark」的人也找了：

  1. AudioSet download
    2.
  2. Sound dataset
    3.
  3. Audio classification
    4.
  4. FSD50K
    5.
  5. Keyword spotting benchmark
    6.
  6. Audio Set: an ontology and human-labeled dataset for audio events
    7.
  7. Esc 50 leaderboard
    8.
  8. Audio machine learning
    9.