TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/PDVC (TSP features, no SCST)

PDVC (TSP features, no SCST)

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision8 results

  • Video CaptioningonActivityNet Captions
    BLEU-4· 2021-08-17
    2.17
    best: 9.45 (ADV-INF + Global)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Video CaptioningonActivityNet Captions
    CIDEr· 2021-08-17
    31.14
    best: 39.3 (VideoCoCa)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Video CaptioningonActivityNet Captions
    SODA· 2021-08-17
    6.05
    best: 7.11 (GVL)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Dense Video CaptioningonActivityNet Captions
    BLEU-4· 2021-08-17
    2.17
    best: 9.45 (ADV-INF + Global)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Dense Video CaptioningonActivityNet Captions
    CIDEr· 2021-08-17
    31.14
    best: 33.33 (GVL)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Dense Video CaptioningonActivityNet Captions
    SODA· 2021-08-17
    6.05
    best: 7.11 (GVL)
    SOTA
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Video CaptioningonActivityNet Captions
    METEOR· 2021-08-17
    9.03
    best: 17.97 (VLTinT (ae-test split) C3D/Ling)
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781
  • Dense Video CaptioningonActivityNet Captions
    METEOR· 2021-08-17
    9.03
    best: 17 (Vid2Seq)
    End-to-End Dense Video Captioning with Parallel DecodingarXiv:2108.07781