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/DSNet

DSNet

Reported on 10 benchmarks across 4 tasks · 1 paper

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

Computer Vision16 results

  • VideoonTvSum
    F1-score (Augmented)· uses extra data
    63.9
    best: 69 (CLIP-It)
  • VideoonTvSum
    F1-score (Canonical)· uses extra data
    62.1
    best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
  • VideoonSumMe
    F1-score (Augmented)
    53.3
    best: 56.9 (iPTNet)
  • VideoonSumMe
    F1-score (Canonical)
    53
    best: 57.1 (PGL-SUM (maximum learning capacity))
  • VideoonTvSum
    F1-score (Augmented)
    63.9
    best: 69 (CLIP-It)
  • VideoonTvSum
    F1-score (Canonical)
    62.1
    best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
  • VideoonSumMe
    F1-score (Augmented)
    50.7
    best: 56.9 (iPTNet)
  • VideoonSumMe
    F1-score (Canonical)
    50.2
    best: 57.1 (PGL-SUM (maximum learning capacity))
  • Video SummarizationonTvSum
    F1-score (Augmented)· uses extra data
    63.9
    best: 69 (CLIP-It)
  • Video SummarizationonTvSum
    F1-score (Canonical)· uses extra data
    62.1
    best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
  • Video SummarizationonSumMe
    F1-score (Augmented)
    53.3
    best: 56.9 (iPTNet)
  • Video SummarizationonSumMe
    F1-score (Canonical)
    53
    best: 57.1 (PGL-SUM (maximum learning capacity))
  • Video SummarizationonTvSum
    F1-score (Augmented)
    63.9
    best: 69 (CLIP-It)
  • Video SummarizationonTvSum
    F1-score (Canonical)
    62.1
    best: 67.5 (MAVS [DBLP:conf/mm/FengLKZ18])
  • Video SummarizationonSumMe
    F1-score (Augmented)
    50.7
    best: 56.9 (iPTNet)
  • Video SummarizationonSumMe
    F1-score (Canonical)
    50.2
    best: 57.1 (PGL-SUM (maximum learning capacity))

Medical1 result

  • Semantic SegmentationonCityscapes val
    Frame (fps)· 2024-06-06
    81.9
    best: 163.9 (FasterSeg)
    DSNet: A Novel Way to Use Atrous Convolutions in Semantic SegmentationarXiv:2406.03702

Audio1 result

  • 10-shot image generationonCityscapes val
    Frame (fps)· 2024-06-06
    81.9
    best: 163.9 (FasterSeg)
    DSNet: A Novel Way to Use Atrous Convolutions in Semantic SegmentationarXiv:2406.03702