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/MFNet

MFNet

Reported on 27 benchmarks across 8 tasks · 2 papers · 3 SOTA

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

Computer Vision7 results

  • Action Recognition In VideosonJester (Gesture Recognition)
    Val· 2018-07-26
    96.68
    best: 96.7 (CPNet Res34, 5 CP)
    SOTA
    Motion Feature Network: Fixed Motion Filter for Action RecognitionarXiv:1807.10037
  • VideoonKinetics-400
    Acc@1· 2018-07-30
    72.8
    best: 93.6 (OmniVec2)
    Multi-Fiber Networks for Video RecognitionarXiv:1807.11195
  • VideoonKinetics-400
    Acc@5· 2018-07-30
    90.4
    best: 98.9 (TubeViT-H (ImageNet-1k))
    Multi-Fiber Networks for Video RecognitionarXiv:1807.11195
  • Scene SegmentationonNoisy RS RGB-T Dataset
    mIoU
    33.1
    best: 60.3 (CMNeXt (B4))
  • Scene SegmentationonKP day-night
    mIoU
    24
    best: 57.6 (HAPNet)
  • Scene SegmentationonPST900
    mIoU
    57
    best: 89.8 (SHIFNet)
  • Scene SegmentationonMFN Dataset
    mIOU
    39.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))

Medical7 results

  • Semantic SegmentationonSYN-UDTIRI
    IoU
    87.7
    best: 94.11 (RoadFormer+ (B))
  • Semantic Segmentationon Synthetic Bathing Perception
    mIoU
    87.25
    best: 94.2 (CMX-SRA)
  • Semantic SegmentationonGAMUS
    mIoU
    52.73
    best: 76.38 (TIMF)
  • Semantic SegmentationonNoisy RS RGB-T Dataset
    mIoU
    33.1
    best: 60.3 (CMNeXt (B4))
  • Semantic SegmentationonKP day-night
    mIoU
    24
    best: 57.6 (HAPNet)
  • Semantic SegmentationonPST900
    mIoU
    57
    best: 89.8 (SHIFNet)
  • Semantic SegmentationonMFN Dataset
    mIOU
    39.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))

Audio7 results

  • 10-shot image generationonSYN-UDTIRI
    IoU
    87.7
    best: 94.11 (RoadFormer+ (B))
  • 10-shot image generationon Synthetic Bathing Perception
    mIoU
    87.25
    best: 94.2 (CMX-SRA)
  • 10-shot image generationonGAMUS
    mIoU
    52.73
    best: 76.38 (TIMF)
  • 10-shot image generationonNoisy RS RGB-T Dataset
    mIoU
    33.1
    best: 60.3 (CMNeXt (B4))
  • 10-shot image generationonKP day-night
    mIoU
    24
    best: 57.6 (HAPNet)
  • 10-shot image generationonPST900
    mIoU
    57
    best: 89.8 (SHIFNet)
  • 10-shot image generationonMFN Dataset
    mIOU
    39.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))

Methodology4 results

  • 2D Object DetectiononNoisy RS RGB-T Dataset
    mIoU
    33.1
    best: 60.3 (CMNeXt (B4))
  • 2D Object DetectiononKP day-night
    mIoU
    24
    best: 57.6 (HAPNet)
  • 2D Object DetectiononPST900
    mIoU
    57
    best: 89.8 (SHIFNet)
  • 2D Object DetectiononMFN Dataset
    mIOU
    39.7
    best: 62.7 (RoadFormer+ (ConvNeXt-L))

Robots1 result

  • Activity RecognitiononJester (Gesture Recognition)
    Val· 2018-07-26
    96.68
    best: 98.15 (DirecFormer)
    SOTA
    Motion Feature Network: Fixed Motion Filter for Action RecognitionarXiv:1807.10037

Time Series1 result

  • Action RecognitiononJester (Gesture Recognition)
    Val· 2018-07-26
    96.68
    best: 98.15 (DirecFormer)
    SOTA
    Motion Feature Network: Fixed Motion Filter for Action RecognitionarXiv:1807.10037