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/CMN

CMN

Reported on 10 benchmarks across 4 tasks · 1 paper · 3 SOTA

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

Natural Language Processing3 results

  • Visual Question Answering (VQA)onVisual Genome (subjects)
    Percentage correct· 2016-11-30
    44.24
    SOTA
    Modeling Relationships in Referential Expressions with Compositional Modular NetworksarXiv:1611.09978
  • Visual Question Answering (VQA)onVisual Genome (pairs)
    Percentage correct· 2016-11-30
    28.52
    SOTA
    Modeling Relationships in Referential Expressions with Compositional Modular NetworksarXiv:1611.09978
  • Visual Question Answering (VQA)onVisual7W
    Percentage correct· 2016-11-30
    72.53
    SOTA
    Modeling Relationships in Referential Expressions with Compositional Modular NetworksarXiv:1611.09978

Audio3 results

  • Emotion RecognitiononIEMOCAP
    Accuracy
    56.32
    best: 73.95 (SDT)
  • Emotion RecognitiononIEMOCAP
    Macro-F1
    54.84
    best: 66.38 (M2FNet-Text)
  • Emotion RecognitiononIEMOCAP
    Weighted-F1
    56.19
    best: 74.08 (SDT)

Robots2 results

  • Activity RecognitiononMOMA-LRG
    Activity Classification Accuracy (5-shot 5-way)
    86.3
    best: 97.9 (Name Tuning)
  • Activity RecognitiononMOMA-LRG
    Subactivity Classification Accuracy (5-shot 5-way)
    66.6
    best: 78.2 (Name Tuning)

Time Series2 results

  • Action RecognitiononMOMA-LRG
    Activity Classification Accuracy (5-shot 5-way)
    86.3
    best: 97.9 (Name Tuning)
  • Action RecognitiononMOMA-LRG
    Subactivity Classification Accuracy (5-shot 5-way)
    66.6
    best: 78.2 (Name Tuning)