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/UniMSE

UniMSE

Reported on 14 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.

Natural Language Processing10 results

  • Sentiment AnalysisonMOSI
    Accuracy· 2022-11-21
    86.9
    best: 90.35 (MMML)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonMOSI
    F1 score· 2022-11-21
    86.42
    best: 90.35 (MMML)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSEI
    Accuracy· uses extra data· 2022-11-21
    87.5
    best: 88.62 (SeMUL-PCD)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSEI
    F1· uses extra data· 2022-11-21
    87.46
    best: 89.04 (SeMUL-PCD)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSEI
    MAE· uses extra data· 2022-11-21
    0.523
    best: 0.5072 (MMML)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSI
    Acc-2· 2022-11-21
    86.9
    best: 90.35 (MMML)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSI
    Acc-7· 2022-11-21
    48.68
    best: 52.72 (MMML)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSI
    Corr· 2022-11-21
    0.809
    best: 0.8824 (MMML)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSI
    F1· 2022-11-21
    86.42
    best: 90.35 (MMML)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Sentiment AnalysisonCMU-MOSI
    MAE· 2022-11-21
    0.691
    best: 0.5573 (MMML)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256

Audio4 results

  • Emotion RecognitiononIEMOCAP
    Accuracy· 2022-11-21
    70.56
    best: 73.95 (SDT)
    SOTA
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Emotion RecognitiononMELD
    Accuracy· 2022-11-21
    65.09
    best: 68.7 (ELR-GNN)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Emotion RecognitiononMELD
    Weighted-F1· 2022-11-21
    65.51
    best: 69.9 (ELR-GNN)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256
  • Emotion RecognitiononIEMOCAP
    Weighted-F1· 2022-11-21
    70.66
    best: 74.08 (SDT)
    UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion RecognitionarXiv:2211.11256