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/Dense IndRNN

Dense IndRNN

Reported on 18 benchmarks across 9 tasks · 1 paper

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

Computer Vision6 results

  • VideoonNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • VideoonNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Temporal Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Action LocalizationonNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Action LocalizationonNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251

Time Series4 results

  • Action DetectiononNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Action DetectiononNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 97.4 (DSCNet (RGB + Pose))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 99.6 (PoseC3D (RGB + Pose))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251

Methodology2 results

  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Zero-Shot LearningonNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251

Robots2 results

  • Activity RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 97.4 (DSCNet (RGB + Pose))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Activity RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 99.6 (PoseC3D (RGB + Pose))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251

Medical2 results

  • Language ModellingonPenn Treebank (Word Level)
    Test perplexity· 2019-10-11
    56.37
    best: 20.5 (GPT-3 (Zero-Shot))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • Language ModellingonPenn Treebank (Character Level)
    Bit per Character (BPC)· 2019-10-11
    1.18
    best: 1.38 (Bipartite Flow)
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251

Natural Language Processing2 results

  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CS)· 2019-10-11
    86.7
    best: 94.3 (Hulk(Finetune, ViT-L))
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251
  • 3D Action RecognitiononNTU RGB+D
    Accuracy (CV)· 2019-10-11
    93.97
    best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
    Deep Independently Recurrent Neural Network (IndRNN)arXiv:1910.06251