Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TCN

TCN

Reported on 31 benchmarks across 13 tasks · 7 papers · 15 SOTA

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

Computer Vision13 results

Surgical phase recognitiononCholec80
F1· 2020-03-24
80.3
best: 90.24 (LoViT)
SOTA
TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks arXiv:2003.10751
Video UnderstandingonUPenn Action
Kendall's Tau· 2017-04-23
0.7353
best: 0.7672 (TCC + TCN)
SOTA
Time-Contrastive Networks: Self-Supervised Learning from Video arXiv:1704.06888
VideoonUPenn Action
Kendall's Tau· 2017-04-23
0.7353
best: 0.7672 (TCC + TCN)
SOTA
Time-Contrastive Networks: Self-Supervised Learning from Video arXiv:1704.06888
VideoonNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Temporal Action LocalizationonNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action LocalizationonNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action LocalizationonJIGSAWS
Accuracy· 2016-08-29
81.4
best: 82.9 (TricorNet)
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action LocalizationonJIGSAWS
Edit Distance· 2016-08-29
83.1
best: 88.53 (RL+Tree)
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action SegmentationonJIGSAWS
Accuracy· 2016-08-29
81.4
best: 82.9 (TricorNet)
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action SegmentationonJIGSAWS
Edit Distance· 2016-08-29
83.1
best: 88.53 (RL+Tree)
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
VideoonNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516
Temporal Action LocalizationonNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516
Action LocalizationonNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516

Methodology5 results

Zero-Shot LearningonNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Zero-Shot LearningonCUB-200-2011
average top-1 classification accuracy· 2019-08-16
59.5
best: 87.5 (ZeroDiff)
Transferable Contrastive Network for Generalized Zero-Shot Learning arXiv:1908.05832
Zero-Shot LearningonSUN Attribute
average top-1 classification accuracy· 2019-08-16
61.5
best: 77.3 (ZeroDiff)
Transferable Contrastive Network for Generalized Zero-Shot Learning arXiv:1908.05832
Zero-Shot LearningonSUN Attribute
Harmonic mean· 2019-08-16
34
best: 59.8 (ZeroDiff)
Transferable Contrastive Network for Generalized Zero-Shot Learning arXiv:1908.05832
Zero-Shot LearningonNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516

Time Series4 results

Action DetectiononNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action RecognitiononNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 99.6 (PoseC3D (RGB + Pose))
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Action DetectiononNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516
Action RecognitiononNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 97.4 (DSCNet (RGB + Pose))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516

Music4 results

Music ModelingonNottingham
NLL· 2019-11-14
2.783
best: 4.05 (RNN)
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling arXiv:1911.06393
Music ModelingonJSB Chorales
NLL· 2019-11-14
8.154
best: 8.54 (GRU)
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling arXiv:1911.06393
Music ModelingonNottingham
NLL· 2018-03-04
3.07
best: 4.05 (RNN)
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling arXiv:1803.01271
Music ModelingonJSB Chorales
NLL· 2018-03-04
8.1
best: 8.54 (GRU)
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling arXiv:1803.01271

Medical3 results

Language ModellingonPenn Treebank (Word Level)
Test perplexity· 2019-11-14
108.47
best: 20.5 (GPT-3 (Zero-Shot))
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling arXiv:1911.06393
Language ModellingonPenn Treebank (Character Level)
Bit per Character (BPC)· 2019-11-14
1.31
best: 1.38 (Bipartite Flow)
Seq-U-Net: A One-Dimensional Causal U-Net for Efficient Sequence Modelling arXiv:1911.06393
Language ModellingonWikiText-103
Test perplexity· 2018-03-04
45.19
best: 2.4 (RETRO (7.5B))
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling arXiv:1803.01271

Robots2 results

Activity RecognitiononNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 99.6 (PoseC3D (RGB + Pose))
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
Activity RecognitiononNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 97.4 (DSCNet (RGB + Pose))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516

Natural Language Processing2 results

3D Action RecognitiononNTU RGB+D
Accuracy (CV)· 2016-08-29
83.1
best: 98.3 (ST-GCN [PYSKL, 2D Skeleton])
SOTA
Temporal Convolutional Networks: A Unified Approach to Action Segmentation arXiv:1608.08242
3D Action RecognitiononNTU RGB+D
Accuracy (CS)· 2017-04-14
74.3
best: 94.3 (Hulk(Finetune, ViT-L))
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks arXiv:1704.04516