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/C3D

C3D

Reported on 13 benchmarks across 4 tasks · 1 paper · 6 SOTA

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

Time Series7 results

Action RecognitiononSports-1M
Clip Hit@1· 2014-12-02
46.1
best: 57 (R[2+1]D-RGB-32frame)
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Action RecognitiononSports-1M
Video hit@1 · 2014-12-02
61.1
best: 75.5 (ip-CSN-152 (RGB))
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Action RecognitiononSports-1M
Video hit@5· 2014-12-02
85.5
best: 92.8 (ip-CSN-152 (RGB))
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Action RecognitiononHMDB-51
Average accuracy of 3 splits· 2014-12-02
51.6
best: 88.7 (VideoMAE V2-g)
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Action RecognitiononUCF101
3-fold Accuracy· 2014-12-02
82.3
best: 99.7 (FTP-UniFormerV2-L/14)
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Action DetectiononRHM
Accuracy (Top-1)
70.3
best: 71.06 (Dual-Stream C3D)
Human Activity RecognitiononRHM
Accuracy (Top-1)
70.3
best: 71.06 (Dual-Stream C3D)

Robots6 results

Activity RecognitiononSports-1M
Clip Hit@1· 2014-12-02
46.1
best: 57 (R[2+1]D-RGB-32frame)
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Activity RecognitiononSports-1M
Video hit@1 · 2014-12-02
61.1
best: 75.5 (ip-CSN-152 (RGB))
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Activity RecognitiononSports-1M
Video hit@5· 2014-12-02
85.5
best: 92.8 (ip-CSN-152 (RGB))
SOTA
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Activity RecognitiononHMDB-51
Average accuracy of 3 splits· 2014-12-02
51.6
best: 88.7 (VideoMAE V2-g)
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Activity RecognitiononUCF101
3-fold Accuracy· 2014-12-02
82.3
best: 99.7 (FTP-UniFormerV2-L/14)
Learning Spatiotemporal Features with 3D Convolutional Networks arXiv:1412.0767
Activity RecognitiononRHM
Accuracy (Top-1)
70.3
best: 71.06 (Dual-Stream C3D)