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/CT-Net Ensemble (R50, 8+12+16+24)

CT-Net Ensemble (R50, 8+12+16+24)

Reported on 10 benchmarks across 2 tasks · 1 paper · 4 SOTA

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

Robots5 results

Activity RecognitiononSomething-Something V2
GFLOPs· uses extra data· 2021-06-03
280
best: 13321 (InternVideo2-6B)
SOTA
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Activity RecognitiononSomething-Something V2
Parameters· uses extra data· 2021-06-03
83.8
best: 2131 (InternVideo2-6B)
SOTA
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Activity RecognitiononSomething-Something V1
Top 1 Accuracy· 2021-06-03
56.6
best: 70 (InternVideo)
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-06-03
67.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-06-03
91.1
best: 96.3 (DejaVid)
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603

Time Series5 results

Action RecognitiononSomething-Something V2
GFLOPs· uses extra data· 2021-06-03
280
best: 13321 (InternVideo2-6B)
SOTA
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Action RecognitiononSomething-Something V2
Parameters· uses extra data· 2021-06-03
83.8
best: 2131 (InternVideo2-6B)
SOTA
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Action RecognitiononSomething-Something V1
Top 1 Accuracy· 2021-06-03
56.6
best: 70 (InternVideo)
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-06-03
67.8
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-06-03
91.1
best: 96.3 (DejaVid)
CT-Net: Channel Tensorization Network for Video Classification arXiv:2106.01603