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/MS-TCN (I3D)

MS-TCN (I3D)

Reported on 12 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.

Computer Vision12 results

Action LocalizationonBreakfast
Acc· 2019-03-05
66.3
best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
SOTA
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action LocalizationonBreakfast
Edit· 2019-03-05
61.7
best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
SOTA
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
Acc· 2019-03-05
66.3
best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
SOTA
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
Edit· 2019-03-05
61.7
best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
SOTA
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action LocalizationonBreakfast
Average F1· 2019-03-05
46.2
best: 76.2 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action LocalizationonBreakfast
F1@10%· 2019-03-05
52.6
best: 82.1 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action LocalizationonBreakfast
F1@25%· 2019-03-05
48.1
best: 79 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action LocalizationonBreakfast
F1@50%· 2019-03-05
37.9
best: 67.5 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
Average F1· 2019-03-05
46.2
best: 76.2 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
F1@10%· 2019-03-05
52.6
best: 82.1 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
F1@25%· 2019-03-05
48.1
best: 79 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945
Action SegmentationonBreakfast
F1@50%· 2019-03-05
37.9
best: 67.5 (AdaFocus (newly extracted I3D-features, LT-Context model))
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation arXiv:1903.01945