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/DTGRM

DTGRM

Reported on 22 benchmarks across 2 tasks · 1 paper

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

Computer Vision22 results

Action Localizationon50 Salads
Acc· 2020-12-14
80
best: 91.4 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Localizationon50 Salads
Edit· 2020-12-14
72
best: 89.1 (Semantic2Graph)
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Localizationon50 Salads
F1@10%· 2020-12-14
79.1
best: 92.7 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Localizationon50 Salads
F1@25%· 2020-12-14
75.9
best: 91.6 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Localizationon50 Salads
F1@50%· 2020-12-14
66.1
best: 88.5 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
Acc· 2020-12-14
68.3
best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
Average F1· 2020-12-14
59.1
best: 76.2 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
Edit· 2020-12-14
68.9
best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
F1@10%· 2020-12-14
68.7
best: 82.1 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
F1@25%· 2020-12-14
61.9
best: 79 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action LocalizationonBreakfast
F1@50%· 2020-12-14
46.6
best: 67.5 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Segmentationon50 Salads
Acc· 2020-12-14
80
best: 91.4 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Segmentationon50 Salads
Edit· 2020-12-14
72
best: 89.1 (Semantic2Graph)
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Segmentationon50 Salads
F1@10%· 2020-12-14
79.1
best: 92.7 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Segmentationon50 Salads
F1@25%· 2020-12-14
75.9
best: 91.6 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action Segmentationon50 Salads
F1@50%· 2020-12-14
66.1
best: 88.5 (Br-Prompt+ASPnet (RGB, flow, accelerometer))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
Acc· 2020-12-14
68.3
best: 78 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
Average F1· 2020-12-14
59.1
best: 76.2 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
Edit· 2020-12-14
68.9
best: 79.7 (FACT (efficient hybrid of convolution and transformer model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
F1@10%· 2020-12-14
68.7
best: 82.1 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
F1@25%· 2020-12-14
61.9
best: 79 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508
Action SegmentationonBreakfast
F1@50%· 2020-12-14
46.6
best: 67.5 (AdaFocus (newly extracted I3D-features, LT-Context model))
Temporal Relational Modeling with Self-Supervision for Action Segmentation arXiv:2012.07508