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/TAda2D-En (ResNet-50, 8+16 frames)

TAda2D-En (ResNet-50, 8+16 frames)

Reported on 6 benchmarks across 3 tasks · 1 paper

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

Computer Vision2 results

VideoonKinetics-400
Acc@1· 2021-10-12
78.2
best: 93.6 (OmniVec2)
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178
VideoonKinetics-400
Acc@5· 2021-10-12
93.5
best: 98.9 (TubeViT-H (ImageNet-1k))
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-10-12
67.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-10-12
89.8
best: 96.3 (DejaVid)
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· uses extra data· 2021-10-12
67.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178
Action RecognitiononSomething-Something V2
Top-5 Accuracy· uses extra data· 2021-10-12
89.8
best: 96.3 (DejaVid)
TAda! Temporally-Adaptive Convolutions for Video Understanding arXiv:2110.06178