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/ILA (ViT-L/14)

ILA (ViT-L/14)

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· 2023-04-20
88.7
best: 93.6 (OmniVec2)
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465
VideoonKinetics-400
Acc@5· 2023-04-20
97.8
best: 98.9 (TubeViT-H (ImageNet-1k))
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-04-20
70.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-04-20
91.8
best: 96.3 (DejaVid)
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-04-20
70.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-04-20
91.8
best: 96.3 (DejaVid)
Implicit Temporal Modeling with Learnable Alignment for Video Recognition arXiv:2304.10465