PLAR

Reported on 4 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.

Robots2 results

Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-05-21
67.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition arXiv:2305.12437
Activity RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-05-21
91
best: 96.3 (DejaVid)
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition arXiv:2305.12437

Time Series2 results

Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2023-05-21
67.3
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition arXiv:2305.12437
Action RecognitiononSomething-Something V2
Top-5 Accuracy· 2023-05-21
91
best: 96.3 (DejaVid)
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition arXiv:2305.12437