LaViLa (Finetuned, TimeSformer-L)

Reported on 4 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.

Robots3 results

Activity RecognitiononCharades-Ego
mAP· 2022-12-08
36.1
SOTA
Learning Video Representations from Large Language Models arXiv:2212.04501
Activity RecognitiononEGTEA
Average Accuracy· 2022-12-08
81.75
SOTA
Learning Video Representations from Large Language Models arXiv:2212.04501
Activity RecognitiononEGTEA
Mean class accuracy· 2022-12-08
76
SOTA
Learning Video Representations from Large Language Models arXiv:2212.04501

Time Series1 result

Action RecognitiononCharades-Ego
mAP· 2022-12-08
36.1
SOTA
Learning Video Representations from Large Language Models arXiv:2212.04501