COMEDIAN (ViViT T ens.)

Reported on 2 benchmarks across 1 task · 1 paper

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

Computer Vision2 results

VideoonSoccerNet-v2
Average-mAP· 2023-09-03
77.1
best: 78.5 (DenseAnchorsRevisited (Soares et al.))
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers arXiv:2309.01270
VideoonSoccerNet-v2
Tight Average-mAP· 2023-09-03
72
best: 73.1 (COMEDIAN (ViSwin T ens.))
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers arXiv:2309.01270