TokenLearner 16at18 w. Fuser (L/10)

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Computer Vision2 results

VideoonKinetics-600
Top-1 Accuracy· uses extra data· 2021-06-21
86.3
best: 91.9 (InternVideo2-6B)
SOTA
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?arXiv:2106.11297
VideoonKinetics-600
Top-5 Accuracy· uses extra data· 2021-06-21
97
best: 98.9 (TubeVit-H)
SOTA
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?arXiv:2106.11297