TACT

Reported on 2 benchmarks across 2 tasks · 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

VideoonTest-of-Time
2-Class Accuracy· uses extra data· 2023-01-05
64.4
best: 88.33 (Video-LLAMA)
SOTA
Test of Time: Instilling Video-Language Models with a Sense of Time arXiv:2301.02074
Video RetrievalonTest-of-Time
2-Class Accuracy· uses extra data· 2023-01-05
64.4
best: 88.33 (Video-LLAMA)
SOTA
Test of Time: Instilling Video-Language Models with a Sense of Time arXiv:2301.02074