Univl

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

Action LocalizationonCOIN
Frame accuracy· uses extra data· 2020-02-15
70
best: 72.8 (UnLoc-L)
SOTA
UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation arXiv:2002.06353
Action SegmentationonCOIN
Frame accuracy· uses extra data· 2020-02-15
70
best: 72.8 (UnLoc-L)
SOTA
UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation arXiv:2002.06353