Video Question Answering On Sutd Trafficqa

1/4

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
CFMMC-Align	50.2	-
Tem-adapter	46.0	Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer
Eclipse	37.05	SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
HCRN	36.49	Hierarchical Conditional Relation Networks for Video Question Answering
TVQA	35.16	TVQA: Localized, Compositional Video Question Answering
VIS+LST	29.91	Exploring Models and Data for Image Question Answering

0 of 6 row(s) selected.