T EACH T EXT: CrossModal Generalized Distillation for Text-Video Retrieval
Ioana Croitoru 1,2,* Simion-Vlad Bogolin1,2,* Marius Leordeanu2,3
Hailin Jin4 Andrew Zisserman1 Samuel Albanie1,5, Yang Liu1,6,
1 2 3
Visual Geometry Group, Univ. of Oxford Inst. of Mathematics of the Romanian Academy Univ. Politehnica of Bucharest
4 5 6
Adobe Research Dept ...


雷达卡




京公网安备 11010802022788号







