C4AV: Learning Cross-Modal Representations from Transformers.

Shujie Luo Hang Dai Ling Shao 0001 Yong Ding 0003 C4AV: Learning Cross-Modal Representations from Transformers. 33-38 2020 ECCV Workshops (2) https://doi.org/10.1007/978-3-030-66096-3_3 conf/eccv/2020-w2 db/conf/eccv/eccv2020-w2.html#LuoDSD20