Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention

Ding, MY; Shen, YK; Fan, LJ; Chen, ZF; Chen, ZT; Luo, P; Tenenbaum, J; Gan, C

Ding, MY (通讯作者),Univ Hong Kong, Hong Kong, Peoples R China.;Ding, MY (通讯作者),MIT, Cambridge, MA 02139 USA.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023; (): 14528

Abstract

Humans possess a versatile mechanism for extracting structured representations of our visual world. When looking at an image, we can decompose the sce......

Full Text Link