no code implementations • 31 Jan 2023 • Xin Dong, Ruize Wu, Chao Xiong, Hai Li, Lei Cheng, Yong He, Shiyou Qian, Jian Cao, Linjian Mo
GDOD decomposes gradients into task-shared and task-conflict components explicitly and adopts a general update rule for avoiding interference across all task gradients.
no code implementations • 16 May 2020 • Chao Xiong, Che Liu, Zijun Xu, Junfeng Jiang, Jieping Ye
In this work, we propose a matching network, called sequential sentence matching network (S2M), to use the sentence-level semantic information to address the problem.
no code implementations • ICCV 2015 • Chao Xiong, Xiaowei Zhao, Danhang Tang, Karlekar Jayashree, Shuicheng Yan, Tae-Kyun Kim
Faces in the wild are usually captured with various poses, illuminations and occlusions, and thus inherently multimodally distributed in many tasks.