Published in ECCV, 2020
Authors: Hang Wang*, Minghao Xu*, Bingbing Ni, Wenjun Zhang (* equal contribution)
In this work, we propose a Learning to Combine framework, in which the knowledges acquired from multiple source domains are aggregated and applied to the target domain.
Published in CVPR, 2020 (Oral)
Authors: Minghao Xu, Hang Wang, Bingbing Ni, Qi Tian, Wenjun Zhang
In this work, we propose a Graph-induced Prototype Alignment (GPA) framework to align source and target domain for cross-domain detection tasks.
Published in AAAI, 2020 (Oral)
Authors: Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang
In this work, we propose to promote adversarial domain adaptation with both pixel-level and feature-level domain mixup.
Published in TPAMI, 2019
Authors: Yichao Yan, Ning Zhuang, Bingbing Ni, Jian Zhang, Minghao Xu, Qiang Zhang, Zhang Zheng, Shuo Cheng, Qi Tian, Xiaokang Yang, Wenjun Zhang
In this work, we collect a new video dataset from YouTube.com, called Sports Video Narrative (SVN), for fine-grained sports auto-narrative. Also, we propose a novel framework to encode both intra- and inter- team interactions.
Published in ICCV, 2019
Authors: Jian Zhang, Chenglong Zhao, Bingbing Ni, Minghao Xu, Xiaokang Yang
In this work, we propose a variational Bayesian framework to approximate bias-eliminated class specific sample distributions for few-shot learning.
Published in CVPR, 2019 (Oral)
Authors: Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang
In this work, we build a graph learning framework to employ context information for person search.