About Me

I'm Hantao Yao(姚涵涛), a research assistant professor at the Multimedia Computing Group, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences. I have received the B.S. degree from XiDian University, Xi'an, China, in 2012, and the Ph.D. degree in Institute of Computing Technology, University of Chinese Academy of Sciences, in 2018.

My Research interests:

  • Deep learning for computer vision
  • Fine-Grained Object Recognition
  • Person Re-Identification
  • Person detection
  • Multi person multi camera tracking
  • Zero shoting and Domain adaptation

Email: hantao.yao@nlpr.ia.ac.cn / htyao89@gmail.com

News

Two papers have accepted by MM 2019.

One paper have accepted by TIP 2019.

Publications

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian: One-Shot Fine-Grained Instance Retrieval,arXiv preprint arXiv:1707.00811, accepted by MM 2017

[PDF]

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian: Deep Representation Learning with Part Loss for Person Re-Identification. arXiv preprint arXiv:1707.00798

[PDF]

Hantao Yao, Dongming Zhang, Jintao Li, Jianshe Zhou, Shiliang Zhang, Yongdong Zhang: DSP: Discriminative Spatial Part modeling for Fine-Grained Visual Categorization. Image Vision Comput. 63: 24-37 (2017)

Hantao Yao, Shiliang Zhang, Dongming Zhang, Yongdong Zhang, Jintao Li, Yu Wang, Qi Tian: Large-scale Person Re-Identification as Retrieval, ICME 2017

[PDF][Code][Person-520K]

Hantao Yao, Feng Dai, Dongming Zhang, Yike Ma, Shiliang Zhang, Yongdong Zhang, Qi Tian: DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing. arXiv preprint arXiv:1702.05743

[PDF][Code]

Hantao Yao, Shiliang Zhang, Yongdong Zhang, Jintao Li, Qi Tian: Coarse-to-Fine Description for Fine-Grained Visual Categorization. IEEE Trans. Image Processing 25(10): 4858-4872 (2016)

[PDF]

Hantao Yao, Shiliang Zhang, Fei Xie, Yongdong Zhang, Dongming Zhang, Yu Su, Qi Tian: Orientational Spatial Part Modeling for Fine-Grained Visual Categorization. IEEE MS 2015: 360-367