Zijia Lin 1,2
Ph.D.
1 Institute of Information System & Engineering , School of Software
2 Department of Computer Science and Technology
Tsinghua University , Beijing, 100084, China
Email: linzijia07 [AT] tsinghua [DOT] org [DOT] cn
I achieved my Ph.D. degree in 2016 from Department of Computer Science & Technology, Tsinghua University, and my Bachelor degree in 2011 from School of Software, Tsinghua University. I worked with Professor Guiguang Ding on large-scale image retrieval and multi-label learning.
Right now I am a Lead Researcher in Microsoft Research Asia. For the full list of my publications, please refer to my Google Scholar page and DBLP page.
Education
2011 - 2016
2007 - 2011
Department of Computer Science and Technology, Tsinghua University
Ph.D. in Computer Science and Technology
GPA: 96.1/100 (Rank: 1/156 in the department, up to 04/2015)
School of Software, Tsinghua University
B.Eng. in Computer Software
GPA: 91.1/100 (Rank: 3/63 in the school)
Research Interests
1) Multimedia information retrieval: image auto-annotation / tag-refinement, hashing methods, etc.
2) Natural language understanding: named entity recognition, dialog policy learning, etc.
Conference Publications
Zijia Lin , Guiguang Ding, Mingqing Hu, Jianmin Wang: Semantics-Preserving Hashing for Cross-View Retrieval. CVPR 2015: 3864-3872 [pdf] [codes]
-- Update: In our experiments, for MIRFlickr, instances with only one textual tag were also removed, so as to make the text view of each remaining instance more like a textual document with multiple words.
Zijia Lin , Guiguang Ding, Mingqing Hu, Jianmin Wang: Multi-label Classification via Feature-aware Implicit Label Space Encoding. ICML 2014: 325-333 [pdf] [slides] [codes]
Zijia Lin , Guiguang Ding, Mingqing Hu: Multi-source Image Auto-annotation. ICIP 2013: 2567-2571 (Oral, Top 10% Paper) [pdf] [slides]
Zijia Lin , Guiguang Ding, Mingqing Hu, Jianmin Wang, Xiaojun Ye: Image Tag Completion via Image-Specific and Tag-Specific Linear Sparse Reconstructions. CVPR 2013: 1618-1625 [pdf] [data] [codes]
Zijia Lin , Guiguang Ding, Mingqing Hu, Jianmin Wang, Jiaguang Sun: Automatic Image Annotation using Tag-Related Random Search over Visual Neighbors. CIKM 2012: 1784-1788 [pdf]
Zijia Lin , Guiguang Ding, Jianmin Wang: Image Annotation Based on Recommendation Model. SIGIR 2011: 1097-1098 [pdf]
Journal Publications
Zijia Lin , Guiguang Ding, Jungong Han, Ling Shao: End-to-End Feature-Aware Label Space Encoding for Multilabel Classification With Many Classes. IEEE Transactions on Neural Networks and Learning Systems. (Preprint), 2017 [pdf][codes]
-- An extension to substantially improve the efficiency and the effectiveness of our proposed method in ICML 2014 paper.
Zijia Lin , Guiguang Ding, Jungong Han, Jianmin Wang: Cross-View Retrieval via Probability-Based Semantics-Preserving Hashing. IEEE Transactions on Cybernetics. (Preprint), 2016 [pdf][codes]
Zijia Lin , Guiguang Ding, Mingqing Hu: Image Auto-annotation via Tag-dependent Random Search over Range-constrained Visual Neighbours. Multimedia Tools and Applications. Vol. 74, Pages 4091-4116, 2015 [pdf]
Zijia Lin , Guiguang Ding, Mingqing Hu, Yunzhen Lin, Shuzhi Sam Ge: Image Tag Completion via Dual-view Linear Sparse Reconstructions. Computer Vision and Image Understanding. Vol. 124, Pages 42-60, 2014 [pdf]
Recent Honors & Awards
Community Service
Reviewer for IEEE Transactions on Image Processing, IEEE Transactions on Multimedia, IEEE Transactions on Circuits and Systems for Video Technology, Computer Vision and Image Understanding, Multimedia Tools and Applications
PC Member / Reviewer for AAAI 2018