About Me

My name is Handong Zhao. I am a research scientist at Adobe Research, San Jose, CA. I obtained the Ph.D. degree at Department of Electrical & Computer Engineering, Northeastern University, Boston, MA. Before joining Adobe, I have worked at IBM Research. My current research interest includes machine learning and its applications to multimedia content analysis and marketing analytics. I was the recipient of the National Science Foundation’s Innovation Corps (I-Corps™) program award as an entrepreneurial lead.

[Internship] I am hiring self-motivated PhD student research interns, so please feel free to contact me if you are interested in working with me. My current research interests include (but not limited to) multimodal learning, domain adaptation, entity retrieval/recognition, text generation, etc.



Full List: [DBLP] [Google Scholar]
  • Unpaired Image Captioning via Scene Graph Alignments
  • Jiuxiang Gu, Shafiq Joty, Jianfei Cai, Handong Zhao, Xu Yang and Gang Wang
  • ICCV 2019. [paper]
  • Towards Robust and Discriminative Sequential Data Learning: When and How to Perform Adversarial Training?
  • Xiaowei Jia, Sheng Li, Handong Zhao, Sungchul Kim and Vipin Kumar
  • KDD 2019
  • Log2Intent: Towards Interpretable User Modeling via Recurrent Semantics Memory Units
  • Zhiqiang Tao, Sheng Li, Zhaowen Wang, Chen Fang, Longqi Yang, Handong Zhao and Yun Fu
  • KDD 2019 (Oral Presentation)
  • Scene Graph Generation with External Knowledge and Image Reconstruction
  • Jiuxiang Gu, Handong Zhao, Zhe Lin, Sheng Li, Jianfei Cai and Mingyang Ling
  • CVPR 2019 [paper]
  • Domain Switch-Aware Holistic Recurrent Neural Network for Modeling Multi-Domain User Behavior
  • Donghyun Kim, Sungchul Kim, Handong Zhao, Ryan Rossi, Sheng Li and Eunyee Koh
  • WSDM 2019 [paper]

Learning Representation for Multi-View Data Analysis
Zhengming Ding, Handong Zhao and Yun Fu
Springer, 2018, ISBN 978-3-030-00733-1
Multi-View Clustering via Deep Matrix Factorization
Handong Zhao, Zhengming Ding and Yun Fu
AAAI Conference on Artificial Intelligence (AAAI), 2017.
[paper] [code]


  1. Tutorial: Robust Multi-view Visual Learning: A Knowledge Flow Perspective
    Jointly organized with Zhengming Ding and Ming Shao
    IJCAI-2020, virtual.
  2. Tutorial: Analyze, Predict and Visualize: When RNNs Meet Adobe
    Jointly organized with Sungchul Kim, Fan Du and Sana Malik
    Adobe Tech Summit 2019, San Francisco, CA, February 2019.
  3. Tutorial: Deep Multi-View Visual Data Analytics
    Jointly organized with Zhengming Ding and Hongfu Liu
    AAAI-2019, Honolulu, Hawaii, January 2019.
  4. Tutorial: Multi-view Face Representation
    Jointly organized with Zhengming Ding and Yun Raymond Fu
    FG-2017, Washington, D.C., May 2017.