Handong Zhao

Research Scientist

San Jose

Handong is a research scientist at Adobe Research, San Jose, CA, since March 2018. He obtained the Ph.D. degree at Department of Electrical & Computer Engineering, Northeastern University, Boston, MA. His current research interest includes machine learning and its applications to multimedia content analysis and marketing analytics. Before this, he received both my master’s and bachelor’s degrees in Tianjin University, China.

His contact email is hazhao@adobe.com. For more information, please visit his personal page at https://hdzhao.github.io/

Publications

Fine-tuning CLIP Text Encoders with Two-step Paraphrasing

Kim, H., Yoon, D., Bui, T., Zhao, H., Tran, Q., Dernoncourt, F., Kang, J. (Mar. 22, 2024)

EACL 2024 Findings

EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval

Ma, H., Zhao, H., Lin, Z., Kale, A., Wang, Z., Yu, T., Gu, J., Choudhary, S., Xie, X. (Sep. 27, 2022)

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Structured Policy Iteration for Linear Quadratic Regulator

Park, Y., Rossi, R., Wen, Z., Wu, G., Zhao, H. (Jul. 31, 2020)

International Conference on Machine Learning (ICML)

Cross-Domain Document Object Detection: Benchmark Suite and Method

Li, K., Wigington, C., Tensmeyer, C., Zhao, H., Barmpalios, N., Morariu, V., Manjunatha, V., Sun, T., Fu, Y. (Jun. 22, 2020)

Conference on Computer Vision and Pattern Recognition (CVPR)

Linear Quadratic Regulator for Resource-Efficient Cloud Services

Park, Y., Mahadik, K., Rossi, R., Wu, G., Zhao, H. (Nov. 21, 2019)

ACM Symposium on Cloud Computing

Unpaired Image Captioning via Scene Graph Alignments

Gu, J., Joty, S., Cai, J., Zhao, H., Yang, X., Wang, G. (Oct. 27, 2019)

International Conference on Computer Vision (ICCV)

Towards Robust and Discriminative Sequential Data Learning: When and How to Perform Adversarial Training?

Jia, X., Li, S., Zhao, H., Kim, S., Kumar, V. (Aug. 4, 2019)

KDD

Log2Intent: Towards Interpretable User Modeling via Recurrent Semantics Memory Units