Zhongang Qi


Research Associate
School of Electrical Engineering and Computer Science
Oregon State University
2053 Kelley Engineering Center
Corvallis, Oregon, 97331-5501
Email: qiz at oregonstate dot edu
http://web.engr.oregonstate.edu/~qiz/

Zhongang Qi received the BS and the PhD degrees in information science and electronic engineering from Zhejiang University, Hangzhou, China. He was a researcher at NEC Laboratories China. He is currently a research associate in Professor Fuxin Li's group at the School of Electrical Engineering and Computer Science, Oregon State University. His research interests include multimedia and relational data mining, computer vision and model explanation, and machine learning.


Recent Research Topics

[1] Embedding Deep Networks into Visual Explanations [Paper] [Code] [Data]
We propose a novel explanation module to explain the predictions made by a deep network. The explanation module works by embedding a high-dimensional deep network layer nonlinearly into a low-dimensional explanation space while retaining faithfulness, so that the original deep learning predictions can be constructed from the few concepts extracted by the explanation module. We then visualize such concepts for human to learn about the high-level concepts that deep learning is using to make decisions.


Publications

Embedding Deep Networks into Visual Explanations
Zhongang Qi, Saeed Khorram, Fuxin Li, in arXiv preprint arXiv:1709.05360.

Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-grained Air Quality
Zhongang Qi, Tianchun Wang, Guojie Song, Weisong Hu, Xi Li, Zhongfei (Mark) Zhang, in IEEE Transactions on Knowledge and Data Engineering (TKDE 2018), doi: 10.1109/TKDE.2018.2823740.

Multi-Task Medical Concept Normalization Using Multi-View Convolutional Neural Network
Yi Luo, Guojie Song, Pengyu Li, Zhongang Qi, in the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI'18).

Learning Explainable Embeddings for Deep Networks
Zhongang Qi, Fuxin Li, in the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS'17) workshop: Interpreting, Explaining and Visualizing Deep Learning - now what?.

Bayesian Multi-task Relationship Learning with Link Structure
Yingming Li, Ming Yang, Zhongang Qi, Zhongfei (Mark) Zhang, in IEEE Transactions on Knowledge and Data Engineering (TKDE 2016) 28 (4), 873-887, 2016.

Characterizing and Comparing User Location Preference in an Urban Mobile Network
Chengli Mei, Min Zhang, Zhongang Qi, Qi Bi, in Trustworthy Computing and Services, series Communications in Computer and Information Science, Springer Berlin Heidelberg, 2014.

Bayesian Multi-task Relationship Learning with Link Structure
Yingming Li, Ming Yang, Zhongang Qi, Zhongfei (Mark) Zhang, in Proceedings of the 13th IEEE International Conference on Data Mining (ICDM'13).

Learning with Limited and Noisy Tagging
Yingming Li*, Zhongang Qi*, Zhongfei (Mark) Zhang, Ming Yang, in Proceedings of the 21st ACM International Conference on Multimedia (ACM MM'13). (*Contributed equally to this paper)

Mining Noisy Tagging from Multi-label Space
Zhongang Qi, Ming Yang, Zhongfei (Mark) Zhang, Zhengyou Zhang, in Proceedings of the 21st ACM International Conference on Information and Knowledge Management (CIKM'12).

Multi-View Learning from Imperfect Tagging
Zhongang Qi, Ming Yang, Zhongfei (Mark) Zhang, Zhengyou Zhang, in Proceedings of the 20th ACM International Conference on Multimedia (ACM MM'12).

Mining Partially Annotated Images
Zhongang Qi, Ming Yang, Zhongfei (Mark) Zhang, Zhengyou Zhang, in Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'11).


Patents

[1] Chinese Granted Patents:
As the first inventor:
(1) ZL 201210396793.4; (2) ZL 201210398567.X; (3) ZL 201210396612.8; (4) ZL 201210396335.0
As non-first inventor:
(1) ZL 201310674306.0

[2] Chinese Accepted Patents (under review):
As the first inventor:
(1) 201410834973.5; (2) 201510127794.2; (3) 201510728949.8; (4) 201510778908.X; (5) 201610183511.0
As non-first inventor:
(1) 201510690684.7

The last time this page was updated was on 19 April 2018.