常虹 女 博导 中国科学院计算技术研究所
电子邮件： changhong@ict.ac.cn
通信地址： 北京市海淀区科学院南路6号 中科院计算所534室
邮政编码：100190
研究领域
- 机器学习的算法和模型，特别是深度学习、半监督学习、小样本学习、模型鲁棒性等。
- 机器学习方法在计算机视觉、模式识别、科学智能等领域的应用，特别是与人为中心的感知、理解、生成问题，包括行人重识别、目标检测、跟踪、动作识别、图像生成等。
招生信息
每年招收直博生和硕士生各一名，欢迎对机器学习、计算机视觉等领域有兴趣的同学与我联系！
招生专业
招生方向
教育、工作经历
2008年3月 — 今 ：中国科学院计算技术研究所，副研究员，研究员；
2006年11月 — 2007年12月：施乐（欧洲）研究院，研究员（永久职位）；
2006年2月 — 11月：香港科技大学计算机系，博士后；
2001年9月— 2006年1月：香港科技大学计算机系，博士生；
1998年9月— 2001年4月：天津大学计算机系，硕士生；
1994年9月— 1998年7月：河北工业大学计算机系，本科生
教授课程
主要论文
Journal papers: (Recent selected)
[1] Keliang Li, Hong Chang, Shiguang Shan, Xilin Chen. Enhancing Robustness to Class- Conditional Distribution Shift in Long-Tailed Recognition. Transactions on Machine Learning Research. 2024.
[2] Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Dual Compensation Residual Networks for Class Imbalanced Learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(10): 11733-11752, 2023.
[3] Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, Xilin Chen. Feature Completion for Occluded Person Re-Identification. IEEE Trans. Pattern Anal. Mach. Intell. 44(9): 4894-4912, 2022.
[4] Xinqian Gu, Hong Chang, Bingpeng Ma, Shiguang Shan. Motion Feature Aggregation for Video-Based Person Re-Identification. IEEE Trans. Image Process. 31: 3908-3919, 2022.
[5] Nan Kang, Hong Chang, Bingpeng Ma and Shiguang Shan. A Comprehensive Framework for Long-Tailed Learning via Pretraining and Normalization. IEEE Trans. on Neural Networks and Learning Systems, 35(3):3437-3449, 2022.
[6] Kongming Liang, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Unifying Visual Attribute Learning with Object Recognition in a Multiplicative Framework. IEEE Trans. Pattern Anal. Mach. Intell. 41(7): 1747-1760, 2019.
Conference papers: (Recent selected)
[1] Minyang Hu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing. ICLR, 2024.
[2] Wenrui Liu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Diversity- Measurable Anomaly Detection. CVPR, 2023.
[3] Minyang Hu, Hong Chang, Zong Guo, Bingpeng Ma, Shiguang Shan, Xilin Chen. Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes. NeurIPS, 2023.
[4] Jiachen Liang, Ruibing Hou, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation. NeurIPS, 2023.
[5] Minyang Hu, Hong Chang, Bingpeng Ma, Shiguang Shan. Learning Continuous Graph Structure with Bilevel Programming for Graph Neural Networks. IJCAI, 2022.
[6] Yinqi Li, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen. Optimal Positive Generation via Latent Transformation for Contrastive Learning. NeurIPS, 2022
[7] Botao Ye, Hong Chang, Bingpeng Ma, Shiguang Shan and Xilin Chen. Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework. CVPR, 2022.
[8] Xinqian Gu, Hong Chang, Bingpeng Ma, Shutao Bai, Shiguang Shan, and Xilin Chen. Clothes-Changing Person Re-identification with RGB Modality Only. CVPR, 2022.
[9] Shutao Bai, Bingpeng Ma, Hong Chang, Rui Huang, and Xilin Chen. Salient-to-Broad Transition for Video Person Re-identification. CVPR, 2022.