仉尚航

仉尚航

职称:助理教授(研究员、副高),博士生导师,国家海外高层次人才项目入选者,博雅青年学者

研究所:数字媒体研究所

研究领域:机器学习与计算机视觉,视觉信息处理与类脑智能

办公电话:

电子邮件:shanghang@pku.edu.cn

个人主页:https://www.shanghangzhang.com/

主要研究方向

开放世界泛化机器学习、类脑视觉感知与学习、AI驱动科学计算


主要科研项目

1.自主意识学习,国家自然科学基金委员会专项项目

2.面向驾驶场景的高真实感数据合成与视觉模型训练平台

3.面向自动驾驶的开放环境泛化机器学习, CCF-滴滴盖亚青年学者科研基金项目

4.面向自动驾驶的跨场景泛化3D感知关键技术研究,CCF-百度松果基金项目


主要学术任职

· Senior Program Committee, AAAI Conference on Artificial Intelligence (AAAI), 2022 & 2023.

· Organizing Chair, Advances in Neural Information Processing Systems (NeurIPS) 2022, 1st Human in the Loop Learning Workshop.

· Chief Organizer, International Conference on Machine Learning (ICML) 2021, Self-Supervised Learning for Reasoning and Perception.

· Chief Organizer, International Conference on Machine Learning (ICML) 2021, 3rd Human in the Loop Learning Workshop.

· Guest Editor, Special Issue on Novel Technologies in Multimedia Big Data, Electronics (ISSN 2079-9292).

· Chief Organizer, Conference on Neural Information Processing Systems (NeurIPS) 2020, Self-Supervised Learning-Theory and Practice Workshop.

· Chief Organizer, International Conference on Machine Learning (ICML) 2020, 2nd Human in the Loop Learning Workshop.

· Chief Organizer, International Conference on Machine Learning (ICML) 2019, 1st Human in the Loop Learning Workshop.

· Chief Organizer, ACM International Conference on Multimedia Retrieval (ICMR) 2019, "MMAC: Multi-Modal Affective Computing of Large-Scale Multimedia Data" Special Session.

· Member, IEEE, IEEE Women in Engineering, IEEE Computer Society, IEEE Signal Processing Society.

· Member, Association for Computing Machinery (ACM), ACM-SIGMM, ACM-SIGAI.

· Reviewer, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Neural Networks and Learning Systems (TNNLS), International Journal of Computer Vision (IJCV), IEEE Signal Processing Magazine (SPM), Transactions on Image Processing (TIP), IEEE Transactions on Multimedia (TMM), IEEE Signal Processing Letters (SPL), The ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM).

· Reviewer/Program Committee, NeurIPS; ICLR; CVPR; ICCV; ECML; AAAI; IJCAI.




Selected Publications

[1] Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021, February). Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of AAAI. AAAI Outstanding Paper Award.

[2] Zhang, S., Wu, G., Costeira, J. P., & Moura, J. M. (2017). Understanding traffic density from large-scale web camera data. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 5898-5907).

[3] Zhang, S., Wu, G., Costeira, J. P., & Moura, J. M. (2017). Fcn-rlstm: Deep spatio-temporal neural networks for vehicle counting in city cameras. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 3667-3676).

[4] Zhang, S., Shen, X., Lin, Z., Měch, R., Costeira, J. P., & Moura, J. M. (2018). Learning to understand image blur. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 6586-6595).

[5] Zhao, H., Zhang, S., Wu, G., Moura, J. M., Costeira, J. P., & Gordon, G. J. (2018). Adversarial multiple source domain adaptation. Advances in neural information processing systems (NeurIPS), 31.

[6] J. Ni, S. Zhang, H, Xie, “Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learning”, Advances in Neural Information Processing Systems (NeurIPS), 2019.

[7] X. Ma, X. Kong, S. Zhang, E. Hovy, “MaCow: Masked Convolutional Generative Flow”, Advances in Neural Information Processing Systems (NeurIPS), 2019.

[8] Zhao, S.#, Wang, G.#, Zhang, S.#, Gu, Y., Li, Y., Song, Z., ... & Keutzer, K. (2020, April). Multi-source distilling domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (Vol. 34, No. 07, pp. 12975-12983).

[9] Zhao, S., Yue, X., Zhang, S., Li, B., Zhao, H., Wu, B., ... & Keutzer, K. (2020). A review of single-source deep unsupervised visual domain adaptation. IEEE Transactions on Neural Networks and Learning Systems (TNNLS, IF 14.255).

[10] Dong, H., Dong, H., Ding, Z., Zhang, S., & Chang. (2020). Deep Reinforcement Learning. Springer Singapore.

[11] X. Sun, Y. Xu, P. Cao, Y. Kong*, L. Hu, S. Zhang*, Y.Wang, “TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning”,European Conference on Computer Vision (ECCV) 2020, Oral presentation.

[12] K. Mei, C. Zhu, J. Zou, S. Zhang, “Instance Adaptive Self-Training for Unsupervised Domain Adaptation”, 16th European Conference on Computer Vision (ECCV), 2020.

[13] Li, B.#, Wang, Y.#, Zhang, S.#, Li, D., Keutzer, K., Darrell, T., & Zhao, H. (2021). Learning invariant representations and risks for semi-supervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 1104-1113).

[14] S. Zhou, S. Zhang, et al. “Caching in Dynamic Environments: a Near-optimal Online Learning Approach”, IEEE Transactions on Multimedia (TMM, IF 8.182), 2021.

[15] H. Zhou, J. Li, J. Peng, S. Zhang, S. Zhang, “Triplet Attention: Rethinking the similarity in Transformers”, ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2021.

[16] X Ma, X Kong, S Zhang, E Hovy, “Decoupling Global and Local Representations via Invertible Generative Flows”, Accepted by International Conference on Learning Representations (ICLR), 2021.

[17] T. Li, X. Chen, S. Zhang*, Z. Dong*, K. Keutzer, “Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.

[18] C. Zhang#, M. Zhang#, S. Zhang#, et al. "Delving deep into the generalization of vision transformers under distribution shifts.", Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

[19] M. Liu, Q. Zhou, H. Zhao, L. Du, Y. Du, J. Li, K. Keutzer, S. Zhang*. Prototypical Supervised Contrastive Learning for LiDAR Point Cloud Panoptic Segmentation, International Conference on Robotics and Automation (ICRA), 2022.

[20] S. Zhou, H. Zhao, S. Zhang*, et al. “Online Continual Adaptation with Active Self-Training”, Artificial Intelligence and Statistics Conference (AISTATS), 2022.

[21] S. Zhou, S. Zhang*, et al. “Active Gradual Domain Adaptation: Dataset and Approach”, IEEE Transactions on Multimedia (TMM, IF 8.182), 2022.

[22] J. Yu, J. Liu, X.Wei, H. Zhou, Y. Nakata, D. Gudovskiy, T. Okuno, J. Li, K. Keutzer, S. Zhang*, MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer, 17th European Conference on Computer Vision (ECCV) 2022.

[23] X. Li, J. Liu, S.Wang, C. Lyu, M. Lu, Y. Chen, A. Yao, Y. Guo, S. Zhang*, Efficient Meta-Tuning for Content-aware Neural Video Delivery, 17th European Conference on Computer Vision (ECCV) 2022.

[24] Chu, X., Jin, Y., Zhu, W., Wang, Y., Wang, X., Zhang, S. and Mei, H., 2022, June. DNA: Domain Generalization with Diversified Neural Averaging. In International Conference on Machine Learning (pp. 4010-4034) (ICML). PMLR.

[25] Y Zou, S Zhang, Y Li, R Li, Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation, Neural Information Processing Systems (NeurIPS) 2022.

[26] H Zhou, S Xiao, S Zhang, J Peng, S Zhang, J Li, Jump Self-attention: Capturing High-order Statistics in Transformers, Neural Information Processing Systems (NeurIPS) 2022.