Jun He, Ph.D

Short Bio

Dr. Jun He was an associate professor at Nanjing University of Information Science and Technology. In his past ten years of academia career, he worked on several problems in the field of machine learning, such as subspace models in computer vision, weakly supervised attention models for computer vision, reinforcement learning based "hard" attention model for human activity recognition and long document classification, and synthetic to real-world domain adaptation models. Dr. He not only conducted fundamental research in machine learning, but also worked closely with industrial research, for example, joint projects of wearable sensor based human activity recognition and long document classification. He did his postdoctoral research at the Chinese University of Hong Kong and he was a research fellow at IPAM, UCLA.

My Google Scholar Profile

Email = "%s%s.%s@gmail.com"%('he', 'jun', 'zz')

Research Interests

Machine Learning, Deep Learning, High-dimensional Data Analysis, Optimization

Projects

• Domain Gap Estimation for Source Free Unsupervised Domain Adaptation (Code available with Colab demonstration) (2019~ 2022)

• Human Activity Recognition and Localization, joint work with Lei Zhang and Ling Pei. (2017~2021)

• Long Document Classification, collaborated with industrial research. (2017~2018)

• Transformed-GRASTA , joint work with Laura Balzano (2012~ 2014)

• GRASTA (Grassmannian Robust Adaptive Subspace Tracking Algorithm), joint work with Laura Balzano and Arthur Szlam , (2011 ~2013)

Selected Publication

• Kun Wang, Jun He, and Lei Zhang. "Sequential Weakly Labeled Multiactivity Localization and Recognition on Wearable Sensors Using Recurrent Attention Networks." IEEE Transactions on Human-Machine Systems (2021).

• Y Zhou, B Hu, Jun He, Y Guan, L Shao. "Dual reference age synthesis." Neurocomputing 411 (2020): 164-177.

• Jun He, QJ Cao, L Zhang, H Tao. "Conditionally Learn to Pay Attention for Sequential Visual Task." IEEE Access 8 (2020): 56695-56710.

• Kun Wang, Jun He, Lei Zhang. "Attention-based convolutional neural network for weakly labeled human activities’ recognition with wearable sensors." IEEE Sensors Journal 19.17 (2019): 7598-7604.

• Jun He, L Wang, L Liu, J Feng, H Wu. "Long document classification from local word glimpses via recurrent attention learning." IEEE Access 7 (2019): 40707-40718.

• Jun He, Q Zhang, L Wang, L Pei. "Weakly supervised human activity recognition from wearable sensors by recurrent attention learning." IEEE Sensors Journal 19.6 (2018): 2287-2297.

• Jun He, Dejiao Zhang, Laura Balzano, Tao Tao. “Iterative Grassmannian Optimization for Robust Image Alignment.” Image and Vision Computing, Best of Automatic Face and Gesture Recognition 2013, vol.32. 10 (2014): 800–813. doi:10.1016/j.imavis.2014.02.015.

• Jun He, Dejiao Zhang, Laura Balzano, Tao Tao. Iterative Online Subspace Learning for Robust Image Alignment, In IEEE Conference on Automatic Face and Gesture Recognition (FG), April 2013. (Oral, PDF)

• Jun He, Laura Balzano, Arthur Szlam. Incremental Gradient on the Grassmannian for Online Foreground and Background Separation in Subsampled Video. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2012. (Oral, PDF) (Slides by Laura)

• Jun He, Laura Balzano, John C.S. Lui, Online Robust Subspace Tracking from Partial Information, preprint, http://arxiv.org/abs/1109.3827, Sept., 2011.

Last update: Oct. 12, 2022