Jian Ma

I am an Assistant Researcher (Postdoc) in Prof. Kun Li group at Tianjin University. My research interests include egocentric video understanding, 3D human reconstruction.

Email / Google Scholar / Github

Educations and Working Experiences

I completed my Ph.D. journey at University of Bristol under the supervision of Prof. Dima Damen and I achieved my master degree in computer science at the College of Intelligence and Computing at Tianjin University from 2016 - 2019, supervised by Prof. Kun Li. Additionally, I did internships at Baidu and OPPO Research Institute, under the supervision of Dr. Yandong Guo.

Publications

	InterCoser: Interactive 3D Character Creation with Disentangled Fine-Grained Features Yi Wang¹, Jian Ma¹, Zhou Su, Guidong Wang, Jingyu Yang, Yu-Kun Lai, Kun Li* Association for the Advancement of Artificial Intelligence (AAAI) [Oral] , 2025
	DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video Hao Wen, Hongbo Kang, Jian Ma, Jing Huang, Yuanwang Yang, Haozhe Lin, Yu-Kun Lai, Kun Li* IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 project page
	RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters Xiaolin Liu, Tianyi Zhou, Hongbo Kang, Jian Ma, Ziwen Wang, Jing Huang, Wenguo Weng, Yu-Kun Lai, Kun Li* International Conference on Computer Vision (ICCV) [Highlight] , 2025 project page
	Active Object Segmentation: A New Modality for Egocentric Action Recognition Jian Ma, Bin Zhu, Kun Li, Dima Damen ACM Multimedia Asia, 2024
	Multi-scale information transport generative adversarial network for human pose transfer Jinsong Zhang, Yu-Kun Lai, Jian Ma, Kun Li Displays, 2024
	HumanCoser: Layered 3D human generation via semantic-aware diffusion model Yi Wang¹, Jian Ma¹, Ruizhi Shao, Qiao Feng, Yu-Kun Lai, Kun Li* IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2024 project page
	AEGIS-Net: Attention-Guided Multi-Level Feature Aggregation for Indoor Place Recognition Yuhang Ming¹, Jian Ma¹, Xingrui Yang, Weichen Dai, Yong Peng, Wanzeng Kong IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 project page
	Epic-kitchens visor benchmark: Video segmentations and object relations Ahmad Darkhalil¹, Dandan Shan¹, Bin Zhu¹, Jian Ma¹, Amlan Kar, Richard Higgins, Sanja Fidler, David Fouhey, Dima Damen Advances in Neural Information Processing Systems (NeurIPS), 2022 project page
	Hand-object interaction reasoning Jian Ma, Dima Damen IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 2022
	Rescaling Egocentric Vision Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray International Journal of Computer Vision (IJCV), 2021 project page
	Discern Depth Under Foul Weather: Estimate PM2.5 for Depth Inference Kun Li, Jian Ma, Han Li, Yahong Han, Xibin Yue, Zihao Chen, and Jingyu Yang IEEE Transactions on Industrial Informatics (T-II), 2020 project page
	Spatiotemporally scalable matrix recovery for background modeling and moving object detection Jingyu Yang, Wen Shi, Huanjing Yue, Kun Li, Jian Ma, Chunping Hou Signal Processing, 2020
	Image-based Air Pollution Estimation Using Hybrid Convolutional Neural Network Jian Ma, Kun Li, Yahong Han, Jingyu Yang International Conference on Pattern Recognition (ICPR), 2018
	Image-Based PM2.5 Estimation and its Application on Depth Estimation Jian Ma, Kun Li, Yahong Han, Pufeng Du, Jingyu Yang IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018