Jiawei He
Jiawei He has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Zhaoxiang Zhang
University of Chinese Academy of Sciences
5 shared publications - Yingyan Li
Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China
2 shared publications - Yuntao Chen
Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences, Hong Kong SAR, China
2 shared publications Bin Xue
Xian Institute of Optics and Precision Mechanics of CAS, Xi'an, Shaanxi, China
1 shared publication- Chuanguang Yang
Institute of Computing Technology, Chinese Academy of Sciences
1 shared publication - Guocai Yao
Beijing Academy of Artificial Intelligence, Beijing, China
1 shared publication
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14308-14315
DA-Nav: Direction-Aware City-Scale Vision-Language Navigation
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14308-14315
DA-Nav: Direction-Aware City-Scale Vision-Language Navigation
- 17 September 2026
- Published by Springer Nature
- p. 258-277
UniPart: Towards Zero-Shot Language-Grounded 3D Part Segmentation for Embodied Interaction
- 17 September 2026
- Published by Springer Nature
- p. 258-277
UniPart: Towards Zero-Shot Language-Grounded 3D Part Segmentation for Embodied Interaction
- 29 September 2024
- Published by Springer Nature
- p. 387-404
OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers
- 29 September 2024
- Published by Springer Nature
- p. 387-404
OneTrack: Demystifying the Conflict Between Detection and Tracking in End-to-End 3D Trackers
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (7) , 4880-4895
Learnable Graph Matching: A Practical Paradigm for Data Association
Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view context information; besides, they either train deep association models in an end-to-end way and hardly utilize the advantage of optimization-based assignment methods, or only use an off-the-shelf neural network to extract features. In this paper, we propose a general learnable graph matching method to address these issues. Especially, we model the intra-view relationships as an undirected graph. Then data association turns into a general graph matching problem between graphs. Furthermore, to make optimization end-to-end differentiable, we relax the original graph matching problem into continuous quadratic programming and then incorporate training into a deep graph neural network with KKT conditions and implicit function theorem. In MOT task, our method achieves state-of-the-art performance on several MOT datasets. For image matching, our method outperforms state-of-the-art methods on a popular indoor dataset, ScanNet. For point cloud registration, we also achieve competitive results.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (7) , 4880-4895
Learnable Graph Matching: A Practical Paradigm for Data Association
Data association is at the core of many computer vision tasks, e.g., multiple object tracking, image matching, and point cloud registration. however, current data association solutions have some defects: they mostly ignore the intra-view context information; besides, they either train deep association models in an end-to-end way and hardly utilize the advantage of optimization-based assignment methods, or only use an off-the-shelf neural network to extract features. In this paper, we propose a general learnable graph matching method to address these issues. Especially, we model the intra-view relationships as an undirected graph. Then data association turns into a general graph matching problem between graphs. Furthermore, to make optimization end-to-end differentiable, we relax the original graph matching problem into continuous quadratic programming and then incorporate training into a deep graph neural network with KKT conditions and implicit function theorem. In MOT task, our method achieves state-of-the-art performance on several MOT datasets. For image matching, our method outperforms state-of-the-art methods on a popular indoor dataset, ScanNet. For point cloud registration, we also achieve competitive results.
- 6 November 2022
- Published by Springer Nature
- p. 718-734
Densely Constrained Depth Estimator for Monocular 3D Object Detection
- 6 November 2022
- Published by Springer Nature
- p. 718-734
Densely Constrained Depth Estimator for Monocular 3D Object Detection
- Open Access
Densely Constrained Depth Estimator for Monocular 3D Object Detection
Estimating accurate 3D locations of objects from monocular images is a challenging problem because of lacking depth. Previous work shows that utilizing the object's keypoint projection constraints to estimate multiple depth candidates boosts the detection performance. However, the existing methods can only utilize vertical edges as projection constraints for depth estimation. So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation. In this paper, we propose a method that utilizes dense projection constraints from edges of any direction. In this way, we employ much more projection constraints and produce considerable depth candidates. Besides, we present a graph matching weighting module to merge the depth candidates. The proposed method DCD (Densely Constrained Detector) achieves state-of-the-art performance on the KITTI and WOD benchmarks. Code is released at https://github.com/BraveGroup/DCD.
Open AccessDensely Constrained Depth Estimator for Monocular 3D Object Detection
Estimating accurate 3D locations of objects from monocular images is a challenging problem because of lacking depth. Previous work shows that utilizing the object's keypoint projection constraints to estimate multiple depth candidates boosts the detection performance. However, the existing methods can only utilize vertical edges as projection constraints for depth estimation. So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation. In this paper, we propose a method that utilizes dense projection constraints from edges of any direction. In this way, we employ much more projection constraints and produce considerable depth candidates. Besides, we present a graph matching weighting module to merge the depth candidates. The proposed method DCD (Densely Constrained Detector) achieves state-of-the-art performance on the KITTI and WOD benchmarks. Code is released at https://github.com/BraveGroup/DCD.
- 1 January 2019
- Published by Elsevier in Optics Communications
- Vol. 430, 311-317
Polarization properties of calibration reflector system in the polarization-modulated space laser communication
- 1 January 2019
- Published by Elsevier in Optics Communications
- Vol. 430, 311-317
Polarization properties of calibration reflector system in the polarization-modulated space laser communication