Dongjiang Cao
Dongjiang Cao has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Desheng Zhang
Rutgers University
2 shared publications - Haotian Wang
JD Logistics, Beijing, China
2 shared publications - Ruofeng Liu
Michigan State University, East Lansing, Michigan, USA
2 shared publications - Shuai Wang
Southeast University
2 shared publications - Tian He
University of Minnesota
2 shared publications - Wenchao Jiang
Singapore University of Technology and Design, Singapore
2 shared publications
Latest Publications
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2756-2767
AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2756-2767
Open AccessAddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data
- Open Access
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Egocentric Human Pose Estimation using Head-mounted mmWave Radar
3D human pose plays a critical role in human behavior understanding and has many applications (e.g., VR/AR). Conventional pose estimations deploy sensors as fixed infrastructure, which significantly restrains the mobility of the user. Inspired by the emerging head-mounted devices (e.g., VR/AR glasses) and the recent advance in low-cost mmWave radar, we present mmEgo, the first egocentric human pose estimation design using a head-mounted mmWave radar, which offers ubiquitous pose tracking with high mobility, robustness to complex environments, and privacy preservation. To tackle the unique challenges of radar sensing from the egocentric perspective (e.g., random radar motion and the scarcity of information on the lower body), we propose several technical designs, including root-relative radar motion tracking for radar motion decoupling and a two-stage pose estimator that incorporates human kinematics priors. Extensive experiments and case studies show that our method can reduce the joint localization error by 44.2% and potentially enable a wide spectrum of applications.
- 12 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Open AccessEgocentric Human Pose Estimation using Head-mounted mmWave Radar
3D human pose plays a critical role in human behavior understanding and has many applications (e.g., VR/AR). Conventional pose estimations deploy sensors as fixed infrastructure, which significantly restrains the mobility of the user. Inspired by the emerging head-mounted devices (e.g., VR/AR glasses) and the recent advance in low-cost mmWave radar, we present mmEgo, the first egocentric human pose estimation design using a head-mounted mmWave radar, which offers ubiquitous pose tracking with high mobility, robustness to complex environments, and privacy preservation. To tackle the unique challenges of radar sensing from the egocentric perspective (e.g., random radar motion and the scarcity of information on the lower body), we propose several technical designs, including root-relative radar motion tracking for radar motion decoupling and a two-stage pose estimator that incorporates human kinematics priors. Extensive experiments and case studies show that our method can reduce the joint localization error by 44.2% and potentially enable a wide spectrum of applications.
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4623-4630
AutoBuild: Automatic Community Building Labeling for Last-mile Delivery
Fine-grained community-building information, such as building names and accurate geographical coordinates, is critical for a range of practical applications like navigation and door-to-door services (e.g., on-demand delivery and last-mile delivery). A common practice of traditional methods to gather community-building information usually relies on manual collection, which is typically labor-intensive and time-consuming. To address these issues, we utilize the massive data generated from e-commerce delivery services and design a framework, AutoBuild, for fine-grained large-scale community-building labeling. AutoBuild consists of two main components: (i) a Location Candidate Detection Module that identifies potential building names and coordinates from multi-source delivery data, and (ii) a Progressive Building Matching Model that employs trajectory modeling, human behavior analysis, and heterogeneous graph alignment to match building names and coordinates. To evaluate the performance of AutoBuild, we applied it to two real-world multi-modal datasets from Beijing City and Chengdu City. The results reveal that AutoBuild significantly outperforms multiple baseline models by 50-meter accuracy of 81.8% and 100-meter accuracy of 95.9% in Beijing City. More importantly, we conduct a real-world case study to demonstrate the practical impact of AutoBuild in last-mile delivery.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4623-4630
Open AccessAutoBuild: Automatic Community Building Labeling for Last-mile Delivery
Fine-grained community-building information, such as building names and accurate geographical coordinates, is critical for a range of practical applications like navigation and door-to-door services (e.g., on-demand delivery and last-mile delivery). A common practice of traditional methods to gather community-building information usually relies on manual collection, which is typically labor-intensive and time-consuming. To address these issues, we utilize the massive data generated from e-commerce delivery services and design a framework, AutoBuild, for fine-grained large-scale community-building labeling. AutoBuild consists of two main components: (i) a Location Candidate Detection Module that identifies potential building names and coordinates from multi-source delivery data, and (ii) a Progressive Building Matching Model that employs trajectory modeling, human behavior analysis, and heterogeneous graph alignment to match building names and coordinates. To evaluate the performance of AutoBuild, we applied it to two real-world multi-modal datasets from Beijing City and Chengdu City. The results reveal that AutoBuild significantly outperforms multiple baseline models by 50-meter accuracy of 81.8% and 100-meter accuracy of 95.9% in Beijing City. More importantly, we conduct a real-world case study to demonstrate the practical impact of AutoBuild in last-mile delivery.
- Open Access
- 27 March 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 7 (1) , 1-22
Human Parsing with Joint Learning for Dynamic mmWave Radar Point Cloud
Human sensing and understanding is a key requirement for many intelligent systems, such as smart monitoring, human-computer interaction, and activity analysis, etc. In this paper, we present mmParse, the first human parsing design for dynamic point cloud from commercial millimeter-wave radar devices. mmParse proposes an end-to-end neural network design that addresses the inherent challenges in parsing mmWave point cloud (e.g., sparsity and specular reflection). First, we design a novel multi-task learning approach, in which an auxiliary task can guide the network to understand human structural features. Secondly, we introduce a multi-task feature fusion method that incorporates both intra-task and inter-task attention to aggregate spatio-temporal features of the subject from a global view. Through extensive experiments in both indoor and outdoor environments, we demonstrate that our proposed system is able to achieve ~ 92% accuracy and ~ 84% IoU accuracy. We also show that the predicted semantic labels can increase the performance of two downstream tasks (pose estimation and action recognition) by ~ 18% and ~ 6% respectively.
- 27 March 2023
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 7 (1) , 1-22
Open AccessHuman Parsing with Joint Learning for Dynamic mmWave Radar Point Cloud
Human sensing and understanding is a key requirement for many intelligent systems, such as smart monitoring, human-computer interaction, and activity analysis, etc. In this paper, we present mmParse, the first human parsing design for dynamic point cloud from commercial millimeter-wave radar devices. mmParse proposes an end-to-end neural network design that addresses the inherent challenges in parsing mmWave point cloud (e.g., sparsity and specular reflection). First, we design a novel multi-task learning approach, in which an auxiliary task can guide the network to understand human structural features. Secondly, we introduce a multi-task feature fusion method that incorporates both intra-task and inter-task attention to aggregate spatio-temporal features of the subject from a global view. Through extensive experiments in both indoor and outdoor environments, we demonstrate that our proposed system is able to achieve ~ 92% accuracy and ~ 84% IoU accuracy. We also show that the predicted semantic labels can increase the performance of two downstream tasks (pose estimation and action recognition) by ~ 18% and ~ 6% respectively.