Xiaokai Bai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaokai Bai has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Hui-Liang Shen
Zhejiang University
11 shared publications - Xiaohan Zhang
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
8 shared publications - Si-Yuan Cao
Zhejiang University
7 shared publications - Zhe Wu
College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China
6 shared publications - Beinan Yu
College of Computer Science and Technology, Zhejiang University, Hangzhou, China
4 shared publications - Jie Bai
School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (12) , 13829-13836
HCDE: Hierarchical Context-Detail Enhancement for 3D Object Detection With 4D Radar
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (12) , 13829-13836
HCDE: Hierarchical Context-Detail Enhancement for 3D Object Detection With 4D Radar
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (11) , 13008-13015
RadarFuser: One-Stage Radar-Camera Depth Estimation With Early and Point-Guided Fusion
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (11) , 13008-13015
RadarFuser: One-Stage Radar-Camera Depth Estimation With Early and Point-Guided Fusion
- 3 October 2026
- Published by Springer Nature
- p. 416-434
Recurrent Cross-View Object Geo-Localization
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (10) , 12112-12119
KCTF-Net: Kinematic Compensation Temporal Fusion for 4D Radar 3D Object Detection
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11  (10) , 12112-12119
KCTF-Net: Kinematic Compensation Temporal Fusion for 4D Radar 3D Object Detection
- Open Access
- 4 September 2026
- Published by Springer Nature in Nature Medicine
- p. 1
Prediction of maternal and infant outcomes from longitudinal electronic health records with a mother–child AI agent
- 4 September 2026
- Published by Springer Nature in Nature Medicine
- p. 1
Open AccessPrediction of maternal and infant outcomes from longitudinal electronic health records with a mother–child AI agent
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Microwave Theory and Techniques
- Vol. 74  (7) , 6562-6577
A Reinforcement-Conditioned Diffusion Model for Electromagnetic Wave Morphology Manipulation of Moving Object Inside Complex Media
Achieving flexible manipulation of specific electromagnetic wave morphology has become an indispensable technique for numerous promising applications, such as wireless communication, energy harvesting, and parameter estimation. However, how to realize efficient and noninvasive electromagnetic wave manipulation for moving objects within complex media remains a significant challenge due to the complicated disordered scattering characteristics. To address this problem, this article proposes a manipulation methodology based on a novel reinforcement-conditioned diffusion model (RC-DM). Specifically, the generalized Wigner–Smith (GWS) operator is leveraged to achieve remarkable target-centric field enhancement or spatial suppression for the desired object inside complex scattering media. Subsequently, to enable noninvasive and accurate wave morphology manipulation for moving objects, the RC-DM is proposed to form the desired electromagnetic field solely through the utilization of the system scattering matrix. Furthermore, an improved sampling process of RC-DM is proposed, offering enhanced efficiency and accuracy to realize a near-real-time response of wave manipulation for moving objects. Finally, the corresponding versatility and performance are comprehensively demonstrated through the numerical validation and experiment under different moving trajectories. The results show that our proposed methodology has excellent effectiveness and robustness to address the challenge of electromagnetic wave morphology manipulation for moving objects inside complex scattering media.
- 28 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Microwave Theory and Techniques
- Vol. 74  (7) , 6562-6577
A Reinforcement-Conditioned Diffusion Model for Electromagnetic Wave Morphology Manipulation of Moving Object Inside Complex Media
Achieving flexible manipulation of specific electromagnetic wave morphology has become an indispensable technique for numerous promising applications, such as wireless communication, energy harvesting, and parameter estimation. However, how to realize efficient and noninvasive electromagnetic wave manipulation for moving objects within complex media remains a significant challenge due to the complicated disordered scattering characteristics. To address this problem, this article proposes a manipulation methodology based on a novel reinforcement-conditioned diffusion model (RC-DM). Specifically, the generalized Wigner–Smith (GWS) operator is leveraged to achieve remarkable target-centric field enhancement or spatial suppression for the desired object inside complex scattering media. Subsequently, to enable noninvasive and accurate wave morphology manipulation for moving objects, the RC-DM is proposed to form the desired electromagnetic field solely through the utilization of the system scattering matrix. Furthermore, an improved sampling process of RC-DM is proposed, offering enhanced efficiency and accuracy to realize a near-real-time response of wave manipulation for moving objects. Finally, the corresponding versatility and performance are comprehensively demonstrated through the numerical validation and experiment under different moving trajectories. The results show that our proposed methodology has excellent effectiveness and robustness to address the challenge of electromagnetic wave morphology manipulation for moving objects inside complex scattering media.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP  (15209210) , 1-13
Boosting Instance Awareness Via Cross-View Correlation With 4D Radar and Camera for 3D Object Detection
4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the effectiveness of existing radar–camera fusion paradigms. BEV-level fusion offers global scene understanding but suffers from weak instance focus, while perspective-level fusion captures instance details but lacks holistic context. To address these limitations, we propose SIFormer, a scene–instance aware transformer for 3D object detection using 4D radar and camera. SIFormer first suppresses background noise during view transformation through segmentation- and depth-guided localization. It then introduces a cross-view activation mechanism that injects 2D instance cues into BEV space, enabling reliable instance awareness under weak radar geometry. Finally, a transformer-based fusion module aggregates complementary image semantics and radar geometry for robust perception. As a result, with the aim of enhancing instance awareness, SIFormer bridges the gap between the two paradigms, combining their complementary strengths to address inherent sparse nature of radar and improve detection accuracy. Experiments demonstrate that SIFormer achieves state-of-the-art performance on View-of-Delft, TJ4DRadSet and NuScenes datasets. The code will be made publicly available.
- 17 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP  (15209210) , 1-13
Boosting Instance Awareness Via Cross-View Correlation With 4D Radar and Camera for 3D Object Detection
4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the effectiveness of existing radar–camera fusion paradigms. BEV-level fusion offers global scene understanding but suffers from weak instance focus, while perspective-level fusion captures instance details but lacks holistic context. To address these limitations, we propose SIFormer, a scene–instance aware transformer for 3D object detection using 4D radar and camera. SIFormer first suppresses background noise during view transformation through segmentation- and depth-guided localization. It then introduces a cross-view activation mechanism that injects 2D instance cues into BEV space, enabling reliable instance awareness under weak radar geometry. Finally, a transformer-based fusion module aggregates complementary image semantics and radar geometry for robust perception. As a result, with the aim of enhancing instance awareness, SIFormer bridges the gap between the two paradigms, combining their complementary strengths to address inherent sparse nature of radar and improve detection accuracy. Experiments demonstrate that SIFormer achieves state-of-the-art performance on View-of-Delft, TJ4DRadSet and NuScenes datasets. The code will be made publicly available.
- Top Cited Papers
- 11 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (6) , 7032-7049
OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving
The rapid advancement of deep learning has intensified the need for comprehensive data for use by autonomous driving algorithms. High-quality datasets are crucial for the development of effective data-driven autonomous driving solutions. Next-generation autonomous driving datasets must be multimodal, incorporating data from advanced sensors that feature extensive data coverage, detailed annotations, and diverse scene representation. To address this need, we present OmniHD-Scenes, a large-scale multimodal dataset that provides comprehensive omnidirectional high-definition data. The OmniHD-Scenes dataset combines data from 128-beam LiDAR, six cameras, and six 4D imaging radar systems to achieve full environmental perception. The dataset comprises 1501 clips, each approximately 30-s long, totaling more than 450 K synchronized frames and more than 5.85 million synchronized sensor data points. We also propose a novel 4D annotation pipeline. To date, we have annotated 200 clips with more than 514 K precise 3D bounding boxes. These clips also include semantic segmentation annotations for static scene elements. Additionally, we introduce a novel automated pipeline for generation of the dense occupancy ground truth, which effectively leverages information from non-key frames. Alongside the proposed dataset, we establish comprehensive evaluation metrics, baseline models, and benchmarks for 3D detection and semantic occupancy prediction. These benchmarks utilize surround-view cameras and 4D imaging radar to explore cost-effective sensor solutions for autonomous driving applications. Extensive experiments demonstrate the effectiveness of our low-cost sensor configuration and its robustness under adverse conditions.
- 11 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48  (6) , 7032-7049
Top Cited PapersOmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving
The rapid advancement of deep learning has intensified the need for comprehensive data for use by autonomous driving algorithms. High-quality datasets are crucial for the development of effective data-driven autonomous driving solutions. Next-generation autonomous driving datasets must be multimodal, incorporating data from advanced sensors that feature extensive data coverage, detailed annotations, and diverse scene representation. To address this need, we present OmniHD-Scenes, a large-scale multimodal dataset that provides comprehensive omnidirectional high-definition data. The OmniHD-Scenes dataset combines data from 128-beam LiDAR, six cameras, and six 4D imaging radar systems to achieve full environmental perception. The dataset comprises 1501 clips, each approximately 30-s long, totaling more than 450 K synchronized frames and more than 5.85 million synchronized sensor data points. We also propose a novel 4D annotation pipeline. To date, we have annotated 200 clips with more than 514 K precise 3D bounding boxes. These clips also include semantic segmentation annotations for static scene elements. Additionally, we introduce a novel automated pipeline for generation of the dense occupancy ground truth, which effectively leverages information from non-key frames. Alongside the proposed dataset, we establish comprehensive evaluation metrics, baseline models, and benchmarks for 3D detection and semantic occupancy prediction. These benchmarks utilize surround-view cameras and 4D imaging radar to explore cost-effective sensor solutions for autonomous driving applications. Extensive experiments demonstrate the effectiveness of our low-cost sensor configuration and its robustness under adverse conditions.
- Top Cited Papers
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (6) , 7630-7645
Doracamom: Joint 3D Detection and Occupancy Prediction With Multi-View 4D Radars and Cameras for Omnidirectional Perception
3D object detection and occupancy prediction are critical tasks in autonomous driving, attracting significant attention. Despite the potential of recent vision-based methods, they encounter challenges under adverse conditions. Thus, integrating cameras with next-generation 4D imaging radar to achieve unified multi-task perception is highly significant, though research in this domain remains limited. In this paper, we propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction, enabling comprehensive environmental perception. Specifically, we introduce a novel Coarse Voxel Queries Generator that integrates geometric priors from 4D radar with semantic features from images to initialize voxel queries, establishing a robust foundation for subsequent Transformer-based refinement. To leverage temporal information, we design a Dual-Branch Temporal Encoder that processes multi-modal temporal features in parallel across BEV and voxel spaces, enabling comprehensive spatio-temporal representation learning. Furthermore, we propose a Cross-Modal BEV-Voxel Fusion module that adaptively fuses complementary features through attention mechanisms while employing auxiliary tasks to enhance feature quality. Extensive experiments on the OmniHD-Scenes, View-of-Delft (VoD), and TJ4DRadSet datasets demonstrate that Doracamom achieves state-of-the-art performance in both tasks, establishing new benchmarks for multi-modal 3D perception. Code and models can be available at https: //github.com/TJRadarLab/Doracamom.
- 22 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36  (6) , 7630-7645
Top Cited PapersDoracamom: Joint 3D Detection and Occupancy Prediction With Multi-View 4D Radars and Cameras for Omnidirectional Perception
3D object detection and occupancy prediction are critical tasks in autonomous driving, attracting significant attention. Despite the potential of recent vision-based methods, they encounter challenges under adverse conditions. Thus, integrating cameras with next-generation 4D imaging radar to achieve unified multi-task perception is highly significant, though research in this domain remains limited. In this paper, we propose Doracamom, the first framework that fuses multi-view cameras and 4D radar for joint 3D object detection and semantic occupancy prediction, enabling comprehensive environmental perception. Specifically, we introduce a novel Coarse Voxel Queries Generator that integrates geometric priors from 4D radar with semantic features from images to initialize voxel queries, establishing a robust foundation for subsequent Transformer-based refinement. To leverage temporal information, we design a Dual-Branch Temporal Encoder that processes multi-modal temporal features in parallel across BEV and voxel spaces, enabling comprehensive spatio-temporal representation learning. Furthermore, we propose a Cross-Modal BEV-Voxel Fusion module that adaptively fuses complementary features through attention mechanisms while employing auxiliary tasks to enhance feature quality. Extensive experiments on the OmniHD-Scenes, View-of-Delft (VoD), and TJ4DRadSet datasets demonstrate that Doracamom achieves state-of-the-art performance in both tasks, establishing new benchmarks for multi-modal 3D perception. Code and models can be available at https: //github.com/TJRadarLab/Doracamom.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30  (1) , 266-278
Remote PPG Measurement Using a Synergistic Time-Frequency Network
Remote photoplethysmography (rPPG) aims to estimate the blood volume pulse (BVP) signal from facial videos. Existing rPPG approaches still suffer from limitations. We attribute this issue to two primary problems: (1) the reliance solely on time-domain processing that makes the signal susceptible to interference, and (2) the presence of a phase discrepancy between the supervision signal and the ground-truth PPG. To address these problems, we propose TFSNet, a novel time-frequency synergy network for rPPG signal estimation and heart rate prediction. Specifically, we leverage time-frequency fusion (TFF) module, which integrates frequency-domain information into the learning process to enrich the feature representations. Additionally, we introduce the amplitude-phase decoupling (APD) module, which apply phase compensation in frequency domain to mitigate the adverse effects of incorrect phase supervision. Extensive experiments demonstrate that TFSNet achieves state-of-the-art performance, significantly outperforming current approaches in both accuracy and robustness.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30  (1) , 266-278
Remote PPG Measurement Using a Synergistic Time-Frequency Network
Remote photoplethysmography (rPPG) aims to estimate the blood volume pulse (BVP) signal from facial videos. Existing rPPG approaches still suffer from limitations. We attribute this issue to two primary problems: (1) the reliance solely on time-domain processing that makes the signal susceptible to interference, and (2) the presence of a phase discrepancy between the supervision signal and the ground-truth PPG. To address these problems, we propose TFSNet, a novel time-frequency synergy network for rPPG signal estimation and heart rate prediction. Specifically, we leverage time-frequency fusion (TFF) module, which integrates frequency-domain information into the learning process to enrich the feature representations. Additionally, we introduce the amplitude-phase decoupling (APD) module, which apply phase compensation in frequency domain to mitigate the adverse effects of incorrect phase supervision. Extensive experiments demonstrate that TFSNet achieves state-of-the-art performance, significantly outperforming current approaches in both accuracy and robustness.