Haixin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Haixin Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Jinqiao Wang
Chinese Academy of Sciences
4 shared publications - Lu Zhou
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China
4 shared publications - Yingying Chen
Institute of Automation, Chinese Academy of Sciences, Beijing, China
4 shared publications - Ming Tang
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3 shared publications - Chunlin Leng
Institute of Automation, Chinese Academy of Sciences
1 shared publication - Jiajun Zhang
School of Artificial Intelligence University of Chinese Academy of Sciences
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7533-7538
Dual-Granularity Text Guidance for Dyadic Motion Generation
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 7533-7538
Open AccessDual-Granularity Text Guidance for Dyadic Motion Generation
- 3 August 2026
- Published by Springer Nature
- p. 276-290
TOEP: Task-Specific Operator Evolution via Multi-objective Pareto Optimization for Automatic Workflow Generation
- 3 August 2026
- Published by Springer Nature
- p. 276-290
TOEP: Task-Specific Operator Evolution via Multi-objective Pareto Optimization for Automatic Workflow Generation
- 16 August 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22 (6) , 1116-1126
Semi-supervised Learning for Detector-free Multi-person Pose Estimation
- 16 August 2025
- Published by Springer Nature in Machine Intelligence Research
- Vol. 22 (6) , 1116-1126
Semi-supervised Learning for Detector-free Multi-person Pose Estimation
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6039-6050
EFCPose: End-to-End Multi-Person Pose Estimation With Fully Convolutional Heads
Mainstream methods of multi-person pose estimation are not end-to-end. Recently, some methods build an end-to-end framework based on the DETR framework, aiming to eliminate the need for hand-crafted modules like heuristic grouping and NMS post-processing. However, these DETR-based methods suffer from a heavy memory burden of processing the high-resolution backbone feature maps with transformers. In this paper, we propose an end-to-end multi-person pose estimation method with a fully convolutional network, termed EFCPose. Different from DETR-based methods, it directly predicts instance-aware poses in a pixel-wise manner with lightweight convolutional heads, avoiding the heavy memory burden. Overall, our method adopts the center-offset formulation and a one-to-one label assignment strategy to achieve the multi-person pose estimation in an end-to-end manner. The main contribution of our fully convolutional heads includes two aspects. On the one hand, we propose an unaligned center-offset representation to learn more reliable semantic centers to replace the inconsistent geometric centers, improving the performance of instance detection. On the other hand, we propose a novel regression strategy named limb-aware adaptive regression, which leverages separate adaptive points to convert challenging long-range offsets into simplified short-range offsets and incorporates limb constraints to elevate the regression quality of joint offsets. Compared with current DETR-based end-to-end methods, EFCPose avoids high computational complexity and achieves higher accuracy. Extensive experiments on COCO Keypoint and CrowdPose benchmarks show that EFCPose outperforms other state-of-the-art bottom-up and single-stage methods without flipping augmentation.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6039-6050
EFCPose: End-to-End Multi-Person Pose Estimation With Fully Convolutional Heads
Mainstream methods of multi-person pose estimation are not end-to-end. Recently, some methods build an end-to-end framework based on the DETR framework, aiming to eliminate the need for hand-crafted modules like heuristic grouping and NMS post-processing. However, these DETR-based methods suffer from a heavy memory burden of processing the high-resolution backbone feature maps with transformers. In this paper, we propose an end-to-end multi-person pose estimation method with a fully convolutional network, termed EFCPose. Different from DETR-based methods, it directly predicts instance-aware poses in a pixel-wise manner with lightweight convolutional heads, avoiding the heavy memory burden. Overall, our method adopts the center-offset formulation and a one-to-one label assignment strategy to achieve the multi-person pose estimation in an end-to-end manner. The main contribution of our fully convolutional heads includes two aspects. On the one hand, we propose an unaligned center-offset representation to learn more reliable semantic centers to replace the inconsistent geometric centers, improving the performance of instance detection. On the other hand, we propose a novel regression strategy named limb-aware adaptive regression, which leverages separate adaptive points to convert challenging long-range offsets into simplified short-range offsets and incorporates limb constraints to elevate the regression quality of joint offsets. Compared with current DETR-based end-to-end methods, EFCPose avoids high computational complexity and achieves higher accuracy. Extensive experiments on COCO Keypoint and CrowdPose benchmarks show that EFCPose outperforms other state-of-the-art bottom-up and single-stage methods without flipping augmentation.
- 11 November 2022
- Published by Springer Nature
- p. 107-122
Regularizing Vector Embedding in Bottom-Up Human Pose Estimation
- 11 November 2022
- Published by Springer Nature
- p. 107-122
Regularizing Vector Embedding in Bottom-Up Human Pose Estimation