CV

Education

• Ph.D. Dalian University of Technology, 2014.9 - 2020.6
• M.S. China University of Geosciences (Wuhan), 2011.9 - 2014.6
• B.S. China University of Geosciences (Wuhan), 2007.9 - 2011.6

Work experience

• Assistant Researcher, Peng Cheng National Laboratory
  August 2022 – Present

• Postdoctoral Fellow, Peng Cheng National Laboratory
  August 2020 – July 2022

Publications

3D Reconstruction from Endoscopy Images: A Survey

Zhuoyue Yang, Ju Dai, Junjun Pan. "3D Reconstruction from Endoscopy Images: A Survey." *Computers in Biology and Medicine*, vol. 175, 108546, 2024.

Self-supervised Endoscopy Depth Estimation Framework with CLIP-guidance Segmentation

Zhuoyue Yang, Junjun Pan, Ju Dai*, Zhen Sun, Yi Xiao. "Self-supervised Endoscopy Depth Estimation Framework with CLIP-guidance Segmentation." *Biomedical Signal Processing and Control*, vol. 95, 106410, 2024.

Motion Editing for Quadruped Characters via Latent Frequency Embedding

Rui Zeng, Junjun Pan, Ju Dai*, Yang Gao, Junxuan Bai, Hong Qin. "Motion Editing for Quadruped Characters via Latent Frequency Embedding." *IEEE Trans. Vis. Comput. Graph.*, 2024. (CCF-A)

Hierarchical Proxy Learning for Cloth-Changing Person Re-Identification

Chenyang Yu, Xuehu Liu, Ju Dai, Pingping Zhang, Huchuan Lu. "Hierarchical Proxy Learning for Cloth-Changing Person Re-Identification." In *ICASSP 2025*, pp. 1–5.

Chat-Driven 3D Human Pose and Shape Editing with Large Language Models

Feng Zhou, Chi Li, Ju Dai*, Mengxiao Zhu, Yongmei Zhang, Yu-Kun Lai, Paul L. Rosin. "Chat-Driven 3D Human Pose and Shape Editing with Large Language Models." In *ICASSP 2025*, pp. 1–5.

LiteNeRFAvatar: A Lightweight NeRF with Local Feature Learning for Dynamic Human Avatar

Junjun Pan, Xiaoyu Li, Junxuan Bai, Ju Dai*. "LiteNeRFAvatar: A Lightweight NeRF with Local Feature Learning for Dynamic Human Avatar." *Pattern Recognition*, 2025. (JCR-Q1)

AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation

Hao Li, Ju Dai*, Xin Zhao, Kaida Ning, Feng Zhou, Lei Li, Junjun Pan. "AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation." In *Proceedings of the IEEE International Conference on Computer Vision (ICCV)*, 2025. (CCF-A)

A Bi-directional Message Passing Model for Salient Object Detection

Lu Zhang*, Ju Dai, Huchuan Lu, You He, Gang Wang. "A Bi-directional Message Passing Model for Salient Object Detection." In *Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)*, pp. 1741–1750, 2018. (CCF-A)

Cross-view Semantic Projection Learning for Person Re-identification

Ju Dai, Ying Zhang, Huchuan Lu*, Hongyu Wang. "Cross-view Semantic Projection Learning for Person Re-identification." *Pattern Recognition*, 75: 63–76, 2018. (JCR-Q1)

Video Person Re-identification by Temporal Residual Learning

Ju Dai, Pingping Zhang, Dong Wang*, Huchuan Lu, Hongyu Wang. "Video Person Re-identification by Temporal Residual Learning." *IEEE Transactions on Image Processing*, vol. 28, pp. 1366–1377, 2019. (CCF-A)

Dynamic Imposter Based Online Instance Matching for Person Search

Ju Dai, Pingping Zhang, Huchuan Lu*, Hongyu Wang. "Dynamic Imposter Based Online Instance Matching for Person Search." *Pattern Recognition*, vol. 100, 107122, 2020. (JCR-Q1)

EmoDescriptor: A Hybrid Feature for Emotional Classification in Dance Movements

Junxuan Bai, Rong Dai, Ju Dai, Junjun Pan*. "EmoDescriptor: A Hybrid Feature for Emotional Classification in Dance Movements." *Computer Animation and Virtual Worlds*, 2021.

3D-CariNet: End-to-End 3D Caricature Generation from Natural Face Images with Differentiable Renderer

Meijiang Huang, Ju Dai, Junjun Pan*, Junxuan Bai, Hong Qin. "3D-CariNet: End-to-End 3D Caricature Generation from Natural Face Images with Differentiable Renderer." *Pacific Graphics*, 2021.

Diverse Dance Synthesis via Keyframes with Transformer Controllers

Junjun Pan, Siyuan Wang, Junxuan Bai, Ju Dai*. "Diverse Dance Synthesis via Keyframes with Transformer Controllers." *Computer Graphics Forum*, 2021.

Human Motion Synthesis and Control via Contextual Manifold Embedding

Rui Zeng, Ju Dai, Junxuan Bai, Junjun Pan*, Hong Qin. "Human Motion Synthesis and Control via Contextual Manifold Embedding." *Pacific Graphics*, 2021.

Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation

Hao Li, Ju Dai*, Xin Zhao, Feng Zhou, Junjun Pan, Lei Li. "Wav2Sem: Plug-and-Play Audio Semantic Decoupling for 3D Speech-Driven Facial Animation." In *Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)*, 2025. (CCF-A)

GFENet: Group-Free Enhancement Network for Indoor Scene 3D Object Detection

Feng Zhou, Ju Dai*, Junjun Pan, Mengxiao Zhu, Xingquan Cai, Bin Huang, Chen Wang. "GFENet: Group-Free Enhancement Network for Indoor Scene 3D Object Detection." *CGI (3)*, 2023, pp. 119-136.

A Lightweight Pose Estimation Network with Multi-scale Receptive Field

Shuo Li, Ju Dai*, Zhangmeng Chen, Junjun Pan. "A Lightweight Pose Estimation Network with Multi-scale Receptive Field." *Visual Computer*, 39(8), pp. 3429-3440, 2023.

KD-Former: Kinematic and Dynamic Coupled Transformer Network for 3D Human Motion Prediction

Ju Dai, Hao Li, Rui Zeng, Junxuan Bai, Feng Zhou, Junjun Pan. "KD-Former: Kinematic and Dynamic Coupled Transformer Network for 3D Human Motion Prediction." *Pattern Recognition*, vol. 143, 109806, 2023. (JCR-Q1)

AHRNET: Attention and Heatmap-Based Regressor for Hand Pose Estimation and Mesh Recovery

Feng Zhou, Pei Shen, Ju Dai*, Na Jiang, Yong Hu, Yu-Kun Lai, Paul L. Rosin. "AHRNET: Attention and Heatmap-Based Regressor for Hand Pose Estimation and Mesh Recovery." In *ICASSP 2024*, pp. 3000-3004.

FormationCreator: Designing A VR Dance Formation System for Intangible Cultural Heritage Dance

Junkai Rao, Feng Zhou, Ju Dai*, Chi Li, Yong Hu. "FormationCreator: Designing A VR Dance Formation System for Intangible Cultural Heritage Dance." *CHI Extended Abstracts 2024*, pp. 166:1-166:7. (CCF-A)

Free Editing of Shape and Texture with Deformable Net for 3D Caricature Generation

Yuanyuan Lin, Ju Dai*, Junjun Pan, Feng Zhou, Junxuan Bai. "Free Editing of Shape and Texture with Deformable Net for 3D Caricature Generation." *Visual Computer*, 40(7), pp. 4675-4687, 2024.

MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction

Jin Li, Yang Gao, Ju Dai, Shuai Li, Aimin Hao, Hong Qin. "MPMNet: A Data-Driven MPM Framework for Dynamic Fluid-Solid Interaction." *IEEE Trans. Vis. Comput. Graph.*, 30(8), pp. 4694-4708, 2024. (CCF-A)

Foot-constrained Spatial-Temporal Transformer for Keyframe-based Complex Motion Synthesis

Hao Li, Ju Dai*, Rui Zeng, Junxuan Bai, Zhangmeng Chen, Junjun Pan. "Foot-constrained Spatial-Temporal Transformer for Keyframe-based Complex Motion Synthesis." *Computers & Animation and Virtual Worlds*, 35(1), 2024.

DGFormer: Dynamic Graph Transformer for 3D Human Pose Estimation

Zhangmeng Chen, Ju Dai*, Junxuan Bai, Junjun Pan. "DGFormer: Dynamic Graph Transformer for 3D Human Pose Estimation." *Pattern Recognition*, vol. 152, 110446, 2024. (JCR-Q1)

Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer

Zhuoyue Yang, Junjun Pan, Ju Dai, Zhen Sun, Yi Xiao. "Self-Supervised Lightweight Depth Estimation in Endoscopy Combining CNN and Transformer." *IEEE Transactions on Medical Imaging*, vol. 43, no. 5, pp. 1934–1944, 2024. (JCR-Q1)

Position-aware Guided Point Cloud Completion with CLIP Model

Feng Zhou, Qi Zhang, Ju Dai*, Lei Li, Qing Fan, Junliang Xing. "Position-aware Guided Point Cloud Completion with CLIP Model." In *Proceedings of the AAAI Conference on Artificial Intelligence*, pp. 10734–10742, 2025. (CCF-A)

Projects

• PI, National Natural Science Foundation of China (No. 62102208)
  Monocular 3D Human Pose Estimation Driven by Complex Relations and its Application in Person Re-identification

• PI, China Postdoctoral Science Foundation (No. 2020M682827)
  Research on Emotion Understanding and Affective Computing Based on Visual Perception and Its Application in Intelligent Nursing

• Participant, National Natural Science Foundation of China (No. 61771088)
  Research on Method of Deep Learning in Salient Object Detection

• Participant, National Key R&D Program of China (No. 2022ZD0115902)
  Research and Application Demonstration on Key Technologies of Smart Connected Computing in Learning Environments

Academic competition

• First Prize, Shoeprint Image Data Age Mining Challenge
  The Second China Conference on Pattern Recognition and Computer Vision (PRCV2019)