论文出版

Benxiang Zhai(翟本祥), Yifang Xu(徐一舫), Guofeng Zhang, Yang Li(李杨), Sidan Du(都思丹) (2025). FaceSnap: Enhanced ID-Fidelity Network forTuning-Free Portrait Customization. In ICANN 2025.

Yifang Xu(徐一舫), Benxiang Zhai(翟本祥), 孙运卓, Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2025). HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion. In CVPR 2025.

Jinghao Cao(曹靖豪), Sheng Liu(刘晟), Chaofan Wu(武超凡), Yang Li(李杨), Sidan Du(都思丹) (2025). ATHENA - Autonomous Vehicle Trajectory Planning Considered Human Action Awareness. In IEEE Signal Processing Letters.

Yifang Xu(徐一舫), 孙运卓, Benxiang Zhai(翟本祥), Wenxin Liang, Yang Li(李杨), Sidan Du(都思丹) (2025). Zero-shot Video Moment Retrieval via Off-the-shelf Multimodal Large Language Models. In AAAI-25.

Jingzhao Dai(戴京昭), Yang Li(李杨), Sidan Du(都思丹) (2025). HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion. In IET Image Processing.

Yifang Xu(徐一舫), Chenyu Zhang, Benxiang Zhai(翟本祥), Sidan Du(都思丹) (2025). HP3: Tuning-Free Head-Preserving Portrait Personalization Via 3D-Controlled Diffusion Models. In IEEE Signal Processing Letters.

Xuejiao Hu(胡雪娇), Jingzhao Dai(戴京昭), Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2024). An efficient action proposal processing approach for temporal action detection. In Neurocomputing.

Jinghao Cao(曹靖豪), Ming Li(李明), Sheng Liu(刘晟), Yang Li(李杨), Sidan Du(都思丹) (2024). CASSC: Context-aware method for depth guided semantic scene completion. In IET Image Process.

Jinghao Cao(曹靖豪), Sheng Liu(刘晟), Xiong Yang(杨雄), Yang Li(李杨), Sidan Du(都思丹) (2024). ARES: Text-Driven Automatic Realistic Simulator for Autonomous Traffic. In IEEE Signal Processing Letters.

Yifang Xu(徐一舫), Yunzhuo Sun, Benxiang Zhai(翟本祥), Zien Xie(谢子恩), Youyao Jia, Sidan Du(都思丹) (2024). Modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection. In ICME 2024.

Shijie Wang(王师捷), Xuejiao Hu(胡雪娇), Sheng Liu(刘晟), Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2024). TIG: A Multitask Temporal Interval Guided Framework for Key Frame Detection. In IEICE TRANS.

Siyuan Bei, Yu Zhou;, Yao Yu, Sidan Du(都思丹) (2024). Multi-View Weakly-Supervised 3D Human Pose Estimation for Depth Maps via SoG With Semantic Segmentation Information. In IEEE Access.

Yifang Xu(徐一舫), Yunzhuo Sun, Benxiang Zhai(翟本祥), Youyao Jia, Sidan Du(都思丹) (2024). MH-DETR: Video Moment and Highlight Detection with Cross-modal Transformer. In IJCNN 2024.

Jinghao Cao(曹靖豪), Xiong Yang(杨雄), Sheng Liu(刘晟), Tiejian Tang(唐铁健), Yang Li(李杨), Sidan Du(都思丹) (2024). DPCalib: Dual-Perspective View Network for LiDAR-Camera Joint Calibration. In Electronics 2024.

Jiaxuan Zheng(郑嘉璇), Jiayu Wu(吴佳昱), Shuwen Xu(许薯文), Sidan Du(都思丹), Yang Li(李杨) (2024). Disparity Distribution Equalization: An Effective Data Enhancement for Stereo Matching. In PAIS.

Tiejian Tang(唐铁健), Jinghao Cao(曹靖豪), Xiong Yang(杨雄), Sheng Liu(刘晟), Dongsheng Zhu, Sidan Du(都思丹), Yang Li(李杨) (2024). A Real-Time Method for Railway Track Detection and 3D Fitting Based on Camera and LiDAR Fusion Sensing. In Remote Sens.

Jinghao Cao(曹靖豪), Yang Li(李杨), Sidan Du(都思丹) (2024). Robust Artificial Intelligence-Aided Multimodal Rail-Obstacle Detection Method by Rail Track Topology Reconstruction. In Applied Sciences.

Xuejiao Hu(胡雪娇), Shijie Wang(王师捷), Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2024). Time-attentive fusion network: An efficient model for online detection of action start. In IET Image Process.

Yifang Xu(徐一舫), Yunzhuo Sun, Zien Xie(谢子恩), Benxiang Zhai(翟本祥), Sidan Du(都思丹) (2024). VTG-GPT: Tuning-Free Zero-Shot Video Temporal Grounding with GPT. In Applied Sciences.

Xuejiao Hu(胡雪娇), Shijie Wang(王师捷), Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2024). Distribution-aware Activity Boundary Representation for Online Detection of Action Start in Untrimmed Videos. In IEEE Signal Processing Letters.

Pinzhi Wang(王品智), Ming Li(李明), Jinghao Cao(曹靖豪), Sidan Du(都思丹), Yang Li(李杨) (2024). CasOmniMVS: Cascade Omnidirectional Depth Estimation with Dynamic Spherical Sweeping. In Applied Sciences.

Yunzhuo Sun, Yifang Xu(徐一舫), Zien Xie(谢子恩), Yukun Shu, Sidan Du(都思丹) (2023). GPTSee: Enhancing Moment Retrieval and Highlight Detection via Description-Based Similarity Features. In IEEE Signal Processing Letters.

Jianghai Shuai(帅江海), Ming Li(李明), Yongkang Feng(冯永康), Yang Li(李杨), Sidan Du(都思丹) (2023). A Monocular Depth Estimation Method for Indoor-Outdoor Scenes Based on Vision Transformer. In UEMCOM.

Zhiyi Zhu(朱治亦), Sheng Liu(刘晟), Jianghai Shuai(帅江海), Sidan Du(都思丹), Yang Li(李杨) (2023). 3D Associative Embedding: Multi-View 3D Human Pose Estimation in Crowded Scenes. In CNIOT.

Jingzhao Dai(戴京昭), Ming Li(李明), Xuejiao Hu(胡雪娇), Yang Li(李杨), Sidan Du(都思丹) (2023). GazeFollowTR: A Method of Gaze Following with Reborn Mechanism. In IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences.

Sheng Liu(刘晟), Jianghai Shuai(帅江海), Yang Li(李杨), Sidan Du(都思丹) (2023). MMDA: Multi-person Marginal Distribution Awareness for Monocular 3D Pose Estimation. In IET Image Processing.

Jingzhao Dai(戴京昭), Xuejiao Hu(胡雪娇), Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2023). The multi-learning for food analyses in computer vision: a survey. In Multimedia Tools and Applications.

Ming Li(李明), Xueqian Jin(靳学乾) (2022). MODE: Multi-view Omnidirectional Depth Estimation with 360° Cameras. In ECCV.

PDF 代码视频

Xuejiao Hu(胡雪娇), Jingzhao Dai(戴京昭), Ming Li(李明), 彭成磊, Yang Li(李杨), Sidan Du(都思丹) (2022). Online human action detection and anticipation in videos: A survey. In Neurocomputing.

Hanrong Wang(王汉镕), Ming Li(李明), Jie Wang(王杰), Yang Li(李杨), Sidan Du(都思丹) (2022). A Discussion of Optimization about Stereo Image Depth Estimation Based on Multi-baseline Trinocular Camera Model. In CSCI.

Jingyi Cao(曹静怡), 彭成磊, Yang Li(李杨), Sidan Du(都思丹) (2022). A Shadow Detection Method for Retaining Key Objects in Complex Scenes. In KST.

Zhaoxu Li(李兆旭), Sheng Liu(刘晟), Jue Bai(白珏), 彭成磊, Yang Li(李杨) (2022). A Novel Skeleton-based Model with Spine for 3D Human Pose Estimation. In CCWC.

Jie Wang(王杰), 彭成磊, Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2022). The study of stereo matching optimization based on multi-baseline trinocular model. In Multimedia Tools and Applications.

Xueqian Jin(靳学乾), Ming Li(李明), 彭成磊, Sidan Du(都思丹), Yang Li(李杨) (2022). Depth-based removal of thermal reflection with the light-field theory. In Journal of the Optical Society of America A.

Jue Bai(白珏), 彭成磊, Zhaoxu Li(李兆旭), Sidan Du(都思丹), Yang Li(李杨) (2021). A Study of General Data Improvement for Large-Angle Head Pose Estimation. In CAIP.

Ming Li(李明), Xuejiao Hu(胡雪娇), Jingzhao Dai(戴京昭), Yang Li(李杨), Sidan Du(都思丹) (2021). Omnidirectional stereo depth estimation based on spherical deep network. In *Image and Vision Computing *.

Yifang Xu(徐一舫), 彭成磊, Ming Li(李明), Yang Li(李杨), Sidan Du(都思丹) (2021). Pyramid Feature Attention Network for Monocular Depth Prediction. In ICME.

Qi Li(黎琪), Ma Yazhen, 彭成磊, Guo Bin, Sidan Du(都思丹), Yang Li(李杨) (2021). Pixel-level Diabetic Retinopathy Lesion Detection Using Multi-scale Convolutional Neural Network. In LifeTech.

Tong Chen(陈佟), 彭成磊, Ming Li(李明), Xudong Chen(陈旭东), Sidan Du(都思丹), Yang Li(李杨) (2021). A Review on Quantitative Analyzing Axonal Transport of Mitochondria. In LifeTech.

Zihao Zhou(周子豪), Yang Li(李杨), 彭成磊, Hanrong Wang(王汉镕), Sidan Du(都思丹) (2021). Image Processing: Facilitating Retinanet for Detecting Small Objects. In Journal of Physics Conference Series.