叶昕辰 简历

IEEE协会会员，ACM协会会员，CCF会员

教育经历：

 2010/09－2016/01，天津大学，电子信息工程学院，博士（硕博连读），导师：王瑶，杨敬钰

 2006/09－2010/07，天津大学，电子信息工程学院，学士

工作经历：

 2019/12 - 至今,大连理工大学，国际信息与软件学院，副教授

 2016/06 - 2019/12，大连理工大学，国际信息与软件学院，讲师

 2014/12 - 2015/12，瑞士洛桑联邦理工学院，电子系，访问学者（中瑞科技合作计划），合作导师：Pascal Frossard

主持或参加科研项目（课题）及人才计划项目情况：

军工横向项目，模型和数据联合驱动的多模态融合智能识别，2021-10至2023-10，105万，主持

国家自然科学基金委面上项目，恶劣非结构化环境下的多模态联合鲁棒感知及三维重建，2024-01至2027-12，61万，主持

大连市高层次人才创新支持计划项目，面向水下近距离深度感知及场景重建，2022-1至2023-12，10万，主持

国家自然科学基金委青年项目，融合多重线索的高质量场景深度感知，2018-01至2020-12，24万，主持

国家自然科学基金委面上项目，水下近距离场景的智能立体视觉感知，2020-01至2023-12，61万，主持

国家自然科学基金委重大仪器项目，水下主从式高动态范围三维全景感知探测设备，2021-01至2025-12，676万，参与

国家自然科学基金委重点项目，水下敏捷机器人抓捕性能智能评测模型与融合平台，2019-01至2021-12，300万，参与

国家自然科学基金委重点项目，面向公共安全的复杂场景多源视频智能感知与高效管理，2020-01至2024-12，301万，参与

国家自然科学基金委面上项目，多信息融合的复杂动态场景高效感知与语义重建，2018-01至2021-12，70.3万，参与

 

代表性研究成果和学术奖励情况

一、期刊论文

22. Xinchen Ye, Yanjun Guo, Baoli Sun, Rui Xu, Zhihui Wang, Haojie Li, C2ANet: Cross-Scale and Cross-Modality Aggregation Network for Scene Depth Super-Resolution, IEEE Trans. Multimedia, 2023 （CCF-B, 中科院1区TOP, IF:7.3）

21. Xinchen Ye, Jinyi Zhang, Yazhi Yuan, Rui Xu, Zhihui Wang, Haojie Li, Underwater Depth Estimation via Stereo Adaptation Networks, IEEE Trans. Circuits and Systems for Video Technology, 2023 （CCF-B, 中科院1区TOP, IF:8.181）

20. Jingyu Yang, Wenqiang Xu, Xinchen Ye, Pascal Frossard, Kun Li, High-Quality Reconstruction of Depth Maps from Graph-Based Non-Uniform Sampling, IEEE Trans. Multimedia. 2023 （CCF-B, 中科院1区TOP, IF:7.3）

19. Jian shi, Baoli Sun, Xinchen Ye*, et al., Semantic Decomposition Network with Contrastive and Structural Constraints for Dental Plaque Segmentation, IEEE Trans. on Medical Imaging, early access, Nov 2022. （中科院1区TOP, IF:11.073）

18. Hong Zhang, Xinchen Ye*, Shenglun Chen, et al., The Farther the Better: Balanced Stereo Matching via Depth-based Sampling and Adaptive Feature Refinement, IEEE Trans. Circuits and Systems for Video Technology, 32 (7): 4613-4625, 2022. （CCF-B, 中科院1区TOP, IF:8.181）

17. Xinchen Ye, Xin Fan*, Mingliang Zhang, Rui Xu, Wei Zhong, Unsupervised Monocular Depth Estimation via Recursive Stereo Distillation, IEEE Trans.  Image Processing, 30: 4492 - 4504, 2021. （CCF-A, 中科院1区TOP, IF:11.041）

16. Xinchen Ye*, Shude Chen, Rui Xu, DPNet: Detail-Preserving Network for High Quality Monocular Depth Estimation, Pattern Recognition, 109:107578, 2021.（CCF-B, 中科院1区TOP, IF:8.518）

15. Rui Xu, Tiantian Liu, Xinchen Ye*, et al., Joint Extraction of Retinal Vessels and Centerlines Based on Deep Semantics and Multi-Scaled Cross-Task Aggregation, IEEE Journal of Biomedical and Health Informatics, 25(7):2722-2732, 2021 （中科院1区TOP, IF:7.7）

14. Xinchen Ye, Baoli Sun, Zhihui Wang*, Jingyu Yang, Rui Xu, Haojie Li, Baopu Li, PMBANet: Progressive Multi-Branch Aggregation Network for Scene Depth Super-Resolution, IEEE Transactions on Image Processing, Accepted, 2020. （CCF-A, 中科院1区TOP, IF:11.041）

13. Xinchen Ye*, Mingliang Zhang, Jingyu Yang, Xin Fan, Fangfang Guo, A Sparsity-Promoting Image Decomposition Model for Depth Recovery, Pattern Recognition, DOI: 10.1016/j.patcog.2020.107506, 2020. （CCF-B, 中科院1区TOP, IF:8.518）

12. Xinchen Ye; Zheng Li; Baoli Sun; et al.; Deep Joint Depth Estimation and Color Correction from Monocular Underwater Images based on Unsupervised Adaptation Networks, IEEE Trans. Circuits and Systems for Video Technology, 2020. （CCF-B, 中科院1区TOP, IF:8.181）

11. Zhihui Wang; Xinchen Ye*; Baoli Sun; Jingyu Yang; Rui Xu, Haojie Li; Depth Upsampling based on Deep Edge-Aware Learning, Pattern Recognition, Pattern Recognition, DOI: 10.1016/j.patcog.2020.107274, 2020. （CCF-B, 中科院1区TOP, IF:8.518）

10. Mingliang Zhang; Xinchen Ye*; Xin Fan; Wei Zhong; Unsupervised Depth Estimation from Monocular Videos with Hybrid Geometric-refined Loss and Contextual Attention, Neurocomputing, DOI: 10.1016/j.neucom.2019.10.107, 2020. （CCF-C, 中科院2区, IF:5.981）

9. Xinchen Ye*; Xiang Ji; Baoli Sun; Shenglun Chen; Zhihui Wang; Haojie Li; DRM-SLAM: Towards Dense Reconstruction of Monocular SLAM with Scene Depth Fusion, Neurocomputing, DOI: 10.1016/j.neucom.2020.02.044, 2020. （CCF-C, 中科院2区, IF:5.981）

8. Mingliang Zhang; Xinchen Ye*; Xin Fan; Unsupervised Detail-Preserving Network for High Quality Monocular Depth Estimation, Neurocomputing,  DOI: 10.1016/j.neucom.2020.05.015, 2020. （CCF-C, 中科院2区, IF:5.981）

7. Rui Xu, Zhen Cong, Xinchen Ye*, Pulmonary Textures Classification via a Multi-Scale Attention Network, IEEE journal of Biomedical and Health Informatics, doi: 10.1109/JBHI.2019.2950006, 2019.（中科院1区TOP, IF:7.7）

6. Jingyu Yang, Zhongyu Jiang, Xinchen Ye, Kun Li; Depth Super-Resolution with Color Guidance: A Review, Book chapter, pp 51-65, RGB-D Image Analysis and Processing, Springer, 2019 （著作）

5. Jingyu Yang, Xinchen Ye*, Pascal Frossard, Global autoregressive depth recovery via non-local iterative filtering, IEEE Trans. on Broadcasting, 65(1), 123-137, 2018.（中科院1区TOP, IF:4.308）

4. Jingyu Yang, Xuemeng Yang, Xinchen Ye* and Chunping Hou. Reconstruction of Structurally-Incomplete Matrices with Reweighted Low-rank and Sparsity Priors, IEEE Trans. Image Processing, vol. 26, no. 3, pp. 1158-1172, 2017. （CCF-A, 中科院1区TOP, IF:11.041）

3. Xinchen Ye, Jingyu Yang, Xin Sun, et al., Foreground-Background Separation from Video Clips via Motion Assisted Matrix Restoration, IEEE Trans. Circuits and Systems for Video Technology, vol. 25, no. 11, pp. 1721-1734, 2015. （CCF-B, 中科院1区TOP, IF:8.181）

2. Xinchen Ye, Jingyu Yang, Hao Huang, Chunping Hou, Yao Wang, Computational Multi-view Imaging with Kinect, IEEE Trans. Broadcasting, vol. 60, no. 3, pp. 540-554, 2014. （中科院1区TOP, IF:4.308）

1. Jingyu Yang, Xinchen Ye*, Kun Li, Chunping Hou, Yao Wang, Color-Guided Depth Recovery From RGB-D Data Using an Adaptive Autoregressive Model, IEEE Trans. Image Processing, vol. 23, no. 8, pp. 3443 - 3458, 2014. （CCF-A, 中科院1区TOP, IF:11.041）

二、会议论文

31. Shi Tang, Xinchen Ye*, Fei Xue, Rui Xu. Cross-Modality Depth Estimation via Unsupervised Stereo RGB-to-Infrared Translation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. (CCF-B)

30. Baoli Sun, Xinchen Ye, Tiantian Yan, Zhihui Wang, Haojie Li, Zhiyong Wang, Fine-grained Action Recognition with Robust Motion Representation Decoupling and Concentration, Oct 10 2022, ACMMM 2022, Lisbon, Portugal. (CCF-A)

29. Biao Wu, Xinchen Ye*, Fei Xue, Rui Xu, Learning Data Hallucination and Reciprocal Guidance for Underwater Depth Estimation and Color Correction, IEEE ICME 2022, Taipei, China. (CCF-B)

28. Wei Zhong, Yazhi Yuan, Xinchen Ye*, Dian Zheng, and Rui Xu, Underwater stereo matching via unsupervised appearance and feature adaptation networks, IEEE ICASSP, 2022, Singapore. (CCF-B)

27. Xinchen Ye*, Rui Xu, Zheng Sun, Low-Dose CT Reconstruction via Dual-Domain Learning and Controllable Modulation, MICCAI 2022, Singapore. (医学顶级会议)

26. Rui Xu, Jiaxin Zhao, Xinchen Ye*, Pengcheng Wu, Yen-Wei Chen, Local-Region and Cross-Dataset Contrastive Learning for Retinal Vessel Segmentation, MICCAI 2022, Singapore. (医学顶级会议)

25. Baoli Sun, Xinchen Ye*, Baopu Li, Haojie Li, Zhihui Wang, Rui Xu, Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, virtual. (CCF-A)

24. Qi Jia, ZhengJun Li, Xin Fan*, Haotian Zhao, Shiyu Teng, Xinchen Ye, Longin Jan Latecki, Leveraging Line-point Consistence to Preserve Structures for Wide Parallax Image Stitching, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021,  (CCF-A)

23. Xinchen Ye*, Baoli Sun, Zhihui Wang, Jingyu Yang, Rui Xu, Haojie Li, Baopu Li, Depth Super-Resolution via Deep Controllable Slicing Network, ACM International Conference on Multimedia, 2020, Seattle, USA. (CCF-A)

22. Xinchen Ye*, Mingliang Zhang, Xin Fan, Rui Xu, Juncheng Pu, Ruoke Yan, Cascaded Detail-Aware Network for Unsupervised Monocular Depth Estimation, ICME 2020, London, UK.(CCF-B)

21. Rui Xu, Tiantian Liu, Xinchen Ye*, Yen-Wei Chen, Boosting Connectivity in Retinal Vessel Segmentation via a Recursive Semantics-Guided Network, MICCAI 2020, Lima, Peru. (医学顶级会议)

20. Xinchen Ye, Yuyao Xu, Rui Xu*, Shoji Kido, Noriyuki Tomiyama, Detail-Revealing Deep Low-Dose CT Reconstruction, International Conference on Pattern Recognition, ICPR 2020. (CCF-C)

19. Rui Xu, Xiao Cao, Yufeng Wang, Yen-wei Chen, Xinchen Ye*, Lin Lin, Wenchao Zhu, Chao Chen, Fangyi Xu, Yong Zhou, Hongjie Hu, Shoji Kido, Noriyuki Tomiyama, Unsupervised Detection of Pulmonary Opacities for Computer-Aided Diagnosis of COVID-19 on CT Images, International Conference on Pattern Recognition, ICPR 2020. (CCF-C)

18. Rui Xu, Yi Wang, Tiantian Liu, Xinchen Ye*, Lin Lin, Yen-wei Chen, Shoji Kido, Noriyuki Tomiyama, BG-Net: Boundary-Guided Network for Lung Segmentation on Clinical CT Images, International Conference on Pattern Recognition, ICPR 2020. (CCF-C)

17. Rui Xu, Zhen Cong, Xinchen Ye*, Shoji Kido, Noriyuki Tomiyama, Uuspervised Content-Preserved Adaptation Network for Classification of Pulmonary Textures from different CT Scanners, IEEE ICASSP, 2020, Barcelona, Spain.（CCF-B）

16. Rui Xu, Xinchen Ye*, Guiliang Jiang, Tiantian Liu, Liang Li, Satoshi Tanaka, Retinal Vessel Segmentation via A Semantics and Multi-Scale Aggregation Network, IEEE ICASSP, 2020, Barcelona, Spain.（CCF-B）

15.  Xinchen Ye*, Mingliang Zhang, Rui Xu, Wei Zhong, Xin Fan, Unsupervised Monocular Depth Estimation based on Dual Attention Mechanism and Depth-Aware Loss. IEEE International Conference on Multimedia and Expo, ICME 2019, Shanghai, China. (CCF-B)

14. Jingyu Yang, Wenqiang Xu, Xinchen Ye, Pascal Frossard and Kun Li*, "Graph Based Non-Uniform Sampling and Reconstruction of Depth Maps," IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 2324-2328.

13. Xinchen Ye*, Hongcan Xu, Xiang Ji, Rui Xu, Underwater Image Enhancement using Stacked Generative Adversarial Networks. Pacific-Rim Conference on Multimedia, PCM 2018, Hefei, China. (CCF-C)

12. Xinchen Ye*, Mingliang Zhang, Qianyu Yan, Xin Fan, Zhongxuan Luo, Image Denoising Based on Non-Parametric ADMM Algorithm. Pacific-Rim Conference on Multimedia, PCM 2018, Hefei, China. (CCF-C)

11. Rui Xu, Guiliang Jiang, Xinchen Ye*, Yen-Wei Chen, Retinal Vessel Segmentation via Multiscaled Deep-Guidance, Pacific-Rim Conference on Multimedia, PCM 2018, Hefei, China. (CCF-C)

10. Xiang Ji, Xinchen Ye*, Hongcan Xu, Haojie Li, Dense Reconstruction from Monocular SLAM with Fusion of Sparse Map-Points and CNN-Inferred Depth. IEEE International Conference on Multimedia and Expo, ICME 2018, San Diego, USA. (CCF-B)

9. Xiangyue Duan, Xinchen Ye*, Yang Li, Haojie Li,High Quality Depth Estimation from Monocular Images Based on Depth Prediction and Enhancement Sub-Networks. IEEE International Conference onMultimedia and Expo, ICME 2018, San Diego, USA. (CCF-B)

8. Xinchen Ye*, Xiangyue Duan, Haojie Li, Depth Super-Resolution With Deep Eedge-Inference Network and Edege-Guided Depth Filling. IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, Alberta, Canada.（CCF-B）

7. Rui Xu, Zhen Cong, Xinchen Ye*, Pulmonary Textures Classification Using A Deep Neural Network with Appearence and Geometry Cues, IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2018, Calgary, Alberta, Canada.（CCF-B）

6. Yujie Wang, Kun Li, Jingyu Yang*, Xinchen Ye. Intrinsic Decomposition from A Single RGB-D Image with Sparse and Non-local Priors. IEEE International Conference on Multimedia and Expo, ICME 2017, Hongkong, China. （CCF-B） 

5. Xinchen Ye, Xiaolin Song and Jingyu Yang*. Depth Recovery via Decomposition of Polynomial and Piece-wise Constant Signals. Visual Communications and Image Processing, 2016, Chengdu, China.

4. Jinghui Bai, Jingyu Yang and Xinchen Ye. Depth Refinement for Binocular Kinect RGB-D Cameras. Visual Communications and Image Processing, 2016, Chengdu, China.

3. Jingyu Yang, Xuemeng Yang and Xinchen Ye. Completion of Structurally-Incomplete Matrices with Reweighted Low-rank and Sparsity Priors (ReLaSP). IEEE International Conference on Acoustics, Speech and Signal Processing, 2016, pp. 1189-1193, Shanghai, China. （CCF-B）

2. Jingyu Yang, Xin Sun, Xinchen Ye and Kun Li, Background Extraction from Video Sequences via Motion-assisted Matrix Completion, IEEE International Conference on Image Processing, 2014, pp. 2437-2441, Paris, France. （CCF-B）

1. Jingyu Yang, Xinchen Ye, Kun Li and Chunping Hou. Depth Recovery using an Adaptive Colorguided Auto-Regressive Model, European Conference on Computer Vision, 2012, pp. 158-171, Venice, Italy. （CCF-B）

 

三、授权发明专利

1.国际专利

  [6] 叶昕辰；徐睿；樊鑫, 基于深度神经网络单目水下图像深度估计和颜色矫正方法，2022.4.5，美国专利，US17112499，2020.12.04

  [5] 叶昕辰；仲维；王智慧；李豪杰；林林；樊鑫；罗钟铉，一种基于单目相机的三维场景稠密重建方法，2021.12.28，美国，US16650331

  [4] 叶昕辰；仲维；李豪杰；林林；樊鑫；罗钟铉，一种基于深度预测和增强子网络的高质量深度估计方法，2022.2.1，美国，US16649322

  [3] 徐睿；叶昕辰；李豪杰；林林，面向多种CT肺部纹理识别的非监督保内容域适应方法，2020，进入美国阶段，US17112623，2020.12.04

  [2] 徐睿；叶昕辰；李豪杰；林林，一种结合多尺度注意力的深层网络肺部纹理识别方法，2020，进入美国阶段，US17112367，2020.12.04

  [1] 徐睿；叶昕辰；林林；李豪杰；樊鑫；罗钟铉，一种基于深度神经网络提取表观和几何特征的肺部纹理识别方法，2021.11.9，US11170502

2.国内专利 

[21] 叶昕辰；吕佳龙；徐睿；樊鑫，一种基于卷积神经网络的立体视觉无监督深度估计方法，2022，中国

[20] 叶昕辰；徐睿；樊鑫；张明亮，一种基于上下文注意力机制的单目无监督深度估计方法，2022，中国

[19] 叶昕辰；黄宏威；徐睿; 樊鑫，一种基于深度神经网络的单目水下图像深度估计和颜色矫正方法，2022，中国

[18] 叶昕辰；徐睿；孙宝利；王智慧；李豪杰，一种基于深度神经网络的多信息渐进融合的场景深度超分辨率方法，2022，中国

[17] 叶昕辰；徐禹尧；徐睿；樊鑫，一种基于孪生反馈网络的低剂量CT重建方法，2020，中国

[16] 徐睿；叶昕辰；丛臻，一种结合多尺度注意力的深层网络肺部纹理识别方法，2020，中国

[15] 徐睿；叶昕辰；丛臻，一种面向多厂家计算机断层扫描肺部纹理识别的非监督保内容域适应网络方法，2020，中国

[14] 徐睿；叶昕辰；姜桂良；刘恬恬, 一种语义和多尺度融合网络的眼底图像血管分割方法，2020，中国

[13] 叶昕辰，纪祥，徐弘灿，李豪杰，一种基于单目相机的三维场景稠密重建方法。2020，中国, 201810207145.7

[12] 叶昕辰，张明亮，蔡钰，樊鑫，一种基于非参数化交替方向乘子法的图像去噪算法。2020，中国，201810207235.6

[11] 叶昕辰，段祥越，严倩羽，李豪杰，一种基于深度神经网络的多信息融合的场景深度恢复方法。2019，中国，201810208334.6 

[10] 叶昕辰，李豪杰，李阳，段祥越，一种基于深度预测和增强子网络的高质量深度估计方法。2019，中国，201810207285.4

[9] 徐睿，叶昕辰，丛臻，一种基于深度神经网络提取表观和几何特征的肺部纹理识别方法。2019，中国，201810206846.9

[8] 徐睿，叶昕辰，一种基于多尺度深监督网络的视网膜图像血管分割方法.2019，中国，201811471196.7

[7] 叶昕辰，李豪杰，樊鑫，罗钟铉，一种联合全局建模和非局部滤波的深度计算重建算法。2018，中国，201610680688.1 

[6] 叶昕辰，李豪杰，樊鑫，罗钟铉，一种基于信号分解的场景深度恢复方法。2018，中国，201610823231.1

[5] 叶昕辰，李豪杰，樊鑫，罗钟铉，一种基于Kinect相机的多视点深视频复原方法。2018，中国，201610680651.9

[4] 杨敬钰，杨雪梦，叶昕辰，基于低秩矩阵重建的结构性缺失图像填充方法。2015，中国，201510264039.9

[3] 杨敬钰，叶昕辰，侯春萍，基于自回归模型深度恢复的参数自适应选取方法。2013，中国，201310073242.9

[2] 杨敬钰，叶昕辰，侯春萍，李坤. 采用自回归模型对深度图进行超分辨率重建的方法，2012，中国，201210109883.0

[1] 杨敬钰，叶昕辰，侯春萍，李坤. 基于飞行时间TOF相机的深度计算成像方法，2012，中国，201210110335.X

四、获奖情况

  2022大连市高层次人才（青年才俊），大连市高层次人才奖励，大连市

  2022 ACM International Conference on Multimedia Retrieval (ACM ICMR, CCF-B会议)，第三名

  2018年度 ACM新星奖（大连）（颁奖于ACM TURC 2019）

  ICME 2017 最佳（铂金）论文奖: (World’s FIRST 10K Best Paper Award—Platinum Best Paper)

 

五、社会兼职

    水下机器人目标抓取大赛，网站主席，外场裁判

 CCF中国多媒体协会 ChinaMM 2019 Web Chair

 IEEE ICIP, PCM, ICME, ICASSP, PRCV, ACCV 等会议审稿人

 IEEE Trans. Image Processing, IEEE Trans. CSVT, IEEE Trans. Cybernetics,IEEE Access, Neuro Computing, Information Sciences等期刊审稿人