Selected Publications
Note: ^ indicates equal contribuion. # indicates corresponding author. (Full Publication List)
International Journal
- SAM Struggles in Concealed Scenes – Empirical Study on “Segment Anything”
- Authors: Ge-Peng Ji, Deng-Ping Fan, Peng Xu#, Ming-Ming Cheng, Bowen Zhou, Luc Van Gool
- Journal: SCIENCE CHINA Information Sciences , Volume 66, Issue 12: 226101 (2023). (CCF-A类, CCF T1分级, SCI IF: 8.8, 中国最具国际影响力学术期刊)
- Links: Paper (arXiv & Official PDF & SciEngine) ; 中国科学信息科学官方公众号解读 ; Top five most-read SCIS articles (October)
- Advances in Deep Concealed Scene Understanding
- Authors: Deng-Ping Fan#, Ge-Peng Ji, Peng Xu, Ming-Ming Cheng, Christos Sakaridis, Luc Van Gool
- Journal: Visual Intelligence (VINT), 1, 16 (2023). (中国国际影响力优秀学术期刊)
- DOI: https://doi.org/10.1007/s44267-023-00019-6
- Links: Paper (Paper & Springer link & 中译版本); Project (Link); Awesome list for COD; 视觉智能VINT官方公众号解读 ; 微信公众号解读
- Full-duplex Strategy for Video Object Segmentation
- Video Polyp Segmentation: A Deep Learning Perspective
- Authors: Ge-Peng Ji^, Guobao Xiao^, Yu-Cheng Chou^, Deng-Ping Fan#, Kai Zhao, Geng Chen, and Luc Van Gool
- Journal: Machine Intelligence Research (MIR), 2022, 19 (6): 531-549. (中国国际影响力优秀学术期刊)
- Links: Paper (arXiv & official) ; Code (PyTorch)
; Dataset Download ; Awesome Paper List ; 中译版本 ; Awesome list for VPS ; MIR News (EN) ; 公众号解读 ; YouTube Video
- Deep Gradient Learning for Efficient Camouflaged Object Detection
- Authors: Ge-Peng Ji, Deng-Ping Fan#, Yu-Cheng Chou, Dengxin Dai, Alexander Liniger, Luc Van Gool
- Journal: Machine Intelligence Research (MIR), 2023, 20 (1): 92-108. (中国国际影响力优秀学术期刊)
- Links: Paper (arXiv & Springer) ; Code (PyTorch & Jittor & Huawei Ascend)
; 中译版本; MIR News (EN) ; 微信公众号解读 ; YouTube Video
- Masked Vision-Language Transformer in Fashion
- Concealed Object Detection
- Authors: Deng-Ping Fan, Ge-Peng Ji, Ming-Ming Cheng#, Ling Shao
- Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022, 44 (10): 6024-6042. (IF: 24.314)
- Info: ESI Highly Cited Paper (1%) ; JDC 2021 Distinguish Paper ; Extension of CVPR 2020
- Links: Paper (arXiv & IEEE) ; Code (PyTorch & Jittor)
; Project Page ; Online Demo ; 中译版本 ; Awesome list for COD
- Cognitive Vision Inspired Object Segmentation Metric and Loss Function
- Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images
- Authors: Deng-Ping Fan, Tao Zhou, Ge-Peng Ji, Yi Zhou, Geng Chen#, Huazhu Fu#, Jianbing Shen#, Ling Shao
- Journal: IEEE Transactions on Medical Imaging (TMI), 2020, 39 (8): 2626-2637. (IF: 11.037)
- Info: ESI Highly Cited Paper (1%) ; Top-20 Most Cited Paper within 5 Years in IEEE TMI 2022 ; Top-50 Most Frequently Accessed Documents in IEEE TMI ; Extension of MICCAI 2020
- Links: Paper (arXiv & official) ; Code (PyTorch)
; 中译版本
; 
International Conference
- Full-duplex Strategy for Video Object Segmentation
- Progressively Normalized Self-Attention Network for Video Polyp Segmentation
- Authors: Ge-Peng Ji^, Yu-Cheng Chou^, Deng-Ping Fan#, Geng Chen, Huazhu Fu, Debesh Jha, Ling Shao
- Conference: Medical Image Computing and Computer Assisted Intervention (MICCAI), Strasbourg, France, September 27-October 1, 2021.
- Info: Early Accept (Accept rate = 13%) ; Student Travel Award (Rate = 95/1630 = 5.8%)
- Links: Paper (arXiv & official) ; Code (PyTorch)
; 中译版本
- PraNet: Parallel Reverse Attention Network for Polyp Segmentation
- Authors: Deng-Ping Fan, Ge-Peng Ji, Tao Zhou, Geng Chen, Huazhu Fu#, Jianbing Shen#, Ling Shao
- Conference: Medical Image Computing and Computer Assisted Intervention (MICCAI), Vitural, October 4-8, 2020.
- Info: Early Accept & Oral Presentation (Accept rate = 13%) ; JDC 2021 Most Influential (Application) Paper) ; Top-10 Most Cited Paper within 5 Years in MICCAI 2020 ; Best precision of MediaEval 2020 Workshop at Medico Track
- Links: Paper (arXiv & official) ; Code (PyTorch & Jittor & Huawei Ascend ModelZoo)
; 中译版本
- Camouflaged Object Detection
- Authors: Deng-Ping Fan, Ge-Peng Ji, Guolei Sun, Ming-Ming Cheng, Jianbing Shen#, Ling Shao
- Conference: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Virtual, June 14-19, 2020.
- Info: Oral Presentation (Accept rate = 335/5865 = 5.7%) ; Coverage of ‘New scientist’
- Links: Paper (official) ; Code (PyTorch)
; 中译版本
Book
- Inf-Net: an automatic lung infection segmentation network that uses CT images (Chapter 3, pp: 3-1 to 3-15)
- Authors: Tao Zhou, Deng-Ping Fan, Ge-Peng Ji, Geng Chen, Huazhu Fu, Ling Shao
- Book Info: Artificial Intelligence Strategies for Analyzing COVID-19 Pneumonia Lung Imaging (Volume 1), Ayman El-Baz, Jasjit S Suri, University of Louisville, Louisville, KY, USA.
- Publisher: IOP Publishing (Access Link)
Patent Application (in Chinese)
- Pre-Training Image-Text Model Processing Method and Image-Text Retrieval System
- 申请日： 2022-03-30
- 申请号： 202210327383.8
- 中文名： 预训练图像文本模型处理方法和图文检索系统
- Camouflage Object Detection Method and System based on Grouping Gradient Learning Strategy
- 申请日： 2022-02-14
- 申请号： 202210134042.9
- 中文名： 一种基于分组梯度学习策略的伪装物体检测方法及系统
- Video Target Segmentation Method and System Based on Full-Duplex Strategy
- 申请日： 2021-07-30
- 申请号： 202110870786.2
- 中文名： 一种基于全双工策略的视频目标分割方法及系统
- Video Saliency Target Detection Method Based on Implicit Guidance and Explicit Teaching Strategy (Granted)
- 申请日： 2021-05-12
- 申请号： 202110516620.0
- 中文名： 一种基于隐式引导与显式教导策略的视频显著性目标检测方法
- Grouping Reverse Attention-Based Camouflage Object Detection Method and System (Granted)
- 申请日： 2021-02-08
- 申请号： 202110180500.8
- 中文名： 基于分组反向注意力的伪装物体检测方法及系统
- Face Anti-Counterfeiting Method Based on Face Depth Information and Edge Image Fusion (Granted)
- 申请日： 2019-06-18
- 申请号： 201910525961.7
- 中文名： 一种基于人脸深度信息和边缘图像融合的人脸防伪方法