Publications

Publications

2023 Papers

  1. Hao Li, Jinfa Huang, Peng Jin, Guoli Song, Qi Wu and Jie Chen. "Weakly-Supervised 3D Spatial Reasoning for Text-based Visual Question Answering." IEEE Transactions on Image Processing, 2023.
  2. Pengchong Qiao, Zhidan Wei, Yu Wang, Zhennan Wang, Guoli Song, Fan Xu, Xiangyang Ji, Chang Liu, Jie Chen. Fuzzy Positive Learning for Semi-supervised Semantic Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. [Paper]
  3. Zesen Cheng, Pengchong Qiao, Kehan Li, Siheng Li, Pengxu Wei, Xiangyang Ji, Li Yuan, Chang Liu, Jie Chen. Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. [Paper]
  4. Peng Jin, JinFa Huang, Pengfei Xiong, Shangxuan Tian, Chang Liu, Xiangyang Ji, Li Yuan, Jie Chen. Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. [Paper]
  5. Kehan Li, Zhennan Wang, Zesen Cheng, Runyi Yu, Yian Zhao, Guoli Song, Chang Liu, Li Yuan, Jie Chen. ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. [Paper]
  6. Yu Wang, Pengchong Qiao, Guoli Song, Chang Liu, Xiawu Zheng, Jie Chen. Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning.[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. [Paper]
  7. Haoliang Zhao, Huizhou Zhou, Yongjun Zhang, Jie Chen, Yitong Yang, Yong Zhao. High-frequency Stereo Matching Network.[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. CVPR 2023. 
  8. Yan Y, Xiang G, Xie X, et al. Efficient Algorithm and Hardware Architecture for Rate Estimation in Mode Decision of AVS3[C]//2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2022: 1-6.
  9. Jucai Zhai, Pengcheng Zeng, Chihao Ma, Yong Zhao, Jie Chen，Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild，Association for the Advancement of Artificial Intelligence，AAAI, 2023.
  10. Bin Fu , Hongliang He, Pengxu Wei , Jie Chen, Learning Task-Aligned Mask Query For Instance Segmentation, ICASSP 2023. [Paper]
  11. Jifan Zhang, Zhe Wu, Xinfeng Zhang, Guoli Song, Yaowei Wang, Jie Chen, Recurrent Fine-Grained Self-Attention Network For Video Crowd Counting ICASSP 2023. [Paper]

2022 Papers

Locality Guidance for Improving Vision Transformers on Tiny Datasets (ECCV 2022)

This paper proposes the locality guidance for improving the performance of VTs on tiny datasets.
See here for Paper and Code.

Joint Learning of Object Graph And Relation Graph For Visual Question Answering (ICME 2022)

This paper introduces
a novel Dual Message-passing enhanced Graph Neural Network. 
See here for Paper and Code.

Training-free Transformer Architecture Search (CVPR 2022)

This paper, for the first time,  investigates how to conduct TAS in a training-free manner and devise an effective trainingfree TAS scheme.
See here for Paper and Code.

  1. Wang Z, Li K, Yu R, et al. Difference in Euclidean Norm Can Cause Semantic Divergence in Batch Normalization[J]. arXiv preprint arXiv:2207.02625, 2022.
  2. Ren Q, Chen J. Dual Complementary Prototype Learning for Few-Shot Segmentation[C]//Computer Sciences & Mathematics Forum. MDPI, 2022, 3(1): 8.
  3. Zhang W, Wu Z, Zhang X, et al. Robust and Hierarchical Spatial Relation Analysis for Traffic Forecasting[J]. IEEE Transactions on Intelligent Transportation Systems, 2022.
  4. Wang L, Ning M, Lu D, et al. An Inclusive Task-Aware Framework for Radiology Report Generation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2022: 568-577.
  5. Zhang C, Cheng Y, Wei P, et al. CENet: Consolidation-and-Exploration Network for Continuous Domain Adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 3426-3432.
  6. Jin P, Huang J, Liu F, et al. Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations[J]. arXiv preprint arXiv:2211.11427, 2022.
  7. Li K, Yu R, Wang Z, et al. Locality guidance for improving vision transformers on tiny datasets[C]//European Conference on Computer Vision. Springer, Cham, 2022: 110-127.
  8. Wang L, Ning M, Lu D, et al. An Inclusive Task-Aware Framework for Radiology Report Generation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2022: 568-577.
  9. Yan Y, Xiang G, Xie X, et al. Efficient Algorithm and Hardware Architecture for Rate Estimation in Mode Decision of AVS3[C]//2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2022: 1-6.
  10. Li H, Li X, Karimi B, et al. Joint learning of object graph and relation graph for visual question answering[J]. arXiv preprint arXiv:2205.04188, 2022.
  11. Zhou Q, Sheng K, Zheng X, et al. Training-free Transformer Architecture Search[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 10894-10903.
  12. Cheng M, Sun Y, Wang L, et al. ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 5184-5193.
  13. Zhang Y, Lin M, Lin C W, et al. Carrying Out CNN Channel Pruning in a White Box[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022.

戈登贝尔（Gordon Bell）新冠特别奖

Video Description

领先于病毒的进化——通过人工智能模拟预测未来高风险新冠病毒变异株

  11月17日，美国计算机协会（ACM）公布2022年度戈登贝尔新冠特别奖评选结果。北京大学深圳研究生院信息工程学院与鹏城实验室、山东大学组成的联合研究团队在自行研发的鹏程·神农生物信息研究平台上完成的“领先于病毒的进化——通过人工智能模拟预测未来高风险新冠病毒变异株”研究项目成功入围2022年度“戈登贝尔新冠特别奖”，也是本次入围的唯一来自中国团队的项目。
  北大主要参与者是来自信息工程学院的田永鸿教授、陈杰副教授和博士研究生聂志伟和来自数学科学学院的杨超教授。

点击此处查看相关论文和PPT。

2021 Papers (top10 cited)

  1. Li C, Xie C, Zhang B, et al. Memory attention networks for skeleton-based action recognition[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021.
  2. Zhang C, Cao M, Yang D, et al. Cola: Weakly-supervised temporal action localization with snippet contrastive learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 16010-16019.
  3. Wu Q, Dai P, Chen J, et al. Discover cross-modality nuances for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 4330-4339.
  4. Wang S, Li C, Wang R, et al. Annotation-efficient deep learning for automatic medical image segmentation[J]. Nature communications, 2021, 12(1): 1-13.
  5. He H, Zhang C, Chen J, et al. A hybrid-attention nested UNet for nuclear segmentation in histopathological images[J]. Frontiers in Molecular Biosciences, 2021, 8: 614174.
  6. Zheng X, Ji R, Chen Y, et al. MIGO-NAS: Towards fast and generalizable neural architecture search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(9): 2936-2952.
  7. Wu J, Xu H, Zhang S, et al. Joint segmentation and detection of COVID-19 via a sequential region generation network[J]. Pattern recognition, 2021, 118: 108006.
  8. He H, Huang Z, Ding Y, et al. CDNet: Centripetal Direction Network for Nuclear Instance Segmentation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 4026-4035.
  9. Cheng M, Kong Z, Song G, et al. Learnable Oriented-Derivative Network for Polyp Segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2021: 720-730.
  10. Ding Y, Han Z, Zhou Y, et al. Dynamic perception framework for fine-grained recognition[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(3): 1353-1365.
  11. ...
    See here for more information.

Patents

  1. 高志强，陈杰，乔鹏冲，田永鸿. 一种胸部CT图像病灶分割模型的训练方法及系统[P].申请号202110705914.8，2021年6月24日
  2. 黄锦发，陈杰，高志强，田永鸿 . 一种基于Transformer的CT报告生成方法[P].申请号202110795676.4，2021年7月14日
  3. 陈杰、田永鸿、高文、王中岐、王林. 一种基于任务感知的报告自动生成方法及装置[P].申请号202211156398.9，2022年9月22日 初审通过
  4. 陈杰、田永鸿、高文、王中岐、王林. 利用自然语言模型自动生成结构化报告的方法及相关设备[P].申请号202211078506.5，2022年9月5日 初审通过
  5. 田永鸿、杨文明、王天誉、陈杰. 一种药物-靶点交互作用预测方法、系统及终端设备[P].申请号202210632799.0，2022年6月7日
  6. 王珊珊，黄纬键，郑海荣，陈杰，周晖晖，田永鸿. 基于人机交互的模型训练方法、装置、终端及存储介质[P].申请号202211222416.9，2022年10月8日
  7. 王珊珊、吴若有、黄纬键、陈杰. 一种基于对抗样本的医学图像重建方法及相关装置[P]. 申请号202211425844.1，2022年11月16日
  8. 陈杰、田永鸿、高文、黄显淞、孔子尚.一种基于多任务学习的图像清洁度评估方法及相关装置[P].申请号202211475103.4，2022年11月23日
  9. 陈杰、田永鸿、高文、黄显淞、孔子尚.一种基于可学习方向导数的病灶边缘检测方法及相关装置[P].申请号202211475402.8，2022年11月23日
  10. 陈杰、田永鸿、高文、王中岐、王书博.一种基于区域互补聚合的人群计数方法及相关装置[P].申请号202211384415.4，2022年11月7日
  11. 高文，陈杰，田永鸿，施振辉、夏源. 基于图路径搜索和语义索引的医疗问答系统[P].申请号202211709241.4，2022年12月29日
  12. 高文，陈杰，田永鸿，王兆玮.一种基于数据增强的肝脏CT肿瘤分割方法[P].申请号202211623471.9，2022年12月16日
  13. 陈杰、田永鸿、高文、王中岐、任前. 基于注意力机制的小样本分割方法、装置、终端及介质[P].申请号202211569888.1，2022年12月8日
  14. 陈杰，田永鸿，高文，黄显淞，黄钟毅.一种基于中心点的细胞核分割方法[P].申请号202211705880.3，2022年12月29日
  15. 高文，陈杰，田永鸿，徐凡，耿睿哲.一种多尺度空间特征增强方法及装置[P].申请号202211569881.X，2022年12月8日
  16. 田永鸿，陈杰，高文，徐凡，张弛.一种基于领域对关联的迁移学习方法及装置[P].申请号202211581443.5，2022年12月9日
  17. 田永鸿，高文，陈杰，徐凡，耿睿哲.一种基于上下文特征融合的细胞核分割方法及相关设备[P].申请号202211580495.0，2022年12月9日
  18. 田永鸿，陈杰，高文，徐凡，张弛.基于自适应参数隔离的迁移学习方法、装置、终端及介质[P].申请号202211579420.0，2022年12月8日
  19. 陈杰、田永鸿、高文、黄显淞、徐凡、王中岐. 药物与蛋白质设计服务管理系统（软件著作权）.2022R11L1872673
  20. 李代禧、陈杰、田永鸿、高文. 基于靶位结构和结合自由能的蛋白药物筛选软件（软件著作权）.2022R11L1988060
  21. 李代禧、陈杰、田永鸿、高文. 基于Gromacs的分子模拟软件（软件著作权）.2022R11L1995041

‌

WYSIWYG HTML Editor