金城

教授，博士生导师，复旦大学计算机科学技术学院
首页 | 团队 | 科研 | 教学 | English

 

链接

Email

Github

联系方式

上海市杨浦区淞沪路2005号复旦大学江湾校区二号交叉学科楼D5013

近期研究主题

中国书法与绘画内容生成

任务：可控地生成中国书法与绘画内容，在文化旅游、艺术设计、博物展陈等领域有重要价值，这也是我们书画数字化生成应用服务文化和旅游部技术创新中心的核心工作

Painting and Cligraphy Generation

 

三维点云生成

任务：可控地生成复杂点云结构，在数据增强、工业设计、场景生成等领域有重要价值

3D Point Cloud Generation

 

三维点云补全

任务：给定一个残缺的点云（一般因遮挡、采集缺漏造成），补全其完整结构，在自动驾驶、场景识别等领域有重要价值

3D Point Cloud Completion

 

基于骨架的行为识别

任务：基于骨架信息无监督地识别人体行为，在隐私保护环境下的监控识别等领域有重要价值

Skeleton Action Recognition

 

视觉定位

任务：给定照片识别照片所在的位置，在自动驾驶、机器人、室内导航等领域有重要价值

Visual Place Recognition

 

表面缺陷检测

任务：给定产品表面图像识别出其中的缺陷，在工业生产检测等领域有重要价值

Anomaly Detection

 

电气指纹识别

任务：根据采集到的电气数据判断每一台电气设备的启动、运行和停止情况，在智能电网、双碳战略等领域有重要价值

Electric Footprint

 

部分论文列表

  • Zhao Zhou, Yiqun Wang, Weizhong Zhang, Yingbin Zheng, Xiangcheng Du, Cheng Jin, Achieving Ensemble-Like Performance in A Single Model: A Feature Diversification Framework for Image-Text Matching, AAAI Conference on Artificial Intelligence (AAAI) 2025

  • Zhao Zhou, Xiangcheng Du, Yingbin Zheng, Xingjiao Wu, Cheng Jin, An Exemplar-based Framework for Chinese Text Recognition, AAAI Conference on Artificial Intelligence (AAAI) 2025

  • Zhao Zhou, Weizhong Zhang, Xiangcheng Du, Yingbin Zheng, Cheng Jin, Expanding the Scope of Negatives: Boosting Image-Text Matching with Negatives Distribution Guided Learning, AAAI Conference on Artificial Intelligence (AAAI) 2025

  • Xichen Ye, Yifan Wu, Weizhong Zhang, Xiaoqiang Li, Yifan Chen, Cheng Jin, Optimized Gradient Clipping for Noisy Label Learning, AAAI Conference on Artificial Intelligence (AAAI) 2025

  • Yan Zhuang, Yanlu Cai, Weizhong Zhang, Cheng Jin, Future Motion Dynamic Modeling via Hybrid Supervision for Multi-Person Motion Prediction Uncertainty Reduction, ACM Multimedia 2024

  • Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin, PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering, ACM Multimedia 2024

  • Xiangcheng Du, Zhao Zhou, Xingjiao Wu, Yanlong Wang, Zhuoyao Wang, Yingbin Zheng, Cheng Jin, MultiColor: Image Colorization by Learning from Multiple Color Spaces, ACM Multimedia 2024

  • Zhibo Zhang, Ximing Yang, Weizhong Zhang, Cheng Jin, ELiTe: Efficient Image-to-LiDAR Knowledge Transfer for Semantic Segmentation, The IEEE International Conference on Multimedia & Expo (ICME) 2024 (code, oral)

  • Yiqun Wang, Zhao Zhou, Xiangcheng Du, Xingjiao Wu, Yingbin Zheng, Cheng Jin, Fine-Grained Scene Image Classification with Modality-Agnostic Adapter, The IEEE International Conference on Multimedia & Expo (ICME) 2024 (code, oral)

  • Lintao Zhang, Xiangcheng Du, Sijie Liu, Yiqun Wang, Zhao Zhou, Yingbin Zheng, Cheng Jin, Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling, The IEEE International Conference on Multimedia & Expo (ICME) 2024 (code, oral)

  • Yanlu Cai, Weizhong Zhang, Yuan Wu, Cheng Jin, PoseIRM: Enhance 3D Human Pose Estimation on Unseen Camera Settings via Invariant Risk Minimization, The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024

  • Yibin Wang, Weizhong Zhang, Jianwei Zheng, Cheng Jin, High Fidelity Person-centric Subject-to-Image Synthesis, The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024

  • XingJiao Wu, Luwei Xiao, Xiangcheng Du, Yingbin Zheng, Xin Li, Tianlong Ma, Cheng Jin, Liang He, Cross-Domain Document Layout Analysis via Document Style Guide, Expert Systems with Applications (ESWA), 2024 (paper)

  • LeoWu TomyEnrique, Xiangcheng Du, Kangliang Liu, Han Yuan, Zhao Zhou, Cheng Jin, Efficient Scene Text Image Super-Resolution With Semantic Guidance, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024 (code, oral)

  • Kelvin Ting Zuo Han, Shengxuming Zhang, Gerard Marcos Freixas, Zunlei Feng, Cheng Jin, Target Optimization Direction Guided Transfer Learning For Image, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2024 (code)

  • Kaiyi Zhang, Yang Chen, Ximing Yang, Weizhong Zhang, Cheng Jin, Point Cloud Part Editing: Segmentation, Generation, Assembly, and Selection, AAAI Conference on Artificial Intelligence (AAAI) 2024 (paper, code)

  • Yanlu Cai, Weizhong Zhang, Yuan Wu, Cheng Jin, FusionFormer: A Concise Unified Feature Fusion Transformer for 3D Pose Estimation, AAAI Conference on Artificial Intelligence (AAAI) 2024 (paper)

  • Tianlong Ma, Xiangcheng Du, Xingjiao Wu, Zhao Zhou, Yingbin Zheng, Cheng Jin, Reading Scene Text with Aggregated Temporal Convolutional Encoder, ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) 2023 (paper)

  • Cong Zou, Rui Wang, Cheng Jin, Sanyi Zhang, Xin Wang, S^2CL-Leaf Net: Recognizing Leaf Images Like Human Botanists, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 2023 (paper, code)

  • Jian Ma, Xiaoyin Zhang, Cheng Jin, Ping An, Guoming Xu, Light Field Image Quality Assessment Using Natural Scene Statistics and Texture Degradation, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT) 2023 (paper)

  • Xiangcheng Du, Zhao Zhou, Yingbin Zheng, Xingjiao Wu, Tianlong Ma, Cheng Jin, Progressive Scene Text Erasing with Self-Supervision, Computer Vision and Image Understanding (CVIU) 2023 (paper)

  • Tianlong Ma, Xingjiao Wu, Xiangcheng Du, Yanlong Wang, Cheng Jin, Image Layer Modeling for Complex Document Layout Generation, The IEEE International Conference on Multimedia & Expo (ICME) 2023 (paper)

  • Hao Ren, Wu Ran, Xingson Liu, Haoran Ren, Hong Lu, Rui Zhang, Cheng Jin, Weakly-supervised Temporal Action Localization with Adaptive Clustering and Refining Network, The IEEE International Conference on Multimedia & Expo (ICME) 2023 (paper, code)

  • Kangliang Liu, Xiangcheng Du, Sijie Liu, Yingbin Zheng, Xingjiao Wu, Cheng Jin, DDT: Dual-branch Deformable Transformer for Image Denoising, The IEEE International Conference on Multimedia & Expo (ICME) 2023 (paper, code)

  • Weilin Wan, Weizhong Zhang, Cheng Jin, Pose-motion Video Anomaly Detection Via Memory-augmented Reconstruction And Conditional Variational Prediction, The IEEE International Conference on Multimedia & Expo (ICME) 2023 (paper)

  • Haoran Ren, Hao Ren, Hong Lu, Cheng Jin, Weakly-supervised Temporal Action Localization with Regional Similarity Consistency, International Conference on Multimedia Modeling (MMM) 2023 (paper, code)

  • Xiangcheng Du, Zhao Zhou, Yingbin Zheng, Tianlong Ma, Xingjiao Wu, Cheng Jin, Modeling Stroke Mask for End-to-End Text Erasing, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 (paper, code)

  • Hao Zhang, Xin Chen, Heming Jing, Yingbin Zheng, Yuan Wu, Cheng Jin, ETR: An Efficient Transformer for Re-ranking in Visual Place Recognition, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2023 (paper, code)

  • Hao Ren, Haoran Ren, Wu Ran, Hong Lu, and Cheng Jin, Weakly-supervised Temporal Action Localization with Multi-head Cross-modal Attention, The Pacific Rim International Conferences on Artificial Intelligence (PRICAI) 2022 (paper, code)

  • Sibo Luo, Shangshang Wang, Yuan Wu, Cheng Jin, Memory Enhanced Spatial-Temporal Graph Convolutional Autoencoder for Human-related Video Anomaly Detection, Chinese Conference on Pattern Recognition and Computer Vision (PRCV) 2022 (paper, code)

  • Yuan Wu, Yanlu Cai, Rui Feng, Cheng Jin, ST2PE: Spatial and Temporal Transformer for Pose Estimation, The International Conference on Artificial Neural Networks (ICANN) 2022 (paper)

  • Rui Cao, Kaiyi Zhang, Yang Chen, Ximing Yang, Cheng Jin, Point Cloud Completion via Multi-Scale Edge Convolution and Attention, ACM Multimedia 2022 (paper)

  • Haoyue Qiu, Mengmeng Duan, Yuan Wu, Cheng Jin, GLTA-GCN: Global-Local Temporal Attention Graph Convolutional Network for Unsupervised Skeleton-based Action Recognition, The IEEE International Conference on Multimedia & Expo (ICME) 2022 (paper, code)

  • Jingwen Ye, Yining Mao, Jie Song, Xinchao Wang, Cheng Jin, Mingli Song, Safe Distillation Box, AAAI Conference on Artificial Intelligence (AAAI) 2022 (paper)

  • Kaiyi Zhang, Ximing Yang, Yuan Wu, Cheng Jin, Attention-based Transformation from Latent Features to Point Clouds, AAAI Conference on Artificial Intelligence (AAAI) 2022 (paper, code)

  • Ximing Yang, Yuan Wu, Kaiyi Zhang, Cheng Jin, CPCGAN: A Controllable 3D Point Cloud Generative Adversarial Network with Semantic Label Generating, AAAI Conference on Artificial Intelligence (AAAI) 2021 (paper, code, poster, demo) 

  • Zunlei Feng, Yongming He, Xinchao Wang, Xin Gao, Jie Lei, Cheng Jin, Mingli Song, One-sample Guided Object Representation Disassembling, Conference on Neural Information Processing Systems (NeurIPS) 2020 (paper)

  • Yanlu Cai, Yuqing Li, Runyu Peng, Yipei Xu, Chenzhe Jin, Cheng Jin, Look into Multi-Person: A New Benchmark for Pose Estimation and Human Parsing, IEEE International Conference on Big Data 2020 (paper)

  • Kuncheng Fang, Lian Zhou, Cheng Jin, Yuejie Zhang, Kangnian Weng, Tao Zhang, Weiguo Fan, Fully Convolutional Video Captioning with Coarse-to-Fine and Inherited Attention, AAAI Conference on Artificial Intelligence (AAAI) 2019 (paper)

  • Yuanfang Guo, Xiaochun Cao, Rui Wang, Cheng Jin, A New Data Embedding Method with a New Data Embedding Domain for JPEG Images, 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM), 1-5, 2018 (paper)

  • Fei Huang, Cheng Jin, Yuejie Zhang, Kangnian Weng, Tao Zhang, Weiguo Fan, Sketch-based image retrieval with deep visual semantic descriptor, Pattern Recognition, Volume 76, April 2018, Pages 537-548 (paper)

  • Yong Cheng, Fei Huang, Lian Zhou, Cheng Jin, Yuejie Zhang and Tao Zhang, A Hierarchical Multimodal Attention-based Neural Network for Image Captioning, ACM SIGIR 2017 (short paper) (paper)

  • Fei Huang, Yong Cheng, Cheng Jin, Yuejie Zhang and Tao Zhang, Deep Multimodal Embedding Model for Fine-grained Sketch-based Image Retrieval, ACM SIGIR 2017 (short paper) (paper)

  • Fei Huang, Cheng Jin, Yuejie Zhang and Tao Zhang, Towards Sketch-based Image Retrieval with Deep Cross-modal Correlation, The IEEE International Conference on Multimedia & Expo (ICME) 2017 (paper)

  • Gongze Cao, Yezhou Yang, Jie Lei, Cheng Jin, Yang Liu, Mingli Song, TripletGAN: Training Generative Model with Triplet Loss, arXiv preprint arXiv:1711.05084, 2017 (paper)

  • Cheng Jin, Chenjie Li, Zheming Wang, Yuejie Zhang, Tao Zhang, Sketch-based Image Retrieval with a Novel BoVW Representation, International Conference on Multimedia Modeling (MMM) 2016 (paper)

  • Fei Huang, Yong Cheng, Cheng Jin, Yuejie Zhang and Tao Zhang, Enhancing Sketch-Based Image Retrieval via Deep Discriminative Representation, European Conference on Artificial Intelligence (ECAI) 2016 (paper)

  • Yong Cheng, Fei Huang, Cheng Jin, Yuejie Zhang and Tao Zhang, A Novel Cross-Modal Topic Correlation Model for Cross-Media Retrieval, European Conference on Artificial Intelligence (ECAI) 2016 (paper)

  • Zhixin Liu, Cheng Jin, Yuejie Zhang, Tao Zhang, Automatic Naming of Speakers in Video via Name-Face Mapping, China National Conference on Computational Linguistics (CCL) 2016: 424-436 (paper)

  • Xingmeng Zhang, Cheng Jin, Yuejie Zhang, Tao Zhang, Image Tag Recommendation via Deep Cross-Modal Correlation Mining, China National Conference on Computational Linguistics (CCL) 2016: 437-449 (paper)

  • YongQing Liang, Cheng Jin, Yuejie Zhang, Salient Region Detection with Convex Hull Overlap, CoRR abs/1612.03284, 2016 (paper)

  • Yong Cheng, Zhengxiang Cai, Rui Feng, Cheng Jin, Yuejie Zhang, Tao Zhang, Cross-Modal Image-Tag Relevance Learning for Social Images, ACM MultiMedia 2015 (short paper) (paper)

  • Cheng Jin, Wenhui Mao, Ruiqi Zhang, Yuejie Zhang, Xiangyang Xue, Cross-Modal Image Clustering via Canonical Correlation Analysis, AAAI Conference on Artificial Intelligence (AAAI) 2015 (paper)

  • Cheng Jin, Zheming Wang, Tianhao Zhang, Qinen Zhu, Yuejie Zhang, A Novel Visual-Region-Descriptor-based Approach to Sketch-based Image Retrieval, ACM International Conference on Multimedia Retrieval (ICMR) 2015 (paper)

  • Yong Cheng, Zhixin Liu, Yun Zhao, Cheng Jin, Yuejie Zhang, Tao Zhang, People News Search via Name-Face Association Analysis, ACM International Conference on Multimedia Retrieval (ICMR) 2015 (short paper) (paper)

  • Shuai Ren, Cheng Jin, Chang Sun, Yuejie Zhang, Sketch-Based Image Retrieval via Adaptive Weighting. ACM International Conference on Multimedia Retrieval (ICMR) 2014 (paper)

  • Yuejie Zhang, Wei Wu, Yang Li, Cheng Jin, Xiangyang Xue, Jianping Fan, Automatic Name-Face Alignment to Enable Cross-Media News Retrieval. International Joint Conference on Artificial Intelligence (IJCAI) 2013 (paper)

  • Ruijiang Li, Bin Li, Ke Zhang, Cheng Jin, Xiangyang Xue, Groupwise Constrained Reconstruction for Subspace Clustering, International Conference on Machine Learning (ICML) 2012 (paper)

  • Yao Lu, Wei Zhang, Cheng Jin, Xiangyang Xue, Learning Attention Map from Images, The IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR) 2012 (paper)

  • Xisheng He, Zhe Wang, Cheng Jin, Yingbin Zheng, Xiangyang Xue, A simplified multi-class support vector machine with reduced dual optimization, Pattern Recognition Letters 2012 (paper)

  • Cheng Jin, Chunlei Yang, Integrating Hierarchical Feature Selection and Classifier Training for Multi-Label Image Annotation, ACM SIGIR 2011 (paper)

  • Ruijiang Li, Bin Li, Cheng Jin, Xiangyang Xue, Xingquan Zhu, Tracking User- Preference Varying Speed in Collaborative Filtering, AAAI Conference on Artificial Intelligence (AAAI) 2011 (paper)

  • Yuejie Zhang, Lei Cen, Cheng Jin, Xiangyang Xue and Jianping Fan, Learning Inter-Related Statistical Query Translation Models for English-Chinese Bi-Directional CLIR, International Joint Conference on Artificial Intelligence (IJCAI) 2011 (paper)

  • Yuejie Zhang, Lei Cen, Wei Wu, Cheng Jin and Xiangyang Xue, Fusion of Multiple Features and Supervised Learning for Chinese OOV Term Detection and POS Guessing, International Joint Conference on Artificial Intelligence (IJCAI) 2011 (paper)

  • Yiyang Gu, Cheng Jin, Xiangyang Xue, Quick matting: A matting method based on pixel spread and propagation, IEEE International Conference on Image Processing (ICIP) 2010 (paper)

  • Yuejie Zhang, Lei Cen, Cheng Jin, Xiangyang Xue and Ning Zhou, Bilingual Query Translation and Expansion for Supporting More Effective Cross-Language Image Retrieval, ACM Multimedia 2010 (paper)

  • Renzhong Wei, Hong Lu, Yingbin Zheng, Lei Cen, Cheng Jin, Xiangyang Xue, Weiguo Wu, How Context Helps: A Discriminative Codeword Selection Method for Object Detection, IEEE International Conference on Image Processing (ICIP) 2010 (paper)

  • Jian-Feng Chen, Hong Lu, Renzhong Wei, Cheng Jin, Xiangyang Xue, An effective method for video genre classification, ACM International Conference on Image and Video Retrieval (CIVR) 2010 (paper)