程远
研究员、博士生导师
邮箱:cheng_yuan@fudan.edu.cn

  教育经历

复旦大学计算机本科,新加坡国立大学博士/博士后

  工作经历

2016年-2022年,蚂蚁集团人工智能部工作;

2022年入职复旦大学人工智能创新与产业研究院

  研究方向

(1)AI for Science;(2)多模态细粒度认知;(3)计算机视觉

  主要成果

先后主持和参与2项国家和省部级科研项目;发表国内外顶级论文20余篇;授权发明专利37项。

代表性成果简介:

1. 智能垃圾分类技术,识别精度领先,曾获得第74届联合国大会绿色可持续发展方案“绿眼睛”奖。

2. 全球首个宠物身份识别技术,在三家金融企业大规模应用,入选Gartner、中国保险报等机构年度优秀智能应用案例。

3. 端云结合的多模态细粒度度识别技术,在五家金融企业大规模应用,获得中国图象图形学学会技术发明二等奖。

4. 区块链版权保护技术,识别精度、效率大、成本幅度领先,在中国版权保护中心、蚂蚁集团、字节跳动、视觉中国大规模应用。

  研究方向

依托计算机科学技术学院招生,招生专业为计算机科学与技术。

  发表论文

1. Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng*, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi.’Dual-Modal Attention-Enhanced Text-Video Retrieval with Triplet Partial Margin Contrastive Learning’. In Proc. of ACM MultiMedia, 2023.

2. Junping Zhang, Jian Pu, Jie Chen, Haolin Fu, Yongzhi Tao, Shihmin Wang, Qi Chen, Yun- feng Xiao, Siming Chen, Yuan Cheng, Hongming Shan, Dewang Chen, Fei-Yue Wang.’DSiV: Data Science for Intelligent Vehicles’. In IEEE Transactions on Intelligent Vehicles, 2023.

3. Xingning Dong, Qingpei Guo, Tian Gan, Qing Wang, Jianlong Wu, Xiangyuan Ren, Yuan Cheng, Wei Chu, ’SNP-S3: Shared Network Pre-training and Significant Semantic Strength- ening for Various Video-Text Tasks’. In IEEE Transactions on Circuits and Systems for Video Technology, 2023.

4. Tan Pan, Furong Xu, Xudong Yang, Sifeng He, Chen Jiang, Qingpei Guo, Feng Qian, Xiaobo Zhang, Yuan Cheng, Lei Yang, Wei Chu. ’Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval’. In Proc. of CVPR, 2023.

5. Wen Li, Cheng Zou, Meng Wang, Furong Xu, Jianan Zhao, Ruobing Zheng, Yuan Cheng*, Wei Chu. ’DC-Former: Diverse and Compact Transformer for Person Re-Identification’. In Proc. of AAAI, 2023.

6. Sifeng He, Xudong Yang, Chen Jiang, Gang Liang, Wei Zhang, Tan Pan, Qing Wang, Furong Xu, Chunguang Li, Jinxiong Liu, Xu Hui, Kaiming Huang, Yuan Cheng, Feng Qian, Xiaobo Zhang, Lei Yang. ’A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection’. In Proc. of CVPR, 2022.

7. Xingning Dong, Tian Gan, Xuemeng Song, Jianlong Wu, Yuan Cheng*, Liqiang Nie. ’Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation’. In Proc. of CVPR, Jun 2022.

8. Shaokun Wang, Tian Gan, Yuan Liu, Jianlong Wu, Yuan Cheng, Liqiang Nie. ’Micro- influencer Recommendation by Multi-perspective Account Representation Learning’, Trans. on MM, Jun 2022.

9. Liyu Meng, Yuchen Liu, Xiaolong Liu, Zhaopei Huang, Yuan Cheng, Meng Wang, Chuanhe Liu, Qin Jin. ’Multi-modal Emotion Estimation for in-the-wild Videos’, In Proc. of CVPR ABAW Workshop , Jun 2022.

10. Fang Yu, Kun Huang, Meng Wang, Yuan Cheng*, Wei Chu, Cui Li. ’Width & Depth Pruning for Vision Transformers’, In Proc. of AAAI, Feb, 2022.

11. Chen Jiang, Kaiming Huang, Sifeng He, Xudong Yang, Wei Zhang, Xiaobo Zhang, Yuan Cheng, Lei Yang, Qing Wang, Furong Xu, Wei Chu. ‘Learning Segment Similarity and Alignment in Large-Scale Content Based Video Retrieval’, In Proc. of ACM MultiMedia, Oct 2021.

12. Licai Sun, Mingyu Xu, Zheng Lian, Bin Liu, Jianhua Tao, Meng Wang, Yuan Cheng. ’Multimodal Emotion Recognition and Sentiment Analysis viaAttention Enhanced Recur- rent Model’, In Proc. of ACM MultiMedia MuSe Workshop, Oct 2022.

13. Zhiming Wang, Furong Xu, Kaisheng Yao, Yuan Cheng, Tao Xiong, Huijia Zhu. ‘AntVoice: Neural Speaker Embedding System for FFSVC 2020’, In Proc. of INTERSPEECH, Aug 2021.

14. Furong Xu, Meng Wang, Wei Zhang, Yuan Cheng, Wei Chu. ‘Discrimination-Aware Mechanism for Fine-grained Representation Learning’, In Proc. of CVPR, Jun 2021.

15. Furong Xu, Wei Zhang, Yuan Cheng, Wei Chu. ‘Metric Learning with Equidistant and Equidistributed Triplet-based Loss for Product Image Search’, In Proc. of WWW, Apr 2020.

16. Wei Zhang, Yuan Cheng, Xin Guo, Qingpei Guo, Jian Wang, Qing Wang, Chen Jiang, Meng Wang, Furong Xu, Wei Chu. ‘Automatic Car Damage Assessment System: Read- ing and Understanding Videos as Professional Insurance Inspectors’, AAAI Demonstration Track, Feb, 2020.