李睿凡，博士，北京邮电大学人工智能学院副教授、博士生导师；华中科技大学获学士、硕士学位，北京邮电大学获工学博士学位，美国南加州大学 (USC) 访问学者；主要研究兴趣是机器智能和深度学习基础理论与方法及其在多模态认知计算和自然语言处理等领域的应用；在 CVPR、ACL、ACM MM、AAAI、IJCAI、EMNLP、ECAI、COLING、ICME、ICASSP 等国际会议及 IEEE TMM、IEEE TNNLS、IEEE TCSVT、ACM ToMM、NEUNET 等国际期刊发表学术论文，含ESI高被引论文1篇，谷歌学术总引用4000余次；已授权国家发明专利20项；ACM MM'14会议论文 (Corr-AE跨模态检索方法) 获最佳论文提名奖，ACL'21会议论文 (DualGCN情感分析方法) 入选 Paper Digest 最具影响力论文榜单，获 Aminer'23 AI 2000多媒体领域最具影响力学者提名奖。个人主页；答所问(AQA)；欢迎投稿：Electronics (SCI) DDL 12.15 (Data Mining Applied in Natural Language Processing)，Future Internet (ESCI) DDL 3.31.2025 (Information Communication Technologies and Social Media)。

l部分论文 (* = 通信作者)   

[1] Guangwei Zhang, Yongping Xiong, and Ruifan Li*,  A Noisy Context Optimization Approach for Chinese Spelling Correction, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Macau, China, 2024-12. [Web]   

[2] Pengyue Lin, Ruifan Li*, Yuzhe Ji, Zhihan Yu, Fangxiang Feng, Zhanyu Ma, and Xiaojie Wang, Triple Alignment Strategies for Zero-shot Phrase Grounding under Weak Supervision, ACM International Conference on Multimedia (ACM MM), pp. 4312-4321, Melbourne, Australia, 2024-10. [Web]  

[3] Pengfei Zhou, Fangxiang Feng, Guang Liu, Ruifan Li, and Xiaojie Wang, DiffHarmony++: Enhancing Image Harmonization with Harmony-VAE and Inverse Harmonization Model, ACM International Conference on Multimedia (ACM MM), pp. 10592-10601, Melbourne, Australia, 2024-10. [Web] 

[4] Mingcong Lu, Ruifan Li*, Fangxiang Feng, Zhanyu Ma and Xiaojie Wang, LGR-NET: Language Guided Reasoning Network for Referring Expression Comprehension, in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Vol. 34, pp. 7771-7784, 2024-08. [Web] 

[5] Yuantao Fan, Xinyu Tu, Ruifan Li*, An Inverse Retrieval Method Via Query Generation for Xiaohongshu’s Search Engine, International Conference on Intelligent Computing (ICIC), pp. 362-373, Tianjin, China, 2024-07. [Web] 

[6] Zhihan Yu and Ruifan Li*, Revisiting Counterfactual Problems in Referring Expression Comprehension, IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13438 - 13448, Seattle, USA., 2024-06. [Web] 

[7] Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, and Eduard H. Hovy, DualGCN: Exploring Syntactic and Semantic Information for Aspect-based Sentiment Analysis, IEEE Transactions on Neural Networks and Learning Systems (TNNLS), pp. 7642-7656, 2024-06. [Web] 

[8] Pengyue Lin, Zhihan Yu, Mingcong Lu, Fangxiang Feng, Ruifan Li*, and Xiaojie Wang, Visual Prompt Tuning for Weakly Supervised Phrase Grounding, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7895-7899, Seoul, Korea, 2024-04.  [Web] 

[9] Ruifan Li*, Zhiyu Wei, Yuantao Fan, Shuqin Ye, and Guangwei Zhang, Enhanced Prompt Learning for Few-shot Text Classification Method, The 12th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC), Foshan, Guangzhou, 2023-11, published in Acta Scientiarum Naturalium Universitatis Pekinensis, (in Chinese), Vol. 60 (1), pp. 1-12, 2024-01. [Web] 

[10] Lihui Zhang and Ruifan Li*, Knowledge Prompting with Contrastive Learning for Unsupervised CommonsenseQA, The International Conference on Neural Information Processing (ICONIP), pp. 27-38, Changsha, China, 2023-11. [Web] 

[11] Shuqin Ye, Zepeng Zhai, and Ruifan Li*, Enhanced Machine Reading Comprehension Method for Aspect Sentiment Quadruplet Extraction, The 26th European Conference on Artificial Intelligence (ECAI), pp. 2874-2881, 2023-10. [Web]

[12] Guang Chen, Fangxiang Feng, Guangwei Zhang, Xiaoxu Li, and Ruifan Li*, A Visually Enhanced Neural Encoder for Synset Induction, Electronics, 12 (16), 3521, 1-21, 2023-08. [Web]

[13] Zepeng Zhai, Hao Chen, Ruifan Li*, and Xiaojie Wang, USSA: A Unified Table Filling Scheme for Structured Sentiment Analysis, The 61th Annual Meeting of the Association for Computational Linguistics (ACL, Main Conference, Long Paper), 2023-06. [Web]

[14] Lihui Zhang and Ruifan Li*, KE-GCL: Knowledge Enhanced Graph Contrastive Learning for Commonsense Question Answering, The 2022 Conference on Empirical Methods in Natural Language Processing, (Findings of ACL, Long Paper), pp. 76-87, 2022-12. [Web]

[15] Zepeng Zhai, Hao Chen, Fangxiang Feng, Ruifan Li*, and Xiaojie Wang, COM-MRC: A COntext-Masked Machine Reading Comprehension Framework for Aspect Sentiment Triplet Extraction, The 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP, Main Conference, Long Paper), pp. 3230–3241, 2022-12. [Web]

[16] Zeyuan Wang, Yifan Du, Guangwei Zhang, Ruifan Li*, Yongping Xiong and Chuang Zhang, Semantics-Guided Knowledge Integration for Domain Adaptation Few-shot Relation Extraction, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 506-513, Chiang Mai, Thailand, 2022-11. [Web]

[17] Zhihan Yu, Mingcong, and Ruifan LI*, Multimodal Co-Attention Mechanism for One-stage Visual Grounding, IEEE International Conference on Cloud Computing and Intelligent Systems (CCIS), Chengdu, China,  pp. 288-292, 2022-11.  [Web]

[18] Ziqin Rao, Fangxiang Feng, Ruifan Li*, and Xiaojie Wang, A Simple Model for Distantly Supervised Relation Extraction, The 29th International Conference on Computational Linguistics (COLING, Main Conference, Short Paper), pp. 2651-2657, 2022.10. [Web]

[19] Yun Liu, Yihui Shi, Fangxiang Feng, Ruifan Li*, Zhanyu Ma, and Xiaojie Wang, Improving Image Paragraph Captioning with Dual Relations, IEEE International Conference on Multimedia and Expo (ICME, Regular Paper), pp. 1-6, 2022-07. [Web]

[20] Guangwei Zhang, Bing Zhao, and Ruifan Li*, Multi-level fusion with deep neural networks for multimodal sentiment classification, Vol. 29, pp. 25-33, Journal of China Universities of Posts and Telecommunications (JCUPT), 2022-06.  [Web]

[21] Mingcong Lu, Yusong Zhang, Qu-An Zheng, Zhenyuan Ma, Liqing Liu, Yongping Xiong, Ruifan Li*，EP-BERTGCN: A Simple but Effective Power Equipment Fault Recognition Method, ACM International Conference on Information Technology and Computer Communications (ITCC), pp. 64-68, 2022-06. [Web]

[22] Fangxiang Feng, Tianrui Niu, Ruifan Li, and Xiaojie Wang, Modality Disentangled Discriminator for Text-to-Image Synthesis, IEEE Transactions on Multimedia (TMM), Vol. 24, pp. 2112-2124, 2022-05. [Web]

[23] Hao Chen, Zepeng Zhai, Fangxiang Feng, Ruifan Li*, and Xiaojie Wang, Enhanced Multi-Channel Graph Convolutional Network for Aspect Sentiment Triplet Extraction，The 60th Annual Meeting of the Association for Computational Linguistics (ACL, Main Conference, Long Paper), pp. 2974-2985, 2022-05. [Web]

[24] Yihui Shi, Yun Liu, Fangxiang Feng, Ruifan Li*, Zhanyu Ma, and Xiaojie Wang, S2TD: A Tree-Structured Decoder for Image Paragraph Captioning, ACM Multimedia Asia (MMAsia, Regular Paper), pp. 1-7, 2021-12. [Web]

[25] Zeyuan Wang, Zhiyu Wei, Lihui Zhang, Ruifan Li*, and Zhanyu Ma, Entailment Method Based on Template Selection for Chinese Text Few-shot Learning, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Tokyo, Japan, pp. 2060-2065, 2021-12. [Web]

[26] Yazhou Li, Yihui Shi, Yun Liu, Ruifan Li* and Zhanyu Ma, Image Captioning Based on An Improved Transformer with IoU Position Encoding, Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Tokyo, Japan, pp. 2066-2071, 2021-12. [Web]

[27] Ruifan Li, Hao Chen, Fangxiang Feng, Zhanyu Ma, Xiaojie Wang, and Eduard H. Hovy, Dual Graph Convolutional Neural Networks for Aspect-based Sentiment Analysis, The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP, Main Conference, Long Paper), pp. 6319-6329, 2021-08. [Web]

[28] Ruifan Li, Ning Wang, Fangxiang Feng, Guangwei Zhang, and Xiaojie Wang, Exploring Global and Local Linguistic Representations for Text-to-image Synthesis, IEEE Transactions on Multimedia (TMM), Vol. 22, pp. 3075-3087, 2020-12. [Web]

[29] Fangxiang Feng, Tianrui Niu, Ruifan Li, Xiaojie Wang, and Huixing Jiang, Learning Visual Features from Product Title for Image Retrieval. ACM International Conference on Multimedia (ACM MM, Short Paper), pp. 4723-4727, 2020-10. [Web]

[30] Ruifan Li, Haoyu Liang, Yihui Shi, Fangxiang Feng, and Xiaojie Wang, Dual-CNN: A Convolutional Language Decoder for Paragraph Image Captioning, Neurocomputing (NEUCOM), Vol. 396, pp. 92-101, 2020-07. [Web]

[31] Tingting Zhu, Yifang Du, Ruifan Li*, Yongping Xiong, An unsupervised approach to recognizing new words in power domain, Vol. 39, pp. 159-165, Electronic Power Engineering Technology (in Chinese), 2020-06. [Web]

[32] Ruifan Li, Xuesen Zhang, Guang Chen, Yuzhao Mao, and Xiaojie Wang, Multi-negative samples with Generative Adversarial Networks for image retrieval, Neurocomputing (NEUCOM), Vol. 394, pp. 146-157, 2020-06. [Web]

[33] Chenfei Wu, Jinlai Liu, Xiaojie Wang, and Ruifan Li, Differential Networks for Visual Question Answering, Association for the Advancement of Artificial Intelligence (AAAI), pp. 8997-9004, 2019-02. [Web]

[34] Ruifan Li, Fangxiang Feng, Ibrar Ahmad, and Xiaojie Wang, Retrieving real world clothing images via multi-weight deep convolutional neural networks, Cluster Computing, Vol. 22, pp. 7123-7134, 2019-05. [Web]

[35] Ruifan Li, Haoyu Liang, Fangxiang Feng, Guangwei Zhang, and Xiaojie Wang, Paragraph Image Captioning with Deep Fully Convolutional Neural Networks, Journal of Beijing University of Posts and Telecommunications (in Chinese), Vol. 42, pp. 155-161, 2019-12. [Web] 

[36] Yuzhao Mao, Chang Zhou, Xiaojie Wang, and Ruifan Li, Show and Tell More: Topic-Oriented Multi-Sentence Image Captioning, International Joint Conference on Artificial Intelligence (IJCAI), pp. 4258-4264, 2018-07. [Web]

[37] Ruifan Li, Wencong Lu, Haoyu Liang, Yuzhao Mao, and Xiaojie Wang, Multiple Features With Extreme Learning Machines For Clothing Image Recognition. IEEE Access, Vol. 6, pp. 36283-36294, 2018-07. [Web]

[38] Guangwei Zhang and Ruifan Li*, Fog computing architecture-based data acquisition for WSN applications, China Communications, vol. 14, no. 11, pp. 69-81, 2017-11. [Web]

[39] Ibrar Ahmad, Xiaojie Wang, and Ruifan Li, Manzoor Ahmed, Rahat Ullah, Line and Ligature Segmentation of Urdu Nastaleeq Text. IEEE Access Vol. 5, pp. 10924-10940, 2017-05. [Web]

[40] Ibrar Ahmad, Xiaojie Wang, Ruifan Li and Shahid Rasheed, Offline Urdu Nastaleeq optical character recognition based on stacked denoising autoencoder, China Communications, vol. 14, no. 1, pp. 146-157, 2017-01. [Web]

[41] Peng Lu, Xujun Peng, Caixia Yuan, Ruifan Li, and Xiaojie Wang, Image color harmony modeling through neighbored co-occurrence colors, Neurocomputing, Vol. 201, pp. 82-91, 2016-08. [Web]

[42] Fangxiang Feng, Xiaojie Wang, Ruifan Li, and Ibrar Ahmad, Correspondence Autoencoders for Cross-Modal Retrieval, ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Vol. 12(1s), pp.1-22, 2015-10. [Web]

[43] Ian J. Goodfellow, Dumitru Erhan, Pierre Luc Carrier, Aaron C. Courville, Mehdi Mirza, Benjamin Hamner, William Cukierski, Yichuan Tang, David Thaler, Dong-Hyun Lee, Yingbo Zhou, Chetan Ramaiah, Fangxiang Feng, Ruifan Li, Xiaojie Wang, Dimitris Athanasakis, John Shawe-Taylor, Maxim Milakov, John Park, Radu Tudor Ionescu, Marius Popescu, Cristian Grozea, James Bergstra, Jingjing Xie, Lukasz Romaszko, Bing Xu, Zhang Chuang, and Yoshua Bengio, Challenges in representation learning: A report on three machine learning contests, Neural Networks (NEUNET), Vol. 64, pp.59-63, 2015-04. [Web]

[44] Fangxiang Feng, Ruifan Li, Xiaojie Wang, Deep correspondence restricted Boltzmann machine for cross-modal retrieval, Neurocomputing (NEUCOM), Vol. 154, pp.50-60, 2015-04. [Web]

[45] Fangxiang Feng, Xiaojie Wang, and Ruifan Li, Cross-modal Retrieval with Correspondence Autoencoder, ACM International Conference on Multimedia (ACM MM), pp.7-16, 2014-11. [Web]

[46] Fangxiang Feng, Ruifan Li, and Xiaojie Wang, Constructing Hierarchical Image-tags Bimodal Representations for Word Tags Alternative Choice, Presented at the Workshop on Representation Learning, International Conference on Machine Learning (ICML), 2013-06. [Web]  

l近年学生培养情况 

1. 北京邮电大学优秀硕士学位论文（2023年，Zepeng Zhai；2022年，Hao Chen）

2. 研究生国家奖学金（2024年，Zhihan Yu；2022年，Zepeng Zhai；2021年，Hao Chen）

3. 北京邮电大学优秀学士学位论文（2020年，Lihui Zhang）

l近年研究生去向

阿里、快手、腾讯、字节、网易、中科院自动化所、华为诺亚方舟实验室、微软亚洲工程院、北京蚂蚁集团、360搜索、中兴通讯、奇安信、京东方、中国农业银行、中金公司、富国基金、世坤咨询等