姓名：宋井宽 专业技术职务：教授
联系方式：
邮箱：jingkuan.song@gmail.com
系别：计算机软件与理论系

联系方式 邮箱 jingkuan.song@gmail.com
专业技术职务_详情页 教授

个人背景 2005年-2009年：电子科技大学，本科；
2010年-2014年：澳大利亚昆士兰大学，博士；
2014年-2016年：意大利特伦托大学，博士后；
2016年-2017年：美国哥伦比亚大学，Research Scientist；
2017年-至今：电子科技大学，教授，博导;
研究方向 多媒体理解与检索、计算机视觉、人工智能
讲授课程
本科：《音视频处理技术》、《数据结构与算法》、《人工智能导论》、《走近人工智能》………
研究生：《多媒体技术与应用》………
指导三名硕士生获校级优秀毕业论文奖；三名硕士生获校级优秀毕业生称号；七名研究生获得国家奖学金。
研究成果 研究项目：
1. 协同深度视频理解、描述和视觉问答的关键技术研究，国家自然基金面上项目，2018.01-2021.12，主持；
2. “视问”—视觉问答系统，四川省科技计划项目，2019.01-2021.12，主持；
3. 多源数据融合集成与分析技术研究，贵州省科技计划项目，2018.01-2020.12，主持；
4. 人员径迹辐照环境捕捉技术研究，横向项目，2020.06-2020.11，主持；
5. 地空协作的重大灾害监测搜救平台主动认知技术研究，科技创新2030-“新一代人工智能”重大项目，2019.12-2023.12，参研；
论文列表：
作者+论文名称+期刊名称+发表时间或页面
[1] Jingkuan Song, Tao He, Lianli Gao, Xing Xu, Alan Hanjalic, and Heng T. Shen. “Unified Binary Generative Adversarial Network for Image Retrieval and Compression,”International Journal of Computer Vision, vol.128, no.8-9, pp.2243–2264, 2020.
[2] Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, Alan Hanjalic, and Heng T. Shen. “From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning,”IEEE transactions on neural networks and learning systems, vol.30, no.10, pp.3047–3058, 2019.
[3] Jingkuan Song, Lianli Gao, Li Liu, Xiaofeng Zhu, and Nicu Sebe. “Quantization-based hashing: a general framework for scalable image and video retrieval,”Pattern Recognition, vol.75, pp.175–187, 2018.
[4] Jingkuan Song, Tao He, Lianli Gao, Xing Xu, Alan Hanjalic, and Heng T. Shen. “Binary Generative Adversarial Networks for Image Retrieval,”Proceedings of the AAAI Conference on Artificial Intelligence, vol.32, no.1, 2018.
[5] Jingkuan Song, Tao He, Lianli Gao, Xing Xu, and Heng T. Shen. “Deep Region Hashing for Generic Instance Search from Images,”Proceedings of the AAAI Conference on Artificial Intelligence, vol.32, no.1, 2018.
[6] Jingkuan Song, Hanwang Zhang, Xiangpeng Li, Lianli Gao, Meng Wang, and Richang Hong. “Self-Supervised Video Hashing With Hierarchical Binary Auto-Encoder,”IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, vol.27, no.7, pp.3210–3221, 2018.
[7] Jingkuan Song, Heng T. Shen, Jianfeng Wang, Zi Huang, Nicu Sebe, and Jingdong Wang. “A Distance-Computation-Free Search Scheme for Binary Code Databases,”IEEE Transactions on Multimedia, vol.18, no.3, pp.484–495, 2016.
[8] Jingkuan Song, Lianli Gao, Feiping Nie, Heng T. Shen, Yan Yan, and Nicu Sebe. “Optimized Graph Learning Using Partial Tags and Multiple Features for Image and Video Annotation,”IEEE transactions on image processing: a publication of the IEEE Signal Processing Society, vol.25, no.11, pp.4999–5011, 2016.
[9] Jingkuan Song, Lianli Gao, Fuhao Zou, Yan Yan, and Nicu Sebe. “Deep and fast: Deep learning hashing with semi-supervised graph construction,”Image and Vision Computing, vol.55, pp.101–108, 2016.
[10] Yu Liu,Jingkuan Song, Ke Zhou, Lingyu Yan, Li Liu, Fuhao Zou, and Ling Shao. “Deep Self-Taught Hashing for Image Retrieval,”IEEE transactions on cybernetics, vol.49, no.6, pp.2229–2241, 2019.
[11] Lianli Gao, Xiangpeng Li,Jingkuan Song, and Heng T. Shen. “Hierarchical LSTMs with Adaptive Attention for Visual Captioning,”IEEE transactions on pattern analysis and machine intelligence, vol.42, no.5, pp.1112–1131, 2020.
[12] Jingdong Wang, Ting Zhang,Jingkuan Song, Nicu Sebe, and Heng T. Shen. “A Survey on Learning to Hash,”IEEE transactions on pattern analysis and machine intelligence, vol.40, no.4, pp.769–790, 2018.
[13] Jingkuan Song, Ruimin Lang, Xiaosu Zhu, Xing Xu, Lianli Gao, and Heng T. Shen.“3D Self-Attention for Unsupervised Video Quantization,”InProceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.1061–1070, 2020.
[14] Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu, and Heng T. Shen.“Deep Recurrent Quantization for Generating Sequential Binary Codes,”InProceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pp.912–918, 2019.
[15] Jingkuan Song, Pengpeng Zeng, Lianli Gao, and Heng T. Shen.“From Pixels to Objects: Cubic Visual Attention for Visual Question Answering,”InProceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp.906–912, 2018.
[16] Jingkuan Song, Tao He, Hangbo Fan, and Lianli Gao, 2017. Deep Discrete Hashing with Self-supervised Pairwise Labels. InMachine Learning and Knowledge Discovery in Databases, Michelangelo Ceci, Jaakko Hollmén, Ljup?o Todorovski, Celine Vens and Sa?o D?eroski, Eds. Lecture Notes in Computer Science. Springer International Publishing, Cham, pp.223–238. 2017.
[17] Jingkuan Song, Lianli Gao, Mihai M. Puscas, Feiping Nie, Fumin Shen, and Nicu Sebe.“Joint Graph Learning and Video Segmentation via Multiple Cues and Topology Calibration,”InProceedings of the 24th ACM international conference on Multimedia, pp.831–840, 2016.
[18] Yuyu Guo,Jingkuan Song, Lianli Gao, and Heng T. Shen.“One-shot Scene Graph Generation,”InProceedings of the 28th ACM International Conference on Multimedia, pp.3090–3098, 2020.
[19] Xing Xu,Jingkuan Song, Huimin Lu, Li He, Yang Yang, and Fumin Shen.“Dual Learning for Visual Question Generation,”In2018 IEEE International Conference on Multimedia and Expo (ICME), pp.1–6, 2018.
[20] Xing Xu,Jingkuan Song, Huimin Lu, Yang Yang, Fumin Shen, and Zi Huang.“Modal-adversarial Semantic Learning Network for Extendable Cross-modal Retrieval,”InProceedings of the 2018 ACM on International Conference on Multimedia Retrieva（ICMR）l, pp.46–54, 2018.
[21] Dan Xu,Jingkuan Song, Xavier Alameda-Pineda, Elisa Ricci, and Nicu Sebe.“Multi-Paced Dictionary Learning for cross-domain retrieval and recognition,”In2016 23rd International Conference on Pattern Recognition (ICPR), pp.3228–3233, 2016.
[22] Lianli Gao, Junchen Zhu,Jingkuan Song, Feng Zheng, and Heng T. Shen.“Lab2Pix: Label-Adaptive Generative Adversarial Network for Unsupervised Image Synthesis,”InProceedings of the 28th ACM International Conference on Multimedia, pp.3734–3742, 2020.
[23] Lianli Gao, Qilong Zhang,Jingkuan Song, Xianglong Liu, and Heng T. Shen, 2020. Patch-Wise Attack for Fooling Deep Neural Network. InComputer Vision–ECCV 2020, Andrea Vedaldi, Horst Bischof, Thomas Brox and Jan-Michael Frahm, Eds. Lecture Notes in Computer Science. Springer International Publishing, Cham, pp.307–322.DOI: https://doi.org/10.1007/978-3-030-58604-1_19.
[24] Xuanhan Wang, Lianli Gao,Jingkuan Song, and Heng T. Shen.“KTN: Knowledge Transfer Network for Multi-person DensePose Estimation,”InProceedings of the 28th ACM International Conference on Multimedia, pp.3780–3788, 2020.
研究成果获奖：
2016年获模式识别国际会议ICPR最佳论文奖；
2017获信息检索顶级会议SIGIR最佳论文提名奖；
ADC最佳学生论文奖；
获评2019 ACM China SIGMM学术新星奖；
2020 AMiner AI 2000“多媒体最具影响力****”提名；
社会兼职及荣誉
编委：
ACM Trans. on Multimedia Computing, Communications and Applications
KSII Trans. on Internet and Information System
客座编委：
World Wide Web Journal、IEEE Trans. on Multimedia、Pattern Recognition、ACM Trans. on Data Science
会议：
ACM Multimedia 18'-20' Area Chair领域主席、IJCAI 2018 Senior Program Committee Member、ACM Multimedia 2021 Workshop Chair、ACM Multimedia Asia 2020 Workshop Chair、IEEE ICME Area Chair
学术组织：
IEEE高级会员、CCF多媒体专委会会员
………
【其他】

宋井宽教授常年招收有志于长期在多媒体、计算机视觉和人工智能领域进行国际前沿研究的全职博士生、博士后和副教授（提供极具竞争力的年薪和科研配套支持），根据申请人背景可在攻读期间派送至澳大利亚昆士兰大学、哥伦比亚大学、南洋理工大学等知名高校进行联合培养，并提供奖学金支持。感兴趣者请发送个人学术简历至jingkuan.song@gmail.com。