Jingkuan Song (宋井宽)
Professor (教授,博士生导师)

About Me

Jingkuan Song is a full professor with University of Electronic Science and Technology of China (UESTC) . He joined Columbia University as a Postdoc Research Scientist (2016-2017), and University of Trento as a Research Fellow (2014-2016). He obtained his PhD degree in 2014 from The University of Queensland (UQ), Australia (advised by Prof. Heng Tao Shen). His research interest includes large-scale multimedia retrieval, image/video segmentation and image/video understading using hashing, graph learning and deep learning techniques. He was the winner of the Best Paper Award in ICPR (2016, Mexico), Best Student Paper Award in Australian Database Conference (2017, Australia), and Best Paper Honorable Mention Award (2017, Japan). He is Guest Editor of TMM, WWWJ and he is PC member of CVPR’18, MM'18, IJCAI'18, etc.

I am looking for highly motivated PhD students, Postdoctorals and Assistant Professors to conduct world-class research in my team. Please send your CV or enquiries to my email.


  • May. 1, 2021: I will serve as Technical Demo Chairs for ACM MM 21!      New     
  • May. 1, 2021: 2 IJCAI & 1 AAAI are accepted!
  • Aug. 20, 2020: 4 ACM MM & 2 IJCAI & 1 ECCV & 1 AAAI are accepted!
  • Jun. 18, 2019: I will serve as Associate Editor for TOMM!
  • May. 09, 2019: 5 IJCAI papers are accepted!
  • Feb. 01, 2019: 4 AAAI & 1 TPAMI & 1 TIP papers are accepted!



2017 - now





2017 - now




2019 ACM China SIGMM学术新星奖

2020 AMiner AI 2000“多媒体最具影响力学者”提名


2017 - now

担任国际SCI期刊ACM TOMM等编委

担任WWW Journal、TMM、Pattern Recognition、ACM TDS等期刊的客座编委

担任多个期刊的评审和多个国际顶级会议(MM'18-'21, IJCAI'18)的领域主席




  1. Junchen Zhu, Lianli Gao, Jingkuan Song, Yuan-Fang Li, Feng Zheng, Xuelong Li, Heng Tao Shen. Label-Guided Generative Adversarial Network for Realistic Image Synthesis. TPAMI, 2022. JCR-1. [code]
  2. Ye Liu, Yaya Cheng, Lianli Gao, Xianglong Liu, Qilong Zhang, Jingkuan Song. Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack. CVPR. CCF-A. [code]
  3. Xinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao, Hao Huang, Heng Tao Shen, Jingkuan Song. Fine-Grained Predicates Learning for Scene Graph Generation. CVPR 2022. CCF-A. [code]
  4. Hao Ni, Jingkuan Song, Xiaopeng Luo, Feng Zheng, Wen Li, Heng Tao Shen. Meta Distribution Alignment for Generalizable Person Re-Identification. CVPR. CCF A. [code]
  5. Xiaosu Zhu, Jingkuan Song, Lianli Gao, Feng Zheng, Heng Tao Shen. Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression. CVPR. CCF A. [code]
  6. Qilong Zhang, Xiaodan Li, Yuefeng Chen, Jingkuan Song, Lianli Gao, Yuan He, Hui Xue. Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains. ICLR. [code]
  7. Lianli Gao, Yu Lei, Pengpeng Zeng, Jingkuan Song, Meng Wang, Heng Tao Shen. Hierarchical Representation Network with Auxiliary Tasks for Video Captioning and Visual question answering. TIP. JCR-1. [code]
  8. Pengpeng Zeng, Haonan Zhang, Jingkuan Song, Lianli Gao. S2 Transformer for Image Captioning. IJCAI. CCF A. [code]
  9. Xuanhan Wang, Lianli Gao, Yixuan Zhou, Jingkuan Song, Meng Wang. KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences. TCSVT. JCR-2. [code]
  10. Ji Zhang, Jingkuan Song, Lianli Gao, Ye Liu, Hengtao Shen, Progressive Meta-learning with Curriculum, IEEE Transactions on Circuits and Systems for Video Technology. TCSVT. JCR-2. [code]
  11. Jingkuan Song, Jingqiu Zhang, Lianli Gao, Zhou Zhao, Heng Tao Shen. AgeGAN++: Face Aging and Rejuvenation With Dual Conditional GANs.. TMM, 2022. JCR-2. [code]
  12. Xiangpeng Li, Bo Wu, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Chuang Gan. Text-Instance Graph: Exploring Relational Semantics for Text-based Visual Question Answering. Pattern Recognition. JCR-2. [code]


  1. Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, Jingkuan Song. From General to Specific: Informative Scene Graph Generation via Balance Adjustment. ICCV. CCF-A. [code]
  2. Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li. Exploiting Scene Graphs for Human-Object Interaction Detection Tao. ICCV. CCF-A. [code]
  3. Yuyu Guo, Lianli Gao, Jingkuan Song, Peng Wang, Nicu Sebe, Heng Tao Shen, Xuelong Li. Relation Regularized Scene Graph Generation. TOC. JCR-1. [code]
  4. Yan Dai, Xuanhan Wang, Lianli Gao, Jingkuan Song, Heng Tao Shen. Rsgnet: Relation based skeleton graph network for crowded scenes pose estimation. AAAI. CCF-A. [code]
  5. Lianli Gao, Yaya Cheng, Qilong Zhang, Xing Xu, Jingkuan Song. Feature Space Targeted Attacks by Statistic Alignment. IJCAI. CCF-A. [code]
  6. Sitong Su, Jingkuan Song, Lianli Gao, Junchen Zhu. Towards Unsupervised Deformable-Instances Image-to-Image Translation. In IJCAI, 2021. CCF-A. [code]
  7. Lianli Gao, Zijie Huang, Jingkuan Song, Yang yang, Heng Tao Shen. Push & Pull: Transferable Adversarial Examples With Attentive Attack. TMM. JCR-2. [code]
  8. Xuanhan Wang, Lianli Gao, Jingkuan Song, Yuyu Guo, Heng Tao Shen. AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences. TMM 2021. JCR-2. [code]
  9. Xuanhan Wang, Lianli Gao, Yan Dai, Yixuan Zhou, Jingkuan Song. Semantic-aware Transfer with Instance-adaptive Parsing for Crowded Scenes Pose Estimation. ACM MM. CCF-A. [code]
  10. Sitong Su, Lianli Gao, Junchen Zhu, Jie Shao, Jingkuan Song. Fully Functional Image Manipulation Using Scene Graphs in A Bounding-Box Free Way. In ACM MM,2021. CCF-A. [code]
  11. Ji Zhang, Jingkuan Song, Yazhou Yao, Lianli Gao. Curriculum-Based Meta-learning. ACM MM. CCF-A. [code]
  12. Hao Ni, Jingkuan Song, Xiaosu Zhu, Feng Zheng, Lianli Gao. Camera-Agnostic Person Re-Identification via Adversarial Disentangling Learning. ACM MM. CCF A. [code]
  13. Pengpeng Zeng, Lianli Gao, Xinyu Lyu, Shuaiqi Jing, Jingkuan Song. Conceptual and Syntactical Cross-modal Alignment with Cross-level Consistency for Image-Text Matching. ACM MM. CCF-A. [code]
  14. Xiangpeng Li, Lianli Gao, Lei Zhao, Jingkuan Song. Exploring Contextual-Aware Representation and Linguistic-Diverse Expression for Visual Dialog. ACM MM. CCF-A. [code]
  15. Lianli Gao, Daiyuan Chen, Zhou Zhao, Jie Shao, Heng Tao Shen. Lightweight dynamic conditional GAN with pyramid attention for text-to-image synthesis. PR, 2021. JCR-2. [code]
  16. Lei Zhao, Xinyu Lu, Jingkuan Song, Lianli gao. Guess which? Visual Dialog with Attentive Memory Network. Pattern Recognition 2021. JCR-2. [code]
  17. Lianli Gao, Tangming Chen, Xiangpeng Li, Pengpeng Zeng, Lei Zhao, Yuan-Fang Li. Generalized Pyramid Co-Attention with Learnable Aggregation Net for Video Question Answering. Pattern Recognition. JCR-2. [code]
  18. Lei Zhao, Haonan Zhang, Xiangpeng Li, Sen Yang, Yuanfeng Song. You Should Know More: Learning External Knowledge for Visual Dialog. Neurocomputing. JCR-2. [code]


  1. Lianli Gao, Xiangpeng Li, Jingkuan Song and Heng Tao Shen. Hierarchical LSTMs with Adaptive Attention for Visual Captioning. IEEE Trans. on Pattern Analysis and Machine Intelligence. TPAMI 2020. JCR-1. [code]
  2. Liyang Zhang, Shuaicheng Liu, Donghao Liu, Pengpeng Zeng, Xiangpeng Li, Jingkuan Song, Lianli Gao. Rich Visual Knowledge-Based Augmentation Network for Visual Question Answering. TNNLS 2020. JCR-1. [code]
  3. Lianli Gao, Qilong Zhang, Jingkuan Song, Xianglong Liu, Heng Tao Shen. Patch-wise attack for fooling deep neural network. ECCV. CCF-B. [code]
  4. Xuanhan Wang, Lianli Gao, Jingkuan Song, Heng Tao Shen. Ktn: Knowledge transfer network for multi-person densepose estimation. ACM MM, 2020. CCF-A. [code]
  5. Lianli Gao, Junchen Zhu, Jingkuan Song, Feng Zheng, Heng Tao Shen. Lab2Pix: Label-Adaptive Generative Adversarial Network for Unsupervised Image Synthesis. In ACM MM, 2020. CCF-A. [code]
  6. Yuyu Guo, Jingkuan Song, Lianli Gao, Heng Tao Shen. One-shot Scene Graph Generation. ACM MM, 2020. CCF-A. [code]
  7. Lianli Gao, Tao Li, Jingkuan Song, Zhou Zhao, Heng Tao Shen. Play and rewind: Context-aware video temporal action proposals. PR, 2020. JCR-2. [code]
  8. Lianli Gao, Yiyue Zhang, Fuhao Zou, Jie Shao, Junyu Lai. Unsupervised urban scene segmentation via domain adaptation. Neurocomputing, 2020. JCR-2. [code]
  9. Jingkuan Song, Tao He, Lianli Gao, Xing Xu, Alan Hanjalic, Heng Tao Shen. Unified Binary Generative Adversarial Network for Image Retrieval and Compression. IJCV. JCR-1. [code]


  1. Lianli Gao, Daiyuan Chen, Jingkuan Song, Xing Xu, Dongxiang Zhang, Heng Tao Shen. Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis. In AAAI, 2019. CCF-A. [code]
  2. Lianli Gao, Kaixuan Fan, Jingkuan Song, Xianglong Liu, Xing Xu, Heng Tao Shen, Deliberate Residual based Attention Network for Image Captioning, AAAI 2019. CCF-A. [code]
  3. Lianli Gao, Pengpeng Zeng, Jingkuan Song, Yuan-Fang Li, Tao Mei, Heng Tao Shen, Structured Two-stream Attention Network for Video Question Answering, AAAI, 2019. CCF-A. [code]
  4. Xiangpeng Li, Lianli Gao, Xianglong Liu, Wenbing Huang, Chuang Gan, Xiangnan He. Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering, AAAI 2019. CCF-A. [code]
  5. Xiangpeng Li, Lianli Gao, Xuanhan Wang, Wu Liu, Xing Xu, Jingkuan Song and Heng Tao Shen, Learnable Aggregating Net with Divergent Loss for Video Question Answering, ACM Multimedia 2019. CCF-A. [code]
  6. Lianli Gao, Liangfu Cao, Jingkuan Song, Jie Shao, Xing Xu. Question-Led Object Attention for Visual Question Answering, Neurocomputing, 2019. JCR-2. [code]
  7. Xuanhan Wang, Lianli Gao. Fused GRU with Semantic-Temporal Attention for Video Captioning, Neurocomputing, 2019. JCR-2. [code]
  8. Lianli Gao, Xiaosu Zhu, Jingkuan Song, Zhou Zhao, Heng Tao Shen. Beyond product quantization: deep progressive quantization for image retrieval. IJCAI 2019. CCF-A. [code]
  9. Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu, Heng Tao Shen. Deep recurrent quantization for generating sequential binary codes. IJCAI 2019. CCF-A. [code]


  1. Jingkuan Song, Jingqiu Zhang, Lianli Gao, Xianglong Liu, Heng Tao Shen. Dual Conditional GANs for Face Aging and Rejuvenation.. In IJCAI, 2018. CCF-A. [code]
  2. Jingkuan Song, Pengpeng Zeng, Lianli Gao, Xianglong Liu, Heng Tao Shen. Examine before You Answer: Multi-task Learning with Adaptive-attentions for Multiple-choice VQA. ACM MM, 2018. CCF-A. [code]
  3. Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, Alan Hanjalic, Heng Tao Shen. From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning. TNNLS 2018. JCR-1. [code]
  4. Jingkuan Song, Pengpeng Zeng, Lianli Gao, Heng Tao Shen. From Pixels to Objects: Cubic Visual Attention for Visual Question Answering. IJCAI 2018. CCF-A. [code]


  1. Lianli Gao, Zhao Guo, Hanwang Zhang, Xing Xu, Heng Tao Shen*. “Videos Captioning with Attention-based LSTM and Semantic Consistency”. IEEE Trans. on Multimedia. JCR-2. [code]
  2. Jingkuan Song, Lianli Gao, Zhao Guo, Wu Liu, Dongxiang Zhang, Heng Tao Shen. "Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning", IJCAI 2017. CCF-A. [code]
  3. Jingdong Wang, Ting Zhang, jingkuan song, Nicu Sebe, Heng Tao Shen. A Survey on Learning to Hash. TPAMI. JCR-1. [code]


  1. Zhao Guo, Lianli Gao, Jingkuan Song, Xing Xu, Jie Shao, Heng Tao Shen, “Attention-based LSTM with Semantic Consistency for Videos captioning ", ACM MM 2016.   CCF-A. [code]

Professional Services

Associated Editor


KSII Transactions on Internet and Information Systems (Since 2017).



IJCV, TNNLS, TOMM (Since 2016).

IEEE Transactions on Image Processing, IEEE Transactions on Pattern Analysis and Machine Intelligence (Since 2016).

IEEE Transactions on Knowledge and Data Engineering (Since 2014).

IEEE Transactions on Cybernetics, Transaction on Multimedia, Transaction on Circuits and Systems for Video Technology

CVIU, Neurocomputing, MTAP (Since 2013).

ACM Multimedia, ICMR, etc..

Contact Me

Basic Info
  • Email: jingkuan.song@gmail.com

  • Office:

    Innovation center
    University of Electronic Science and Technology of China