Publications

Publications by categories in reversed chronological order.

2022

  1. TPAMI
    Label-Guided Generative Adversarial Network for Realistic Image Synthesis
    Junchen Zhu, Lianli Gao, Jingkuan Song, Yuan-Fang Li, Feng Zheng, Xuelong Li, Heng Tao Shen
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2022
    HTML Code
  2. CVPR
    Practical evaluation of adversarial robustness via adaptive auto attack
    Ye Liu, Yaya Cheng, Lianli Gao, Xianglong Liu, Qilong Zhang, Jingkuan Song
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
    PDF Code
  3. CVPR
    Fine-Grained Predicates Learning for Scene Graph Generation
    Xinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao, Hao Huang, Heng Tao Shen, Jingkuan Song
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022
    PDF Code
  4. CVPR
    Meta Distribution Alignment for Generalizable Person Re-Identification
    Hao Ni, Jingkuan Song, Xiaopeng Luo, Feng Zheng, Wen Li, Heng Tao Shen
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Jun 2022
    PDF Code
  5. CVPR
    Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression
    Xiaosu Zhu, Jingkuan Song, Lianli Gao, Feng Zheng, Heng Tao Shen
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Jun 2022
    HTML
  6. ICLR
    Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
    Qilong Zhang, Xiaodan Li, Yuefeng Chen, Jingkuan Song, Lianli Gao, Yuan He, Hui Xue
    CoRR Jun 2022
    PDF Code
  7. IJCAI
    S2 transformer for image captioning
    Pengpeng Zeng, Haonan Zhang, Jingkuan Song, Lianli Gao
    In Proceedings of the International Joint Conferences on Artificial Intelligence Jun 2022
    PDF
  8. TCSVT
    KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
    Xuanhan Wang, Lianli Gao, Yixuan Zhou, Jingkuan Song, Meng Wang
    IEEE Transactions on Circuits and Systems for Video Technology Jun 2022
    arXiv
  9. TCSVT
    Progressive Meta-learning with Curriculum
    Ji Zhang, Jingkuan Song, Lianli Gao, Ye Liu, Heng Tao Shen
    IEEE Transactions on Circuits and Systems for Video Technology Jun 2022
    HTML
  10. TMM
    AgeGAN++: Face Aging and Rejuvenation With Dual Conditional GANs
    Jingkuan Song, Jingqiu Zhang, Lianli Gao, Zhou Zhao, Heng Tao Shen
    IEEE Transactions on Multimedia Jun 2022
    HTML
  11. Pattern Recognition
    Text-instance graph: Exploring the relational semantics for text-based visual question answering
    Xiangpeng Li, Bo Wu, Jingkuan Song, Lianli Gao, Pengpeng Zeng, Chuang Gan
    PR Jun 2022
    HTML
  12. TMM
    Push & Pull: Transferable Adversarial Examples With Attentive Attack
    Lianli Gao, Zijie Huang, Jingkuan Song, Yang Yang, Heng Tao Shen
    IEEE Transactions on Multimedia 2022
    HTML

2021

  1. TIP
    Hierarchical representation network with auxiliary tasks for video captioning and video question answering
    Lianli Gao, Yu Lei, Pengpeng Zeng, Jingkuan Song, Meng Wang, Heng Tao Shen
    IEEE Transactions on Image Processing 2021
    HTML
  2. ICCV
    From general to specific: Informative scene graph generation via balance adjustment
    Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, Jingkuan Song
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2021
    HTML
  3. ICCV
    Exploiting scene graphs for human-object interaction detection
    Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li
    In Proceedings of the IEEE/CVF International Conference on Computer Vision 2021
    HTML
  4. TOC
    Relation Regularized Scene Graph Generation
    Yuyu Guo, Lianli Gao, Jingkuan Song, Peng Wang, Nicu Sebe, Heng Tao Shen, Xuelong Li
    IEEE Transactions on Cybernetics 2021
    HTML
  5. IJCAI
    Feature Space Targeted Attacks by Statistic Alignment
    Lianli Gao, Yaya Cheng, Qilong Zhang, Xing Xu, Jingkuan Song
    2021
    arXiv
  6. IJCAI
    Towards Unsupervised Deformable-Instances Image-to-Image Translation
    Sitong Su, Jingkuan Song, Lianli Gao, Junchen Zhu
    In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21 Aug 2021
    PDF
  7. TMM
    AMANet: Adaptive Multi-Path Aggregation for Learning Human 2D-3D Correspondences
    Xuanhan Wang, Lianli Gao, Jingkuan Song, Yuyu Guo, Heng Tao Shen
    IEEE Transactions on Multimedia Aug 2021
    HTML
  8. ACM MM
    Semantic-Aware Transfer with Instance-Adaptive Parsing for Crowded Scenes Pose Estimation
    Xuanhan Wang, Lianli Gao, Yan Dai, Yixuan Zhou, Jingkuan Song
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  9. ACM MM
    Fully Functional Image Manipulation Using Scene Graphs in A Bounding-Box Free Way
    Sitong Su, Lianli Gao, Junchen Zhu, Jie Shao, Jingkuan Song
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  10. ACM MM
    Curriculum-based meta-learning
    Ji Zhang, Jingkuan Song, Yazhou Yao, Lianli Gao
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  11. ACM MM
    Camera-Agnostic Person Re-Identification via Adversarial Disentangling Learning
    Hao Ni, Jingkuan Song, Xiaosu Zhu, Feng Zheng, Lianli Gao
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  12. ACM MM
    Conceptual and syntactical cross-modal alignment with cross-level consistency for image-text matching
    Pengpeng Zeng, Lianli Gao, Xinyu Lyu, Shuaiqi Jing, Jingkuan Song
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  13. ACM MM
    Exploring Contextual-Aware Representation and Linguistic-Diverse Expression for Visual Dialog
    Xiangpeng Li, Lianli Gao, Lei Zhao, Jingkuan Song
    In Proceedings of the 29th ACM International Conference on Multimedia Aug 2021
    HTML
  14. PR
    Lightweight dynamic conditional GAN with pyramid attention for text-to-image synthesis
    Lianli Gao, Daiyuan Chen, Zhou Zhao, Jie Shao, Heng Tao Shen
    Pattern Recognition Aug 2021
    HTML
  15. PR
    GuessWhich? Visual dialog with attentive memory network
    Lei Zhao, Xinyu Lyu, Jingkuan Song, Lianli Gao
    Pattern Recognition Aug 2021
    HTML
  16. PR
    Generalized pyramid co-attention with learnable aggregation net for video question answering
    Lianli Gao, Tangming Chen, Xiangpeng Li, Pengpeng Zeng, Lei Zhao, Yuan-Fang Li
    Pattern Recognition Aug 2021
    HTML

2020

  1. TNNLS
    Rich visual knowledge-based augmentation network for visual question answering
    Liyang Zhang, Shuaicheng Liu, Donghao Liu, Pengpeng Zeng, Xiangpeng Li, Jingkuan Song, Lianli Gao
    IEEE Transactions on Neural Networks and Learning Systems Aug 2020
    HTML
  2. ECCV
    Patch-wise Attack for Fooling Deep Neural Network
    Lianli Gao, Qilong Zhang, Jingkuan Song, Xianglong Liu, Heng Tao Shen
    CoRR Aug 2020
    arXiv
  3. ACM MM
    KTN: Knowledge Transfer Network for Multi-Person DensePose Estimation
    Xuanhan Wang, Lianli Gao, Jingkuan Song, Heng Tao Shen
    In Proceedings of the 28th ACM International Conference on Multimedia Aug 2020
    HTML
  4. ACM MM
    Lab2Pix: Label-Adaptive Generative Adversarial Network for Unsupervised Image Synthesis
    Lianli Gao, Junchen Zhu, Jingkuan Song, Feng Zheng, Heng Tao Shen
    In Proceedings of the 28th ACM International Conference on Multimedia Aug 2020
    HTML
  5. ACM MM
    One-shot scene graph generation
    Yuyu Guo, Jingkuan Song, Lianli Gao, Heng Tao Shen
    In Proceedings of the 28th ACM International Conference on Multimedia Aug 2020
    HTML
  6. PR
    Play and rewind: Context-aware video temporal action proposals
    Lianli Gao, Tao Li, Jingkuan Song, Zhou Zhao, Heng Tao Shen
    Pattern Recognition Aug 2020
    HTML
  7. Neurocomputing
    Unsupervised urban scene segmentation via domain adaptation
    Lianli Gao, Yiyue Zhang, Fuhao Zou, Jie Shao, Junyu Lai
    Neurocomputing Aug 2020
    HTML
  8. IJCV
    Unified binary generative adversarial network for image retrieval and compression
    Jingkuan Song, Tao He, Lianli Gao, Xing Xu, Alan Hanjalic, Heng Tao Shen
    International Journal of Computer Vision Aug 2020
    HTML
  9. Neurocomputing
    Question-Led object attention for visual question answering
    Lianli Gao, Liangfu Cao, Xing Xu, Jie Shao, Jingkuan Song
    Neurocomputing Aug 2020
    HTML
  10. Neurocomputing
    Fused GRU with semantic-temporal attention for video captioning
    Lianli Gao, Xuanhan Wang, Jingkuan Song, Yang Liu
    Neurocomputing Aug 2020
    HTML

2019

  1. TPAMI
    Hierarchical LSTMs with adaptive attention for visual captioning
    Lianli Gao, Xiangpeng Li, Jingkuan Song, Heng Tao Shen
    IEEE transactions on pattern analysis and machine intelligence Aug 2019
    HTML
  2. AAAI
    Perceptual Pyramid Adversarial Networks for Text-to-Image Synthesis
    Lianli Gao, Daiyuan Chen, Jingkuan Song, Xing Xu, Dongxiang Zhang, Heng Tao Shen
    Proceedings of the AAAI Conference on Artificial Intelligence Jul 2019
    HTML
  3. AAAI
    Deliberate attention networks for image captioning
    Lianli Gao, Kaixuan Fan, Jingkuan Song, Xianglong Liu, Xing Xu, Heng Tao Shen
    In Proceedings of the AAAI conference on artificial intelligence Jul 2019
    HTML
  4. AAAI
    Structured two-stream attention network for video question answering
    Lianli Gao, Pengpeng Zeng, Jingkuan Song, Yuan-Fang Li, Wu Liu, Tao Mei, Heng Tao Shen
    In Proceedings of the AAAI Conference on Artificial Intelligence Jul 2019
    HTML
  5. AAAI
    Beyond rnns: Positional self-attention with co-attention for video question answering
    Xiangpeng Li, Jingkuan Song, Lianli Gao, Xianglong Liu, Wenbing Huang, Xiangnan He, Chuang Gan
    In Proceedings of the AAAI Conference on Artificial Intelligence Jul 2019
    HTML
  6. ACM MM
    Learnable Aggregating Net with Diversity Learning for Video Question Answering
    Xiangpeng Li, Lianli Gao, Xuanhan Wang, Wu Liu, Xing Xu, Heng Tao Shen, Jingkuan Song
    In Proceedings of the 27th ACM International Conference on Multimedia Jul 2019
    HTML
  7. IJCAI
    Beyond product quantization: Deep progressive quantization for image retrieval
    Lianli Gao, Xiaosu Zhu, Jingkuan Song, Zhou Zhao, Heng Tao Shen
    arXiv preprint arXiv:1906.06698 Jul 2019
    arXiv
  8. IJCAI
    Deep recurrent quantization for generating sequential binary codes
    Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu, Heng Tao Shen
    arXiv preprint arXiv:1906.06699 Jul 2019
    arXiv

2018

  1. IJCAI
    Dual Conditional GANs for Face Aging and Rejuvenation.
    Jingkuan Song, Jingqiu Zhang, Lianli Gao, Xianglong Liu, Heng Tao Shen
    In IJCAI Jul 2018
    PDF
  2. ACM MM
    Examine before You Answer: Multi-Task Learning with Adaptive-Attentions for Multiple-Choice VQA
    Lianli Gao, Pengpeng Zeng, Jingkuan Song, Xianglong Liu, Heng Tao Shen
    In Proceedings of the 26th ACM International Conference on Multimedia Jul 2018
    HTML
  3. TNNLS
    From deterministic to generative: Multimodal stochastic RNNs for video captioning
    Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, Alan Hanjalic, Heng Tao Shen
    IEEE transactions on neural networks and learning systems Jul 2018
    HTML PDF
  4. IJCAI
    From Pixels to Objects: Cubic Visual Attention for Visual Question Answering
    Jingkuan Song, Pengpeng Zeng, Lianli Gao, Heng Tao Shen
    In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18 Jul 2018
    PDF

2017

  1. Video captioning with attention-based LSTM and semantic consistency
    Lianli Gao, Zhao Guo, Hanwang Zhang, Xing Xu, Heng Tao Shen
    IEEE Transactions on Multimedia Jul 2017
    HTML
  2. IJCAI
    Hierarchical LSTM with adjusted temporal attention for video captioning
    Jingkuan Song, Zhao Guo, Lianli Gao, Wu Liu, Dongxiang Zhang, Heng Tao Shen
    arXiv preprint arXiv:1706.01231 Jul 2017
    arXiv
  3. TPAMI
    A survey on learning to hash
    Jingdong Wang, Ting Zhang, Jingkuan Song, Nicu Sebe, Heng Tao Shen
    IEEE transactions on pattern analysis and machine intelligence Jul 2017
    HTML

2016

  1. ACM MM
    Attention-based LSTM with semantic consistency for videos captioning
    Zhao Guo, Lianli Gao, Jingkuan Song, Xing Xu, Jie Shao, Heng Tao Shen
    In Proceedings of the 24th ACM international conference on Multimedia Jul 2016
    HTML