Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Jingkuan Song

Jingkuan Song

From General to Specific: Informative Scene Graph Generation via Balance Adjustment


Aug 30, 2021
Yuyu Guo, Lianli Gao, Xuanhan Wang, Yuxuan Hu, Xing Xu, Xu Lu, Heng Tao Shen, Jingkuan Song

Figure 1 for From General to Specific: Informative Scene Graph Generation via Balance Adjustment
Figure 2 for From General to Specific: Informative Scene Graph Generation via Balance Adjustment
Figure 3 for From General to Specific: Informative Scene Graph Generation via Balance Adjustment
Figure 4 for From General to Specific: Informative Scene Graph Generation via Balance Adjustment

  Access Paper or Ask Questions

Unsupervised Domain-adaptive Hash for Networks


Aug 20, 2021
Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li

Figure 1 for Unsupervised Domain-adaptive Hash for Networks
Figure 2 for Unsupervised Domain-adaptive Hash for Networks
Figure 3 for Unsupervised Domain-adaptive Hash for Networks
Figure 4 for Unsupervised Domain-adaptive Hash for Networks

  Access Paper or Ask Questions

Semi-supervised Network Embedding with Differentiable Deep Quantisation


Aug 20, 2021
Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li

Figure 1 for Semi-supervised Network Embedding with Differentiable Deep Quantisation
Figure 2 for Semi-supervised Network Embedding with Differentiable Deep Quantisation
Figure 3 for Semi-supervised Network Embedding with Differentiable Deep Quantisation
Figure 4 for Semi-supervised Network Embedding with Differentiable Deep Quantisation

  Access Paper or Ask Questions

Semantic Compositional Learning for Low-shot Scene Graph Generation


Aug 19, 2021
Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, Yuan-Fang Li

Figure 1 for Semantic Compositional Learning for Low-shot Scene Graph Generation
Figure 2 for Semantic Compositional Learning for Low-shot Scene Graph Generation
Figure 3 for Semantic Compositional Learning for Low-shot Scene Graph Generation
Figure 4 for Semantic Compositional Learning for Low-shot Scene Graph Generation

  Access Paper or Ask Questions

Exploiting Scene Graphs for Human-Object Interaction Detection


Aug 19, 2021
Tao He, Lianli Gao, Jingkuan Song, Yuan-Fang Li

Figure 1 for Exploiting Scene Graphs for Human-Object Interaction Detection
Figure 2 for Exploiting Scene Graphs for Human-Object Interaction Detection
Figure 3 for Exploiting Scene Graphs for Human-Object Interaction Detection
Figure 4 for Exploiting Scene Graphs for Human-Object Interaction Detection
* Accepted to ICCV 2021 
  Access Paper or Ask Questions

Feature Space Targeted Attacks by Statistic Alignment


May 25, 2021
Lianli Gao, Yaya Cheng, Qilong Zhang, Xing Xu, Jingkuan Song

Figure 1 for Feature Space Targeted Attacks by Statistic Alignment
Figure 2 for Feature Space Targeted Attacks by Statistic Alignment
Figure 3 for Feature Space Targeted Attacks by Statistic Alignment
Figure 4 for Feature Space Targeted Attacks by Statistic Alignment

  Access Paper or Ask Questions

Staircase Sign Method for Boosting Adversarial Attacks


Apr 20, 2021
Lianli Gao, Qilong Zhang, Xiaosu Zhu, Jingkuan Song, Heng Tao Shen

Figure 1 for Staircase Sign Method for Boosting Adversarial Attacks
Figure 2 for Staircase Sign Method for Boosting Adversarial Attacks
Figure 3 for Staircase Sign Method for Boosting Adversarial Attacks
Figure 4 for Staircase Sign Method for Boosting Adversarial Attacks
* 13 pages, 6 figures 
  Access Paper or Ask Questions

Patch-wise++ Perturbation for Adversarial Targeted Attacks


Jan 07, 2021
Lianli Gao, Qilong Zhang, Jingkuan Song, Heng Tao Shen

Figure 1 for Patch-wise++ Perturbation for Adversarial Targeted Attacks
Figure 2 for Patch-wise++ Perturbation for Adversarial Targeted Attacks
Figure 3 for Patch-wise++ Perturbation for Adversarial Targeted Attacks
Figure 4 for Patch-wise++ Perturbation for Adversarial Targeted Attacks
* 12 pages, 9 figures. arXiv admin note: text overlap with arXiv:2007.06765 
  Access Paper or Ask Questions

Patch-wise Attack for Fooling Deep Neural Network


Jul 16, 2020
Lianli Gao, Qilong Zhang, Jingkuan Song, Xianglong Liu, Heng Tao Shen

Figure 1 for Patch-wise Attack for Fooling Deep Neural Network
Figure 2 for Patch-wise Attack for Fooling Deep Neural Network
Figure 3 for Patch-wise Attack for Fooling Deep Neural Network
Figure 4 for Patch-wise Attack for Fooling Deep Neural Network
* Accepted by ECCV 2020 
  Access Paper or Ask Questions

Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation


Jun 13, 2020
Tao He, Lianli Gao, Jingkuan Song, Jianfei Cai, Yuan-Fang Li

Figure 1 for Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
Figure 2 for Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
Figure 3 for Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
Figure 4 for Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation

  Access Paper or Ask Questions

Binary Neural Networks: A Survey


Mar 31, 2020
Haotong Qin, Ruihao Gong, Xianglong Liu, Xiao Bai, Jingkuan Song, Nicu Sebe

Figure 1 for Binary Neural Networks: A Survey
Figure 2 for Binary Neural Networks: A Survey
Figure 3 for Binary Neural Networks: A Survey
Figure 4 for Binary Neural Networks: A Survey
* Pattern Recognition (2020) 107281 
  Access Paper or Ask Questions

IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks


Sep 25, 2019
Haotong Qin, Ruihao Gong, Xianglong Liu, Ziran Wei, Fengwei Yu, Jingkuan Song

Figure 1 for IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks
Figure 2 for IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks
Figure 3 for IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks
Figure 4 for IR-Net: Forward and Backward Information Retention for Highly Accurate Binary Neural Networks
* Please withdrawn this paper, required by my co-authors 
  Access Paper or Ask Questions

Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking


Aug 12, 2019
Tan Wang, Xing Xu, Yang Yang, Alan Hanjalic, Heng Tao Shen, Jingkuan Song

Figure 1 for Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
Figure 2 for Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
Figure 3 for Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
Figure 4 for Matching Images and Text with Multi-modal Tensor Fusion and Re-ranking
* 9 pages, 7 figures, ACM Multimedia 2019 
  Access Paper or Ask Questions

Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval


Jul 15, 2019
Lianli Gao, Xiaosu Zhu, Jingkuan Song, Zhou Zhao, Heng Tao Shen

Figure 1 for Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
Figure 2 for Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
Figure 3 for Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval
Figure 4 for Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval

  Access Paper or Ask Questions

Deep Recurrent Quantization for Generating Sequential Binary Codes


Jul 15, 2019
Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu, Heng Tao Shen

Figure 1 for Deep Recurrent Quantization for Generating Sequential Binary Codes
Figure 2 for Deep Recurrent Quantization for Generating Sequential Binary Codes
Figure 3 for Deep Recurrent Quantization for Generating Sequential Binary Codes
Figure 4 for Deep Recurrent Quantization for Generating Sequential Binary Codes

  Access Paper or Ask Questions

One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network


Jul 01, 2019
Tao He, Yuan-Fang Li, Lianli Gao, Dongxiang Zhang, Jingkuan Song

Figure 1 for One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
Figure 2 for One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
Figure 3 for One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
Figure 4 for One Network for Multi-Domains: Domain Adaptive Hashing with Intersectant Generative Adversarial Network
* Accepted by IJCAI 2019 
  Access Paper or Ask Questions

Localizing Unseen Activities in Video via Image Query


Jun 28, 2019
Zhu Zhang, Zhou Zhao, Zhijie Lin, Jingkuan Song, Deng Cai

Figure 1 for Localizing Unseen Activities in Video via Image Query
Figure 2 for Localizing Unseen Activities in Video via Image Query
Figure 3 for Localizing Unseen Activities in Video via Image Query
Figure 4 for Localizing Unseen Activities in Video via Image Query
* Accepted by IJCAI 2019 as a poster paper 
  Access Paper or Ask Questions

Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks


Jun 28, 2019
Zhu Zhang, Zhou Zhao, Zhijie Lin, Jingkuan Song, Xiaofei He

Figure 1 for Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
Figure 2 for Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
Figure 3 for Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
Figure 4 for Open-Ended Long-Form Video Question Answering via Hierarchical Convolutional Self-Attention Networks
* Accepted by IJCAI 2019 as a poster paper 
  Access Paper or Ask Questions

Hierarchical LSTMs with Adaptive Attention for Visual Captioning


Dec 26, 2018
Jingkuan Song, Xiangpeng Li, Lianli Gao, Heng Tao Shen

Figure 1 for Hierarchical LSTMs with Adaptive Attention for Visual Captioning
Figure 2 for Hierarchical LSTMs with Adaptive Attention for Visual Captioning
Figure 3 for Hierarchical LSTMs with Adaptive Attention for Visual Captioning
Figure 4 for Hierarchical LSTMs with Adaptive Attention for Visual Captioning
* arXiv admin note: substantial text overlap with arXiv:1706.01231 
  Access Paper or Ask Questions

Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval


Mar 05, 2018
Dan Xu, Xavier Alameda-Pineda, Jingkuan Song, Elisa Ricci, Nicu Sebe

Figure 1 for Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval
Figure 2 for Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval
Figure 3 for Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval
Figure 4 for Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval

  Access Paper or Ask Questions

Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder


Feb 07, 2018
Jingkuan Song, Hanwang Zhang, Xiangpeng Li, Lianli Gao, Meng Wang, Richang Hong

Figure 1 for Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
Figure 2 for Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
Figure 3 for Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder
Figure 4 for Self-Supervised Video Hashing with Hierarchical Binary Auto-encoder

  Access Paper or Ask Questions

From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning


Oct 20, 2017
Jingkuan Song, Yuyu Guo, Lianli Gao, Xuelong Li, Alan Hanjalic, Heng Tao Shen

Figure 1 for From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
Figure 2 for From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
Figure 3 for From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
Figure 4 for From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning

  Access Paper or Ask Questions

Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval


Aug 08, 2017
Yuming Shen, Li Liu, Ling Shao, Jingkuan Song

Figure 1 for Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
Figure 2 for Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
Figure 3 for Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
Figure 4 for Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
* Accepted by ICCV 2017 as a conference paper 
  Access Paper or Ask Questions

Binary Generative Adversarial Networks for Image Retrieval


Aug 08, 2017
Jingkuan Song

Figure 1 for Binary Generative Adversarial Networks for Image Retrieval
Figure 2 for Binary Generative Adversarial Networks for Image Retrieval
Figure 3 for Binary Generative Adversarial Networks for Image Retrieval
Figure 4 for Binary Generative Adversarial Networks for Image Retrieval
* arXiv admin note: text overlap with arXiv:1702.00758 by other authors 
  Access Paper or Ask Questions

Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search


Jul 13, 2017
Lei Zhu, Zi Huang, Xiaobai Liu, Xiangnan He, Jingkuan Song, Xiaofang Zhou

Figure 1 for Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search
Figure 2 for Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search
Figure 3 for Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search
Figure 4 for Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search

  Access Paper or Ask Questions

Learning in High-Dimensional Multimedia Data: The State of the Art


Jul 10, 2017
Lianli Gao, Jingkuan Song, Xingyi Liu, Junming Shao, Jiajun Liu, Jie Shao

Figure 1 for Learning in High-Dimensional Multimedia Data: The State of the Art
Figure 2 for Learning in High-Dimensional Multimedia Data: The State of the Art

  Access Paper or Ask Questions