publications

2024

  1. arXiv
    Class-wise Selection with Mixture of Graph Experts for Noisy Node Classification
    Yifan Li, Zhen Tan, Kai Shu, Huan Liu, and Yu Kong
    2024
    Under review
  2. arXiv
    Multimodal Sarcasm Detection: A Survey
    Shafkat Farabi, Tharindu Ranasinghe, Diptesh Kanojia, Yu Kong, and Marcos Zampieri
    2024
    Under review
  3. arXiv
    The Wolf Within: Covert Injection Of Malice Into Mllm Societies Via An Mllm Operative
    Zhen Tan, Chengshuai Zhao, Raha Moraffah, Yifan Li, Yu Kong, Tianlong Chen, and Huan Liu
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Responsible Generative AI Workshop, 2024
  4. arXiv
    Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
    Wentao Bao, Kai Li, Deep Anil Patel, Yuxiao Chen, and Yu Kong
    2024
    Under review
  5. arXiv
    CF-SSR: Coarse-to-Fine Saliency Score Ranking for Compositional Temporal Grounding
    Zixu Cheng, Yujiang Pu, Shaogang Gong, Parisa Kordjamshidi, and Yu Kong
    2024
    Under review
  6. arXiv
    Facial Affective Behavior Analysis Using Fine-grained Emotion Instructions
    Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, and Yu Kong
    2024
    Under review
  7. arXiv
    Mixture-of-Experts for Lifelong Learning
    Yuansheng Zhu, Md Abdullah Al Forhad, Wentao Bao, Weishi Shi, Yu Kong, and Qi Yu
    2024
    Under review
  8. arXiv
    Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
    Wentao Bao, Lichang Chen, Heng Huang, and Yu Kong
    2024
  9. arXiv
    Exploring Latent Space Energy-based Model for Fine-grained Open Set Recognition
    Wentao Bao, Qi Yu, and Yu Kong
    2024

2023

  1. ATM: Action Temporality Modeling for Video Question Answering
    Junwen Chen, Jie Zhu, and Yu Kong
    In ACM Multimedia, 2023
  2. Uncertainty-aware State Space Transformer for Egocentric 3D Trajectory Forecasting
    Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, and Yu Kong
    In International Conference on Computer Vision (ICCV), 2023
  3. arXiv
    An Eye for an Eye: Defending against Gradient-based Attacks with Gradients
    Hanbin Hong, Yuan Hong, and Yu Kong
    In arXiv, 2023
  4. Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder
    Xinmiao Lin, Yikang Li, Jenhao Hsiao, Chiu Man Ho, and Yu Kong
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  5. Ancestor Search: Generalized Open Set Recognition via Hyperbolic Side Information Learning
    Xiwen Dengxiong, and Yu Kong
    In IEEE/CVF Winter Conferences on Applications of Computer Vision (WACV), 2023

2022

  1. Learning an Optimal Linear Program for Multi-Target Tracking
    Shuai Li, Yu Kong, and Hamid Rezatofighi
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  2. GateHUB: Gated History Unit with Background Suppression for Online Action Detection
    Junwen Chen, Gaurav Mittal, Ye Yu, Yu Kong, and Mei Chen
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  3. OpenTAL: Towards Open Set Temporal Action Localization
    Wentao Bao, Qi Yu, and Yu Kong
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  4. A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
    Krishna Prasad Neupane, Ervine Zheng, Yu Kong, and Qi Yu
    In Association for the Advancement of Artificial Intelligence (AAAI), 2022
  5. Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems
    Shangyu Xie, Han Wang, Yu Kong, and Yuan Hong
    In IEEE Symposium on Security and Privacy (S&P), 2022
  6. Human Action Recognition and Prediction: A Survey
    Yu Kong, and Yun Fu
    International Journal of Computer Vision (IJCV), 2022

2021

  1. Coupling Adversarial Graph Embedding for Transductive Zero-shot Action Recognition
    Yi Tian, Yaping Huang, Wanru Xu, and Yu Kong
    Neurocomputing, 2021
  2. Gradient Frequency Modulation for Visually Explaining Video Understanding Models
    Xinmiao Lin, Wentao Bao, and Yu Kong
    In British Machine Vision Conference (BMVC), 2021
  3. Explainable Video Entailment with Grounded Visual Evidence
    Junwen Chen, and Yu Kong
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021
  4. DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation
    Wentao Bao, Qi Yu, and Yu Kong
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021
  5. Evidential Deep Learning for Open Set Action Recognition
    Wentao Bao, Qi Yu, and Yu Kong
    In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021
  6. Multiple Instance Relational Learning for Video Anomaly Detection
    Xiwen Dengxiong, Wentao Bao, and Yu Kong
    In International Joint Conference on Neural Networks (IJCNN), 2021
  7. Residual Dense Network for Image Restoration
    Yulun Zhang, Kunpeng Li, Kai Li, Gan Sun, Yu Kong, and Yun Fu
    IEEE Transaction on Image Processing (T-IP), 2021

2020

  1. Privacy Attributes-aware Message Passing Neural Network for Visual Privacy Attributes Classification
    Hanbin Hong, Wentao Bao, Yuan Hong, and Yu Kong
    In International Conference on Pattern Recognition (ICPR), 2020
  2. Visual Object Tracking via Multi-Stream Deep Similarity Learning Networks
    Kunpeng Li, Yu Kong, and Yun Fu
    IEEE Transaction on Image Processing (T-IP), 2020
  3. RIT-18: A Novel Dataset for Compositional Group Activity Understanding
    Junwen Chen, Haiting Hao, Hanbin Hong, and Yu Kong
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, 2020
  4. Few-shot Human Motion Prediction via Learning Novel Motion Dynamics
    Chuanqi Zang, Mingtao Pei, and Yu Kong
    In International Joint Conference on Artificial Intelligence (IJCAI), 2020
  5. Object-Aware Centroid Voting for Monocular 3D Object Detection
    Wentao Bao, Qi Yu, and Yu Kong
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
  6. Group Activity Prediction with Sequential Relational Anticipation Model
    Junwen Chen, Wentao Bao, and Yu Kong
    In European Conference on Computer Vision (ECCV), 2020
  7. Uncertainty-based Traffic Accident Anticipation withSpatio-Temporal Relational Learning
    Wentao Bao, Qi Yu, and Yu Kong
    In ACM Multimedia, 2020
  8. Activity-driven Weakly-Supervised Spatio-Temporal Grounding from Untrimmed Videos
    Junwen Chen, Wentao Bao, and Yu Kong
    In ACM Multimedia, 2020
  9. Residual Dense Network for Image Restoration
    Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu
    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2020
  10. Publishing Video Data with Indistinguishable Objects
    Han Wang, Yuan Hong, Yu Kong, and Jaideep Vaidya
    In 23rd International Conference on Extending Database Technology (EDBT), 2020
  11. Revealing a History: Palimpsest Text Separation by Recreatingthe Historical Document with Generative Networks
    Anna Starynska, David Messinger, and Yu Kong
    In arXiv, 2020
  12. Adversarial Action Prediction Networks
    Yu Kong, Zhiqiang Tao, and Yun Fu
    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2020

2019

  1. Visual Object Tracking Via Multi-Stream Deep Similarity Learning Networks
    Kunpeng Li, Yu Kong, and Yun Fu
    IEEE Transactions on Image Processing (T-IP), 2019
  2. Semi-Supervised Cross-Modality Action Recognition by Latent Tensor Transfer Learning
    Chengcheng Jia, Zhengming Ding, Yu Kong, and Yun Fu
    IEEE Trans. Circuits and Systems for Video Technology (T-CSVT), 2019
  3. Aligned Dynamic-Preserving Embedding for Zero-Shot Action Recognition
    Yi Tian, Yu Kong, Qiuqi Ruan, Gaoyun An, and Yun Fu
    IEEE Transactions on Circuits and Systems for Video Technology, 2019
  4. Activity Recognition
    Yu Kong, and Yun Fu
    In Deep Learning through Sparse and Low-Rank Modeling, 2019

2018

  1. Clustered Lifelong Learning via Representative Task Selection
    Gan Sun, Yang Cong, Yu Kong, and Xiaowei Xu
    In IEEE International Conference on Data Mining (ICDM), 2018
  2. Residual Dense Network for Image Super-Resolution
    Yulun Zhang, Yapeng Tian, Yu Kong, Bineng Zhong, and Yun Fu
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018
  3. Action Prediction from Videos via Memorizing Hard-to-Predict Samples
    Yu Kong, Shangqian Gao, Bin Sun, and Yun Fu
    In AAAI Conference on Artificial Intelligence (AAAI), 2018

2017

  1. Deep Geo-constrained Auto-encoder for Non-landmark GPS Estimation
    Shuhui Jiang, Yu Kong, and Yun Fu
    IEEE Trans. Big Data, 2017
  2. Deep Active Learning Through Cognitive Information Parcels
    Wencang Zhao, Yu Kong, Zhengming Ding, and Yun Fu
    In ACM Multimedia, 2017
  3. Sparse Subspace Clustering by Learning Approximation l0 Codes
    Jun Li, Yu Kong, and Yun Fu
    In AAAI Conference on Artificial Intelligence (AAAI), 2017
  4. Multi-Stream Deep Similarity Learning Networks for Visual Tracking
    Kunpeng Li, Yu Kong, and Yun Fu
    In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI), 2017
  5. Probabilistic Low-Rank Multitask Learning
    Yu Kong, Ming Shao, Kang Li, and Yun Fu
    IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2017
  6. Max-Margin Heterogeneous Information Machine for RGB-D Action Recognition
    Yu Kong, and Yun Fu
    International Journal of Computer Vision (IJCV), 2017
  7. Deep Sequential Context Networks for Action Prediction
    Yu Kong, Zhiqiang Tao, and Yun Fu
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
  8. Deeply Learned View-Invariant Features for Cross-View Action Recognition
    Yu Kong, Zhengming Ding, Jun Li, and Yun Fu
    IEEE Transactions on Image Processing (T-IP), 2017

2016

  1. Introduction
    Yu Kong, and Yun Fu
    In Human Activity Recognition and Prediction, 2016
  2. Activity Prediction
    Yu Kong, and Yun Fu
    In Human Activity Recognition and Prediction, 2016
  3. Learning Fast Low-Rank Projection for Image Classification
    Jun Li, Yu Kong, Handong Zhao, Jian Yang, and Yun Fu
    IEEE Transactions on Image Processing (T-IP), 2016
  4. Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition
    Yue Wu, Jun Li, Yu Kong, and Yun Fu
    In Proceedings of the 2016 ACM on Multimedia Conference, 2016
  5. RGB-D Action Recognition
    Chengcheng Jia, Yu Kong, Zhengming Ding, and Yun Fu
    In Human Activity Recognition and Prediction, 2016
  6. Efficient Image Geotagging Using Large Databases
    Dmitry Kit, Yu Kong, and Yun Fu
    IEEE Transactions on Big Data, 2016
  7. Action Recognition and Human Interaction
    Yu Kong, and Yun Fu
    In Human Activity Recognition and Prediction, 2016
  8. Close Human Interaction Recognition Using Patch-Aware Models
    Yu Kong, and Yun Fu
    IEEE Transactions on Image Processing (T-IP), 2016
  9. Discriminative Relational Representation Learning for RGB-D Action Recognition
    Yu Kong, and Yun Fu
    IEEE Transactions on Image Processing (T-IP), 2016
  10. Learning hierarchical 3D kernel descriptors for RGB-D action recognition
    Yu Kong, Behnam Satarboroujeni, and Yun Fu
    Computer Vision and Image Understanding (CVIU), 2016
  11. Max-Margin Action Prediction Machine
    Yu Kong, and Yun Fu
    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2016

2015

  1. Hierarchical 3D kernel descriptors for action recognition using depth sequences
    Yu Kong, Behnam Satarboroujeni, and Yun Fu
    In Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on, 2015
  2. Bilinear Heterogeneous Information Machine for RGB-D Action Recognition
    Yu Kong, and Yun Fu
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

2014

  1. Interactive Phrases: Semantic Descriptions for Human Interaction Recognition
    Yu Kong, Yunde Jia, and Yun Fu
    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2014
  2. Learning a discriminative mid-level feature for action recognition
    CuiWei Liu, MingTao Pei, XinXiao Wu, Yu Kong, and YunDe Jia
    Science China Information Sciences, 2014
  3. Latent tensor transfer learning for RGB-D action recognition
    Chengcheng Jia, Yu Kong, Zhengming Ding, and Yun Raymond Fu
    In ACM Multimedia, 2014
  4. LASOM: Location Aware Self-Organizing Map for Discovering Similar and Unique Visual Features of Geographical Locations.
    Dmitry Kit, Yu Kong, and Yun Fu
    In International Joint Conference on Neural Network (IJCNN), 2014
  5. Modeling supporting regions for close human interaction recognition
    Yu Kong, and Yun Fu
    In European Conference on Computer Vision Workshop, 2014
  6. Recognising human interaction from videos by a discriminative model
    Yu Kong, Wei Liang, Zhen Dong, and Yunde Jia
    IET Computer Vision, 2014
  7. A Discriminative Model with Multiple Temporal Scales for Action Prediction
    Yu Kong, Dmitry Kit, and Yun Fu
    In European Conference on Computer Vision (ECCV), 2014

2013

  1. Activity recognition by learning structural and pairwise mid-level features using random forest
    Jie Hu, Yu Kong, and Yun Fu
    In Automatic Face and Gesture Recognition (FG), 2013 10th IEEE International Conference and Workshops on, 2013

2012

  1. Activity Recognition by Learning Structural and Pairwise Mid-level Features Using Random Forest
    Jie Hu, Yu Kong, and Yun Fu
    In Automatic Face and Gesture Recognition, 2012
  2. Action recognition with discriminative mid-level features
    Cuiwei Liu, Yu Kong, Xinxiao Wu, and Yunde Jia
    In Pattern Recognition (ICPR), 2012 21st International Conference on, 2012
  3. Contour-HOG: A Stub Feature based Level Set Method for Learning Object Contour.
    Zhi Yang, Yu Kong, and Yun Fu
    In British Machine Vision Conference (BMVC), 2012
  4. Decomposed contour prior for shape recognition
    Zhi Yang, Yu Kong, and Yun Fu
    In Pattern Recognition (ICPR), 2012 21st International Conference on, 2012
  5. A Hierarchical Model for Human Interaction Recognition
    Yu Kong, and Yunde Jia
    In IEEE International Conference on Multimedia and Expo (ICME), 2012
  6. Learning Human Interaction by Interactive Phrases
    Yu Kong, Yunde Jia, and Yun Fu
    In European Conference on Computer Vision (ECCV), 2012

2011

  1. Recognizing human interaction by multiple features
    Zhen Dong, Yu Kong, Cuiwei Liu, Hongdong Li, and Yunde Jia
    In Pattern Recognition (ACPR), 2011 First Asian Conference on, 2011
  2. Adaptive learning codebook for action recognition
    Yu Kong, Xiaoqin Zhang, Weiming Hu, and Yunde Jia
    Pattern Recognition Letters, 2011

2010

  1. Compact visual codebook for action recognition
    Qingdi Wei, Xiaoqin Zhang, Yu Kong, Weiming Hu, and Haibin Ling
    In International Conference on Image Processing (ICIP), 2010
  2. A swarm intelligence based searching strategy for articulated 3D human body tracking
    Xiaoqin Zhang, and  al.
    In IEEE Conference on Computer Vision and Pattern Recognition Workshop, 2010
  3. Learning human actions with an adaptive codebook
    Yu Kong, Xiaoqin Zhang, Weiming Hu, and Yunde Jia
    In Virtual Systems and Multimedia (VSMM), 2010 16th International Conference on, 2010

2009

  1. Group action recognition using space-time interest points
    Qingdi Wei, Xiaoqin Zhang, Yu Kong, Weiming Hu, and Haibin Ling
    In Advances in Visual Computing, 2009
  2. Learning group activity in soccer videos from local motion
    Yu Kong, Weiming Hu, Xiaoqin Zhang, Hanzi Wang, and Yunde Jia
    In Asian Conference on Computer Vision (ACCV), 2009

2008

  1. Group action recognition in soccer videos
    Yu Kong, Xiaoqin Zhang, Qingdi Wei, Weiming Hu, and Yunde Jia
    In International Conference on Pattern Recognition (ICPR), 2008