publications

2026

1. arxiv

   

   H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning

   Zhanbo Huang, Xiaoming Liu, and Yu Kong

   2026

   Preprint

   arXiv Bib Website

   @unpublished{Zhanbo2026HFlow,
     author = {Huang, Zhanbo and Liu, Xiaoming and Kong, Yu},
     note = {Preprint},
     title = {H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning},
     year = {2026}
   }

2. arxiv

   

   ViT-AdaLA: Adapting Vision Transformers with Linear Attention

   Yifan Li, Seunghyun Yoon, Viet Dac Lai, Franck Dernoncourt, Jason Kuen, Trung Bui, and Yu Kong

   2026

   Preprint

   arXiv
3. arxiv

   

   IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation

   Yifan Li, Lichi Li, Anh Dao, Yicheng Qiao, Xinyu Zhou, Zheda Mai, Daeun Lee, and 4 more authors

   2026

   Preprint

   arXiv Website
4. arxiv

   

   Time Matters: Evaluating and Enforcing Temporal Relations in Text-to-Video Generation

   Yujiang Pu and Yu Kong

   2026

   Preprint
5. arxiv

   

   From Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning

   Zhongyi Cai, Yi Du, Chen Wang, and Yu Kong

   2026

   Preprint

   arXiv
6. arxiv

   

   Towards Object-centric Reasoning for Instructional Videos

   Wenliang Guo and Yu Kong

   2026

   Preprint
7. arxiv

   Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations

   Zhen Tan, Song Wang, Yifan Li, Yu Kong, Jundong Li, Tianlong Chen, and Huan Liu

   2026

   Preprint
8. ECCV

   

   NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation

   Yujiang Pu and Yu Kong

   In European Conference on Computer Vision (ECCV), 2026

   Bib PDF Website

   @inproceedings{YujiangECCV2026,
     author = {Pu, Yujiang and Kong, Yu},
     booktitle = {European Conference on Computer Vision (ECCV)},
     title = {NoisEasier: Test-Time Noise Optimization for Text-to-Video Generation},
     year = {2026}
   }

9. ICML

   

   Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA

   Mahsa Mozaffari, Hitesh Sapkota, Yu Kong, Xumin Liu, and Qi Yu

   In International Conference on Machine Learning (ICML), 2026

   Bib PDF

   @inproceedings{Mahsa2026a,
     author = {Mozaffari, Mahsa and Sapkota, Hitesh and Kong, Yu and Liu, Xumin and and Qi Yu},
     booktitle = {International Conference on Machine Learning (ICML)},
     title = {Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA},
     year = {2026}
   }

10. FG

    

    Open Set DeepFake Detection with Category-specific Characteristics

    Zhongyi Cai, Bryce Gernon, Wentao Bao, Yifan Li, Matthew Wright, and Yu Kong

    In IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2026

    arXiv Bib Website

    @inproceedings{ZhongyiFG2026,
      author = {Cai, Zhongyi and Gernon, Bryce and Bao, Wentao and Li, Yifan and Wright, Matthew and Kong, Yu},
      booktitle = {IEEE International Conference on Automatic Face and Gesture Recognition (FG)},
      title = {Open Set DeepFake Detection with Category-specific Characteristics},
      year = {2026}
    }

11. CVPR Highlight

    

    Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition

    Zhanbo Huang, Dingqiang Ye, Xiaoming Liu, and Yu Kong

    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

    Highlight

    Bib PDF Website

    @inproceedings{ZhanboCVPR2026,
      author = {Huang, Zhanbo and Ye, Dingqiang and Liu, Xiaoming and Kong, Yu},
      booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      note = {<b>Highlight</b>},
      title = {Unlocking Motion from Large Vision Models with a Semantic and Kinematic Duality for Gait Recognition},
      year = {2026}
    }

12. CVPR

    

    From Pose to Prose: Explainable, Personalized Fitness Coaching with Biomechanical Context

    Yuyang Ji, Yixuan Shen, Shengjie Zhu, Yu Kong, and Feng Liu

    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

    Bib PDF

    @inproceedings{Ji2026,
      author = {Ji, Yuyang and Shen, Yixuan and Zhu, Shengjie and Kong, Yu and Liu, Feng},
      booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
      title = {From Pose to Prose: Explainable, Personalized Fitness Coaching with Biomechanical Context},
      year = {2026}
    }

13. ICLR

    

    Procedural Mistake Detection via Action Effect Modeling

    Wenliang Guo, Yujiang Pu, and Yu Kong

    In International Conference on Learning Representations (ICLR), 2026

    arXiv Bib Website

    @inproceedings{Wenliang2026a,
      author = {Guo, Wenliang and Pu, Yujiang and Kong, Yu},
      booktitle = {International Conference on Learning Representations (ICLR)},
      title = {Procedural Mistake Detection via Action Effect Modeling},
      year = {2026}
    }

14. WACV

    

    Show Me: Generating Instructional Videos with Diffusion Models

    Yujiang Pu, Zhanbo Huang, Vishnu Boddeti, and Yu Kong

    In Winter Conference on Applications of Computer Vision (WACV), 2026

    arXiv Bib Code Website

    @inproceedings{Yujiang2026a,
      author = {Pu, Yujiang and Huang, Zhanbo and Boddeti, Vishnu and Kong, Yu},
      booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
      title = {Show Me: Generating Instructional Videos with Diffusion Models},
      year = {2026}
    }

2025

1. NeurIPS

   

   IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

   Yifan Li, Yuhang Chen, Anh Dao, Lichi Li, Zhongyi Cai, Zhen Tan, Tianlong Chen, and 1 more author

   In NeurIPS DB Track, 2025

   arXiv Bib Code Website

   @inproceedings{YifanNeurIPS2025,
     author = {Li, Yifan and Chen, Yuhang and Dao, Anh and Li, Lichi and Cai, Zhongyi and Tan, Zhen and Chen, Tianlong and Kong, Yu},
     booktitle = {NeurIPS DB Track},
     title = {IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios},
     year = {2025}
   }

2. ICCV

   

   ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads

   Yifan Li, Tianqin Li, Xin Li, Wenbin He, Yu Kong, and Ren Liu

   In International Conference on Computer Vision (ICCV), 2025

   Bib Website

   @inproceedings{YifanICCV2025,
     author = {Li, Yifan and Li, Tianqin and Li, Xin and He, Wenbin and Kong, Yu and Liu, Ren},
     booktitle = {International Conference on Computer Vision (ICCV)},
     date-modified = {2025-03-04 09:52:59 -0500},
     title = {ViT-Split: Unleashing the Power of Vision Foundation Models via Efficient Splitting Heads},
     year = {2025}
   }

3. CVPR Highlight

   

   Learning Human-centric Motion Representation for Action Analysis

   Zhanbo Huang, Xiaoming Liu, and Yu Kong

   In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2025

   Highlight

   Bib PDF Website

   @inproceedings{ZhanboCVPR2025,
     author = {Huang, Zhanbo and Liu, Xiaoming and Kong, Yu},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2025-03-04 09:53:28 -0500},
     title = {Learning Human-centric Motion Representation for Action Analysis},
     note = {<b>Highlight</b>},
     year = {2025}
   }

4. ICML Workshop

   Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations

   Zhen Tan, Song Wang, Yifan Li, Yu Kong, Jundong Li, Tianlong Chen, and Huan Liu

   In International Conference on Machine Learning (ICML) Actionable Interpretability Workshop, 2025

   Bib

   @inproceedings{Zhen2025,
     author = {Tan, Zhen and Wang, Song and Li, Yifan and Kong, Yu and Li, Jundong and Chen, Tianlong and Liu, Huan},
     booktitle = {International Conference on Machine Learning (ICML) Actionable Interpretability Workshop},
     title = {Are We Merely Justifying Results ex Post Facto? Quantifying Explanatory Inversion in Post-Hoc Model Explanations},
     year = {2025}
   }

5. arXiv

   

   Visual Large Language Models for Generalized and Specialized Applications

   Yifan Li, Zhixin Lai, Wentao Bao, Zhen Tan, Anh Dao, Kewei Sui, Jiayi Shen, and 3 more authors

   In under review, 2025

   arXiv Bib

   @inproceedings{Yifan2025b,
     author = {Li, Yifan and Lai, Zhixin and Bao, Wentao and Tan, Zhen and Dao, Anh and Sui, Kewei and Shen, Jiayi and Liu, Dong and Liu, Huan and Kong, Yu},
     booktitle = {under review},
     title = {Visual Large Language Models for Generalized and Specialized Applications},
     year = {2025}
   }

6. CVPRW

   

   Window Token Concatenation for Efficient Visual Large Language Models

   Yifan Li, Wentao Bao, Botao Ye, Zhen Tan, Tianlong Chen, Huan Liu, and Yu Kong

   In 2nd CVPR Workshop on Efficient Large Vision Models, 2025

   Bib Website

   @inproceedings{YifanCVPRW2025,
     author = {Li, Yifan and Bao, Wentao and Ye, Botao and Tan, Zhen and Chen, Tianlong and Liu, Huan and Kong, Yu},
     booktitle = {2nd CVPR Workshop on Efficient Large Vision Models},
     date-added = {2024-06-24 15:38:47 -0400},
     date-modified = {2024-06-24 15:39:52 -0400},
     title = {Window Token Concatenation for Efficient Visual Large Language Models},
     year = {2025}
   }

7. Ensuring Measurement Invariance and Fairness in OSCEs Using AI-Based Action Detection Models for Hand-Washing and Glove-Wearing: A Fairness Approach for Small Sample Sizes

   Chi Chang, Wentao Bao, Yu Kong, and Heather Laird-Fick

   In American Educational Research Association Annual Meeting, 2025

   Bib

   @inproceedings{Chi2025,
     author = {Chang, Chi and Bao, Wentao and Kong, Yu and Laird-Fick, Heather},
     booktitle = {American Educational Research Association Annual Meeting},
     title = {Ensuring Measurement Invariance and Fairness in OSCEs Using AI-Based Action Detection Models for Hand-Washing and Glove-Wearing: A Fairness Approach for Small Sample Sizes},
     year = {2025}
   }

8. WACV

   

   Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection

   Wentao Bao, Kai Li, Deep Anil Patel, Yuxiao Chen, and Yu Kong

   In Winter Conference on Applications of Computer Vision (WACV), 2025

   arXiv Bib

   @inproceedings{WentaoWACV2025,
     author = {Bao, Wentao and Li, Kai and Patel, Deep Anil and Chen, Yuxiao and Kong, Yu},
     booktitle = {Winter Conference on Applications of Computer Vision (WACV)},
     title = {Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection},
     year = {2025}
   }

2024

1. Assessing Medical Students’ Hand-Washing and Glove-Wearing Actions in an Objective Structured Clinical Examination Using Computer Vision

   Chi Chang, Wentao Bao, Yu Kong, and Heather Laird-Fick

   In The annual ChangeMedEd conference, 2024

   Bib

   @inproceedings{Chi2024,
     author = {Chang, Chi and Bao, Wentao and Kong, Yu and Laird-Fick, Heather},
     booktitle = {The annual ChangeMedEd conference},
     title = {Assessing Medical Students’ Hand-Washing and Glove-Wearing Actions in an Objective Structured Clinical Examination Using Computer Vision},
     year = {2024}
   }

2. ECCV

   

   Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

   Wentao Bao, Lichang Chen, Heng Huang, and Yu Kong

   In European Conference on Computer Vision (ECCV), 2024

   arXiv Bib Poster

   @inproceedings{WentaoECCV2024a,
     author = {Bao, Wentao and Chen, Lichang and Huang, Heng and Kong, Yu},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-modified = {2024-07-01 09:54:21 -0400},
     title = {Prompting Language-Informed Distribution for Compositional Zero-Shot Learning},
     year = {2024}
   }

3. ECCV

   

   SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding

   Zixu Cheng, Yujiang Pu, Shaogang Gong, Parisa Kordjamshidi, and Yu Kong

   In European Conference on Computer Vision (ECCV), 2024

   arXiv Bib Poster

   @inproceedings{YujiangECCV2024,
     author = {Cheng, Zixu and Pu, Yujiang and Gong, Shaogang and Kordjamshidi, Parisa and Kong, Yu},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-added = {2024-04-15 10:59:17 -0400},
     date-modified = {2024-07-01 09:53:42 -0400},
     title = {SHINE: Saliency-aware HIerarchical NEgative Ranking for Compositional Temporal Grounding},
     year = {2024}
   }

4. ECCV

   

   Facial Affective Behavior Analysis Using Fine-grained Emotion Instructions

   Yifan Li, Anh Dao, Wentao Bao, Zhen Tan, Tianlong Chen, Huan Liu, and Yu Kong

   In European Conference on Computer Vision (ECCV), 2024

   arXiv Bib Website

   @inproceedings{YifanECCV2024,
     author = {Li, Yifan and Dao, Anh and Bao, Wentao and Tan, Zhen and Chen, Tianlong and Liu, Huan and Kong, Yu},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-added = {2024-04-15 10:58:35 -0400},
     date-modified = {2024-07-01 09:53:56 -0400},
     title = {Facial Affective Behavior Analysis Using Fine-grained Emotion Instructions},
     year = {2024}
   }

5. ECCV

   

   Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment

   Yuxiao Chen, Kai Li, Wentao Bao, Deep Patel, Yu Kong, Martin Renqiang Min, and Dimitris Metaxas

   In European Conference on Computer Vision (ECCV), 2024

   Bib PDF

   @inproceedings{WentaoECCV2024b,
     author = {Chen, Yuxiao and Li, Kai and Bao, Wentao and Patel, Deep and Kong, Yu and Min, Martin Renqiang and Metaxas, Dimitris},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-modified = {2024-07-05 17:56:32 -0400},
     title = {Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment},
     year = {2024}
   }

6. IJCAI

   

   A Survey of Multimodal Sarcasm Detection

   Shafkat Farabi, Tharindu Ranasinghe, Diptesh Kanojia, Yu Kong, and Marcos Zampieri

   In International Joint Conference on Artificial Intelligence (IJCAI), 2024

   Bib PDF

   @inproceedings{Farabi2024,
     author = {Farabi, Shafkat and Ranasinghe, Tharindu and Kanojia, Diptesh and Kong, Yu and Zampieri, Marcos},
     booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
     date-added = {2024-04-15 11:02:55 -0400},
     date-modified = {2024-07-23 10:58:55 -0400},
     title = {A Survey of Multimodal Sarcasm Detection},
     year = {2024}
   }

7. CVPR

   

   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

   arXiv Bib

   @inproceedings{TanCVPRW2024,
     author = {Tan, Zhen and Zhao, Chengshuai and Moraffah, Raha and Li, Yifan and Kong, Yu and Chen, Tianlong and Liu, Huan},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Responsible Generative AI Workshop},
     date-added = {2024-04-15 11:01:39 -0400},
     date-modified = {2024-04-15 11:02:42 -0400},
     title = {The Wolf Within: Covert Injection Of Malice Into Mllm Societies Via An Mllm Operative},
     year = {2024}
   }

8. arXiv

   

   Exploring Latent Space Energy-based Model for Fine-grained Open Set Recognition

   Wentao Bao, Qi Yu, and Yu Kong

   2024

   Under review

   arXiv Bib

   @unpublished{Wentao2024,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {arXiv},
     date-modified = {2024-04-15 11:07:04 -0400},
     note = {Under review},
     title = {Exploring Latent Space Energy-based Model for Fine-grained Open Set Recognition},
     year = {2024}
   }

2023

1. Using Computer Vision to Assess Students’ Safety Behaviors in an Objective Structured Clinical Examination

   Chi Chang, Hong Zhuang, Yu Kong, and Heather Laird-Fick

   In The annual ChangeMedEd conference, 2023

   Bib

   @inproceedings{Chi2023,
     author = {Chang, Chi and Zhuang, Hong and Kong, Yu and Laird-Fick, Heather},
     booktitle = {The annual ChangeMedEd conference},
     title = {Using Computer Vision to Assess Students' Safety Behaviors in an Objective Structured Clinical Examination},
     year = {2023}
   }

2. MM

   ATM: Action Temporality Modeling for Video Question Answering

   Junwen Chen, Jie Zhu, and Yu Kong

   In ACM Multimedia, 2023

   arXiv Bib

   @inproceedings{JunwenMM2023,
     author = {Chen, Junwen and Zhu, Jie and Kong, Yu},
     booktitle = {ACM Multimedia},
     date-modified = {2024-08-26 08:59:08 -0400},
     pages = {4886 - 4895},
     title = {ATM: Action Temporality Modeling for Video Question Answering},
     year = {2023}
   }

3. ICCV

   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

   arXiv Bib

   @inproceedings{BaoICCV2023,
     author = {Bao, Wentao and Chen, Lele and Zeng, Libing and Li, Zhong and Xu, Yi and Yuan, Junsong and Kong, Yu},
     booktitle = {International Conference on Computer Vision (ICCV)},
     date-modified = {2024-08-26 08:56:43 -0400},
     demo = {https://www.linkedin.com/feed/update/urn:li:activity:7087460563957477377/},
     pages = {13656-13665},
     title = {Uncertainty-aware State Space Transformer for Egocentric 3D Trajectory Forecasting},
     year = {2023}
   }

4. arXiv

   An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

   Hanbin Hong, Yuan Hong, and Yu Kong

   In arXiv, 2023

   Bib

   @inproceedings{Hong2023_3,
     author = {Hong, Hanbin and Hong, Yuan and Kong, Yu},
     booktitle = {arXiv},
     title = {An Eye for an Eye: Defending against Gradient-based Attacks with Gradients},
     year = {2023}
   }

5. CVPR

   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

   arXiv Bib

   @inproceedings{LinCVPR2023,
     author = {Lin, Xinmiao and Li, Yikang and Hsiao, Jenhao and Ho, Chiu Man and Kong, Yu},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 08:53:35 -0400},
     pages = {1736-1745},
     title = {Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder},
     year = {2023}
   }

6. WACV

   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

   Bib PDF

   @inproceedings{XiwenWACV2023,
     author = {Dengxiong, Xiwen and Kong, Yu},
     booktitle = {IEEE/CVF Winter Conferences on Applications of Computer Vision (WACV)},
     date-modified = {2024-08-26 08:52:47 -0400},
     pages = {4003-4012},
     title = {Ancestor Search: Generalized Open Set Recognition via Hyperbolic Side Information Learning},
     year = {2023}
   }

2022

1. CVPR

   Learning of Global Objective for Network Flow in Multi-Object Tracking

   Shuai Li, Yu Kong, and Hamid Rezatofighi

   In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

   arXiv Bib PDF Code

   @inproceedings{LiCVPR2022,
     author = {Li, Shuai and Kong, Yu and Rezatofighi, Hamid},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 09:05:44 -0400},
     pages = {8855-8865},
     title = {Learning of Global Objective for Network Flow in Multi-Object Tracking},
     year = {2022}
   }

2. CVPR

   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

   arXiv Bib PDF

   @inproceedings{ChenCVPR2022,
     author = {Chen, Junwen and Mittal, Gaurav and Yu, Ye and Kong, Yu and Chen, Mei},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 09:03:22 -0400},
     pages = {19893-19902},
     title = {GateHUB: Gated History Unit with Background Suppression for Online Action Detection},
     year = {2022}
   }

3. CVPR

   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

   arXiv Bib PDF Code

   @inproceedings{BaoCVPR2022,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 09:02:29 -0400},
     pages = {2969-2979},
     title = {OpenTAL: Towards Open Set Temporal Action Localization},
     year = {2022}
   }

4. AAAI

   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

   arXiv Bib

   @inproceedings{KrishnaAAAI2022,
     author = {Neupane, Krishna Prasad and Zheng, Ervine and Kong, Yu and Yu, Qi},
     booktitle = {Association for the Advancement of Artificial Intelligence (AAAI)},
     date-modified = {2024-08-26 09:00:43 -0400},
     pages = {7868-7876},
     title = {A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations},
     year = {2022}
   }

5. S&P

   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

   arXiv Bib

   @inproceedings{3DPert2022,
     author = {Xie, Shangyu and Wang, Han and Kong, Yu and Hong, Yuan},
     booktitle = {IEEE Symposium on Security and Privacy (S&P)},
     date-modified = {2024-08-26 08:59:57 -0400},
     pages = {1390-1407},
     title = {Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems},
     year = {2022}
   }

6. IJCV

   Human Action Recognition and Prediction: A Survey

   Yu Kong and Yun Fu

   International Journal of Computer Vision (IJCV), 2022

   arXiv Bib PDF

   @article{KongIJCV2022,
     author = {Kong, Yu and Fu, Yun},
     journal = {International Journal of Computer Vision (IJCV)},
     number = {3},
     pages = {1366-1401},
     publisher = {Springer US},
     title = {Human Action Recognition and Prediction: A Survey},
     volume = {130},
     year = {2022}
   }

2021

1. From Ensemble Clustering to Subspace Clustering: Cluster Structure Encoding

   Zhiqiang Tao, Jun Li, Huazhu Fu, Yu Kong, and Yun Fu

   IEEE Transactions on Neural Networks and Learning Systems (T-NNLS), 2021
2. Coupling Adversarial Graph Embedding for Transductive Zero-shot Action Recognition

   Yi Tian, Yaping Huang, Wanru Xu, and Yu Kong

   Neurocomputing, 2021
3. BMVC

   Gradient Frequency Modulation for Visually Explaining Video Understanding Models

   Xinmiao Lin, Wentao Bao, and Yu Kong

   In British Machine Vision Conference (BMVC), 2021

   arXiv Bib PDF

   @inproceedings{LinBMVC2021,
     author = {Lin, Xinmiao and Bao, Wentao and Kong, Yu},
     booktitle = {British Machine Vision Conference (BMVC)},
     date-modified = {2024-08-26 09:14:05 -0400},
     pages = {1-14},
     title = {Gradient Frequency Modulation for Visually Explaining Video Understanding Models},
     year = {2021}
   }

4. ICCV

   Explainable Video Entailment with Grounded Visual Evidence

   Junwen Chen and Yu Kong

   In Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021

   Bib PDF

   @inproceedings{ChenICCV2021,
     author = {Chen, Junwen and Kong, Yu},
     booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
     date-modified = {2024-08-26 09:11:16 -0400},
     pages = {2021-2030},
     title = {Explainable Video Entailment with Grounded Visual Evidence},
     year = {2021}
   }

5. ICCV

   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

   arXiv Bib PDF Code

   @inproceedings{BaoICCV2021_2,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
     date-modified = {2024-08-26 09:10:29 -0400},
     demo = {https://www.youtube.com/watch?v=A3bTWejzUwM},
     pages = {7619-7628},
     title = {DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation},
     year = {2021}
   }

6. ICCV

   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

   arXiv Bib PDF Code

   @inproceedings{BaoICCV2021,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
     date-modified = {2024-08-26 09:09:34 -0400},
     pages = {13349-13358},
     title = {Evidential Deep Learning for Open Set Action Recognition},
     year = {2021}
   }

7. IJCNN

   Multiple Instance Relational Learning for Video Anomaly Detection

   Xiwen Dengxiong, Wentao Bao, and Yu Kong

   In International Joint Conference on Neural Networks (IJCNN), 2021

   Bib Website

   @inproceedings{DengxiongIJCNN2021,
     author = {Dengxiong, Xiwen and Bao, Wentao and Kong, Yu},
     booktitle = {International Joint Conference on Neural Networks (IJCNN)},
     date-modified = {2024-08-26 09:08:39 -0400},
     pages = {1-8},
     title = {Multiple Instance Relational Learning for Video Anomaly Detection},
     year = {2021}
   }

8. T-PAMI

   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), 2021

   Bib PDF

   @article{ZhangTPAMI2021,
     author = {Zhang, Yulun and Tian, Yapeng and Kong, Yu and Zhong, Bineng and Fu, Yun},
     journal = {IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI)},
     title = {Residual Dense Network for Image Restoration},
     year = {2021}
   }

9. T-IP

   Accurate and Fast Image Denoising via Attention Guided Scaling

   Yulun Zhang, Kunpeng Li, Kai Li, Gan Sun, Yu Kong, and Yun Fu

   IEEE Transaction on Image Processing (T-IP), 2021

   Bib PDF

   @article{ZhangTIP2021,
     author = {Zhang, Yulun and Li, Kunpeng and Li, Kai and Sun, Gan and Kong, Yu and Fu, Yun},
     date-modified = {2024-08-20 10:42:50 -0400},
     journal = {IEEE Transaction on Image Processing (T-IP)},
     pages = {6255-6265},
     title = {Accurate and Fast Image Denoising via Attention Guided Scaling},
     volume = {30},
     year = {2021}
   }

10. Revealing a History: Palimpsest Text Separation by Recreatingthe Historical Document with Generative Networks

    Anna Starynska, David Messinger, and Yu Kong

    International Journal on Document Analysis and Recognition (IJDAR), 2021

    Bib PDF

    @article{Kong2020Revealing,
      author = {Starynska, Anna and Messinger, David and Kong, Yu},
      booktitle = {arXiv},
      date-modified = {2024-08-20 11:10:18 -0400},
      journal = {International Journal on Document Analysis and Recognition (IJDAR)},
      number = {181-195},
      title = {Revealing a History: Palimpsest Text Separation by Recreatingthe Historical Document with Generative Networks},
      volume = {24},
      year = {2021}
    }

2020

1. ICPR

   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

   Bib PDF

   @inproceedings{HongICPR2020,
     author = {Hong, Hanbin and Bao, Wentao and Hong, Yuan and Kong, Yu},
     booktitle = {International Conference on Pattern Recognition (ICPR)},
     date-modified = {2024-08-26 09:22:39 -0400},
     pages = {4245-4251},
     title = {Privacy Attributes-aware Message Passing Neural Network for Visual Privacy Attributes Classification},
     year = {2020}
   }

2. 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

   Bib PDF

   @inproceedings{ChenCVPRW2020,
     author = {Chen, Junwen and Hao, Haiting and Hong, Hanbin and Kong, Yu},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop},
     dataset = {https://github.com/junwenchen/RIT-18},
     date-modified = {2024-08-26 09:21:57 -0400},
     pages = {362-363},
     title = {{RIT-18}: A Novel Dataset for Compositional Group Activity Understanding},
     year = {2020}
   }

3. IJCAI

   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

   Bib PDF

   @inproceedings{ZangIJCAI2020,
     author = {Zang, Chuanqi and Pei, Mingtao and Kong, Yu},
     booktitle = {International Joint Conference on Artificial Intelligence (IJCAI)},
     date-modified = {2024-08-26 09:21:43 -0400},
     pages = {846-852},
     title = {Few-shot Human Motion Prediction via Learning Novel Motion Dynamics},
     year = {2020}
   }

4. IROS

   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

   arXiv Bib PDF

   @inproceedings{BaoIROS2020,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
     date-modified = {2024-08-26 09:19:41 -0400},
     pages = {2197-2204},
     title = {Object-Aware Centroid Voting for Monocular 3D Object Detection},
     year = {2020}
   }

5. ECCV

   Group Activity Prediction with Sequential Relational Anticipation Model

   Junwen Chen, Wentao Bao, and Yu Kong

   In European Conference on Computer Vision (ECCV), 2020

   arXiv Bib PDF Code

   @inproceedings{ChenECCV2020,
     author = {Chen, Junwen and Bao, Wentao and Kong, Yu},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-modified = {2024-08-26 09:18:49 -0400},
     pages = {581--597},
     title = {Group Activity Prediction with Sequential Relational Anticipation Model},
     year = {2020}
   }

6. MM

   Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning

   Wentao Bao, Qi Yu, and Yu Kong

   In ACM Multimedia, 2020

   arXiv Bib Code

   @inproceedings{BaoMM2020,
     author = {Bao, Wentao and Yu, Qi and Kong, Yu},
     booktitle = {ACM Multimedia},
     dataset = {https://github.com/Cogito2012/CarCrashDataset},
     date-modified = {2024-08-26 09:18:11 -0400},
     pages = {2682-2690},
     title = {Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning},
     year = {2020}
   }

7. MM

   Activity-driven Weakly-Supervised Spatio-Temporal Grounding from Untrimmed Videos

   Junwen Chen, Wentao Bao, and Yu Kong

   In ACM Multimedia, 2020

   Bib Website

   @inproceedings{ChenMM2020,
     author = {Chen, Junwen and Bao, Wentao and Kong, Yu},
     booktitle = {ACM Multimedia},
     date-modified = {2024-08-26 09:17:03 -0400},
     pages = {3789-3797},
     title = {Activity-driven Weakly-Supervised Spatio-Temporal Grounding from Untrimmed Videos},
     year = {2020}
   }

8. EDBT

   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

   Bib PDF

   @inproceedings{KongEDBT2020,
     author = {Wang, Han and Hong, Yuan and Kong, Yu and Vaidya, Jaideep},
     booktitle = {23rd International Conference on Extending Database Technology (EDBT)},
     date-modified = {2024-08-26 09:15:49 -0400},
     pages = {323-334},
     title = {Publishing Video Data with Indistinguishable Objects},
     year = {2020}
   }

9. T-IP

   Visual Object Tracking Via Multi-Stream Deep Similarity Learning Networks

   Kunpeng Li, Yu Kong, and Yun Fu

   IEEE Transactions on Image Processing (T-IP), 2020

   Bib

   @article{LiTIP2020,
     author = {Li, Kunpeng and Kong, Yu and Fu, Yun},
     date-modified = {2024-08-24 22:50:52 -0400},
     journal = {IEEE Transactions on Image Processing (T-IP)},
     pages = {3311 - 3320},
     title = {Visual Object Tracking Via Multi-Stream Deep Similarity Learning Networks},
     volume = {29},
     year = {2020}
   }

10. T-CSVT

    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, 2020

    PDF
11. T-PAMI

    Adversarial Action Prediction Networks

    Yu Kong, Zhiqiang Tao, and Yun Fu

    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2020

    Bib PDF

    @article{KongTPAMI2018,
      author = {Kong, Yu and Tao, Zhiqiang and Fu, Yun},
      journal = {IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI)},
      number = {3},
      pages = {539 - 553},
      title = {Adversarial Action Prediction Networks},
      volume = {42},
      year = {2020}
    }

2019

1. T-CSVT

   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

   Bib PDF

   @article{JiaTCSVT2019,
     author = {Jia, Chengcheng and Ding, Zhengming and Kong, Yu and Fu, Yun},
     date-modified = {2024-08-20 10:50:41 -0400},
     journal = {IEEE Trans. Circuits and Systems for Video Technology (T-CSVT)},
     pages = {2801 - 2814},
     title = {Semi-Supervised Cross-Modality Action Recognition by Latent Tensor Transfer Learning},
     year = {2019}
   }

2. Activity Recognition

   Yu Kong and Yun Fu

   In Deep Learning through Sparse and Low-Rank Modeling, 2019

   Bib

   @incollection{KongBook3,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {Deep Learning through Sparse and Low-Rank Modeling},
     pages = {107--122},
     publisher = {Elsevier},
     title = {Activity Recognition},
     year = {2019}
   }

2018

1. Hierarchical and Spatio-Temporal Sparse Representation for Human Action Recognition

   Yi Tian, Yu Kong, Qiuqi Ruan, Gaoyun An, and Yun Fu

   IEEE Transactions on Image Processing (T-IP), 2018
2. ICDM

   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

   Bib

   @inproceedings{SunICDM2018,
     author = {Sun, Gan and Cong, Yang and Kong, Yu and Xu, Xiaowei},
     booktitle = {IEEE International Conference on Data Mining (ICDM)},
     date-modified = {2024-08-26 09:28:24 -0400},
     pages = {1248-1253},
     title = {Clustered Lifelong Learning via Representative Task Selection},
     year = {2018}
   }

3. CVPR

   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

   Bib

   @inproceedings{ZhangCVPR2018,
     author = {Zhang, Yulun and Tian, Yapeng and Kong, Yu and Zhong, Bineng and Fu, Yun},
     booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 09:27:19 -0400},
     pages = {2472-2481},
     title = {Residual Dense Network for Image Super-Resolution},
     year = {2018}
   }

4. AAAI

   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

   Bib

   @inproceedings{KongAAAI2018,
     author = {Kong, Yu and Gao, Shangqian and Sun, Bin and Fu, Yun},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     date-modified = {2024-08-26 09:25:44 -0400},
     pages = {7000-7007},
     title = {Action Prediction from Videos via Memorizing Hard-to-Predict Samples},
     year = {2018}
   }

2017

1. T-BD

   Deep Geo-constrained Auto-encoder for Non-landmark GPS Estimation

   Shuhui Jiang, Yu Kong, and Yun Fu

   IEEE Trans. Big Data, 2017

   Bib PDF

   @article{JiangTBD2017,
     author = {Jiang, Shuhui and Kong, Yu and Fu, Yun},
     date-modified = {2023-08-04 15:19:29 -0400},
     journal = {IEEE Trans. Big Data},
     number = {2},
     pages = {120--133},
     title = {Deep Geo-constrained Auto-encoder for Non-landmark GPS Estimation},
     volume = {5},
     year = {2017}
   }

2. MM

   Deep Active Learning Through Cognitive Information Parcels

   Wencang Zhao, Yu Kong, Zhengming Ding, and Yun Fu

   In ACM Multimedia, 2017

   Bib PDF

   @inproceedings{ZhaoMM2017,
     author = {Zhao, Wencang and Kong, Yu and Ding, Zhengming and Fu, Yun},
     booktitle = {ACM Multimedia},
     date-modified = {2024-08-26 09:32:21 -0400},
     pages = {952-960},
     title = {Deep Active Learning Through Cognitive Information Parcels},
     year = {2017}
   }

3. AAAI

   Sparse Subspace Clustering by Learning Approximation l0 Codes

   Jun Li, Yu Kong, and Yun Fu

   In AAAI Conference on Artificial Intelligence (AAAI), 2017

   Bib PDF

   @inproceedings{LiAAAI2017,
     author = {Li, Jun and Kong, Yu and Fu, Yun},
     booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
     date-modified = {2024-08-26 09:31:13 -0400},
     pages = {2189-2195},
     title = {Sparse Subspace Clustering by Learning Approximation l0 Codes},
     year = {2017}
   }

4. IJCAI

   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

   Bib PDF

   @inproceedings{LiIJCAI2017,
     author = {Li, Kunpeng and Kong, Yu and Fu, Yun},
     booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI)},
     date-modified = {2024-08-26 09:30:22 -0400},
     pages = {2166-2172},
     title = {Multi-Stream Deep Similarity Learning Networks for Visual Tracking},
     year = {2017}
   }

5. T-NNLS

   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

   Bib PDF

   @article{KongTNNLS2017,
     author = {Kong, Yu and Shao, Ming and Li, Kang and Fu, Yun},
     journal = {IEEE Transactions on Neural Networks and Learning Systems (T-NNLS)},
     publisher = {IEEE},
     title = {Probabilistic Low-Rank Multitask Learning},
     year = {2017}
   }

6. IJCV

   Max-Margin Heterogeneous Information Machine for RGB-D Action Recognition

   Yu Kong and Yun Fu

   International Journal of Computer Vision (IJCV), 2017

   Bib PDF

   @article{KongIJCV2017,
     author = {Kong, Yu and Fu, Yun},
     journal = {International Journal of Computer Vision (IJCV)},
     number = {3},
     pages = {350-371},
     publisher = {Springer US},
     title = {Max-Margin Heterogeneous Information Machine for RGB-D Action Recognition},
     volume = {123},
     year = {2017}
   }

7. CVPR

   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

   Bib PDF

   @inproceedings{KongCVPR2017,
     author = {Kong, Yu and Tao, Zhiqiang and Fu, Yun},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     date-modified = {2024-08-26 09:29:06 -0400},
     pages = {1473-1481},
     title = {Deep Sequential Context Networks for Action Prediction},
     year = {2017}
   }

8. T-IP

   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

   Bib PDF

   @article{KongTIP2017,
     author = {Kong, Yu and Ding, Zhengming and Li, Jun and Fu, Yun},
     journal = {IEEE Transactions on Image Processing (T-IP)},
     number = {6},
     pages = {3028--3037},
     publisher = {IEEE},
     title = {Deeply Learned View-Invariant Features for Cross-View Action Recognition},
     volume = {26},
     year = {2017}
   }

2016

1. Introduction

   Yu Kong and Yun Fu

   In Human Activity Recognition and Prediction, 2016

   Bib PDF

   @incollection{KongBook4,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {Human Activity Recognition and Prediction},
     pages = {107--122},
     publisher = {Springer},
     title = {Introduction},
     year = {2016}
   }

2. Activity Prediction

   Yu Kong and Yun Fu

   In Human Activity Recognition and Prediction, 2016

   Bib PDF

   @incollection{KongBook1,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {Human Activity Recognition and Prediction},
     pages = {107--122},
     publisher = {Springer International Publishing},
     title = {Activity Prediction},
     year = {2016}
   }

3. T-IP

   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

   Bib PDF

   @article{LiTIP2016,
     author = {Li, Jun and Kong, Yu and Zhao, Handong and Yang, Jian and Fu, Yun},
     journal = {IEEE Transactions on Image Processing (T-IP)},
     number = {10},
     pages = {4803--4814},
     publisher = {IEEE},
     title = {Learning Fast Low-Rank Projection for Image Classification},
     volume = {25},
     year = {2016}
   }

4. MM

   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

   Bib PDF

   @inproceedings{WuMM2016,
     author = {Wu, Yue and Li, Jun and Kong, Yu and Fu, Yun},
     booktitle = {Proceedings of the 2016 ACM on Multimedia Conference},
     organization = {ACM},
     pages = {1063--1067},
     title = {Deep Convolutional Neural Network with Independent Softmax for Large Scale Face Recognition},
     year = {2016}
   }

5. RGB-D Action Recognition

   Chengcheng Jia, Yu Kong, Zhengming Ding, and Yun Fu

   In Human Activity Recognition and Prediction, 2016

   Bib PDF

   @incollection{JiaBook1,
     author = {Jia, Chengcheng and Kong, Yu and Ding, Zhengming and Fu, Yun},
     booktitle = {Human Activity Recognition and Prediction},
     pages = {87--106},
     publisher = {Springer International Publishing},
     title = {RGB-D Action Recognition},
     year = {2016}
   }

6. T-BD

   Efficient Image Geotagging Using Large Databases

   Dmitry Kit, Yu Kong, and Yun Fu

   IEEE Transactions on Big Data, 2016

   Bib PDF

   @article{KitTBD2016,
     author = {Kit, Dmitry and Kong, Yu and Fu, Yun},
     journal = {IEEE Transactions on Big Data},
     number = {4},
     pages = {325--338},
     publisher = {IEEE},
     title = {Efficient Image Geotagging Using Large Databases},
     volume = {2},
     year = {2016}
   }

7. Action Recognition and Human Interaction

   Yu Kong and Yun Fu

   In Human Activity Recognition and Prediction, 2016

   Bib PDF

   @incollection{KongBook2,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {Human Activity Recognition and Prediction},
     pages = {23--48},
     publisher = {Springer International Publishing},
     title = {Action Recognition and Human Interaction},
     year = {2016}
   }

8. T-IP

   Close Human Interaction Recognition Using Patch-Aware Models

   Yu Kong and Yun Fu

   IEEE Transactions on Image Processing (T-IP), 2016

   Bib PDF

   @article{KongTIP2016a,
     author = {Kong, Yu and Fu, Yun},
     journal = {IEEE Transactions on Image Processing (T-IP)},
     number = {1},
     pages = {167--178},
     publisher = {IEEE},
     title = {Close Human Interaction Recognition Using Patch-Aware Models},
     volume = {25},
     year = {2016}
   }

9. T-IP

   Discriminative Relational Representation Learning for RGB-D Action Recognition

   Yu Kong and Yun Fu

   IEEE Transactions on Image Processing (T-IP), 2016

   Bib PDF

   @article{KongTIP2016b,
     author = {Kong, Yu and Fu, Yun},
     journal = {IEEE Transactions on Image Processing (T-IP)},
     number = {6},
     pages = {2856--2865},
     publisher = {IEEE},
     title = {Discriminative Relational Representation Learning for RGB-D Action Recognition},
     volume = {25},
     year = {2016}
   }

10. CVIU

    Learning hierarchical 3D kernel descriptors for RGB-D action recognition

    Yu Kong, Behnam Satarboroujeni, and Yun Fu

    Computer Vision and Image Understanding (CVIU), 2016

    Bib PDF

    @article{KongCVIU2016,
      author = {Kong, Yu and Satarboroujeni, Behnam and Fu, Yun},
      journal = {Computer Vision and Image Understanding (CVIU)},
      pages = {14--23},
      publisher = {Academic Press},
      title = {Learning hierarchical 3D kernel descriptors for RGB-D action recognition},
      volume = {144},
      year = {2016}
    }

11. T-PAMI

    Max-Margin Action Prediction Machine

    Yu Kong and Yun Fu

    IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI), 2016

    Bib PDF

    @article{KongTPAMI2016,
      author = {Kong, Yu and Fu, Yun},
      journal = {IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI)},
      number = {9},
      pages = {1844 - 1858},
      title = {Max-Margin Action Prediction Machine},
      volume = {38},
      year = {2016}
    }

2015

1. FG

   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

   Bib PDF

   @inproceedings{KongFG2015,
     author = {Kong, Yu and Satarboroujeni, Behnam and Fu, Yun},
     booktitle = {Automatic Face and Gesture Recognition (FG), 2015 11th IEEE International Conference and Workshops on},
     organization = {IEEE},
     pages = {1--6},
     title = {Hierarchical 3D kernel descriptors for action recognition using depth sequences},
     volume = {1},
     year = {2015}
   }

2. CVPR

   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

   Bib PDF

   @inproceedings{KongCVPR2015,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {1054-1062},
     title = {Bilinear Heterogeneous Information Machine for {RGB-D} Action Recognition},
     year = {2015}
   }

2014

1. T-PAMI

   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

   Bib PDF

   @article{KongTPAMI2014,
     author = {Kong, Yu and Jia, Yunde and Fu, Yun},
     journal = {IEEE Transaction on Pattern Analysis and Machine Intelligence (T-PAMI)},
     number = {9},
     pages = {1775-1788},
     title = {Interactive Phrases: Semantic Descriptions for Human Interaction Recognition},
     volume = {36},
     year = {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

   Bib PDF

   @article{liu2014learning,
     author = {Liu, CuiWei and Pei, MingTao and Wu, XinXiao and Kong, Yu and Jia, YunDe},
     journal = {Science China Information Sciences},
     number = {5},
     pages = {1--13},
     publisher = {Springer},
     title = {Learning a discriminative mid-level feature for action recognition},
     volume = {57},
     year = {2014}
   }

3. MM

   Latent tensor transfer learning for RGB-D action recognition

   Chengcheng Jia, Yu Kong, Zhengming Ding, and Yun Raymond Fu

   In ACM Multimedia, 2014

   Bib PDF

   @inproceedings{JiaMM2014,
     author = {Jia, Chengcheng and Kong, Yu and Ding, Zhengming and Fu, Yun Raymond},
     booktitle = {ACM Multimedia},
     pages = {87--96},
     title = {Latent tensor transfer learning for RGB-D action recognition},
     year = {2014}
   }

4. IJCNN

   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

   Bib PDF

   @inproceedings{kit2014lasom,
     author = {Kit, Dmitry and Kong, Yu and Fu, Yun},
     booktitle = {International Joint Conference on Neural Network (IJCNN)},
     date-modified = {2024-08-26 09:37:53 -0400},
     pages = {263-270},
     title = {LASOM: Location Aware Self-Organizing Map for Discovering Similar and Unique Visual Features of Geographical Locations.},
     year = {2014}
   }

5. Modeling supporting regions for close human interaction recognition

   Yu Kong and Yun Fu

   In European Conference on Computer Vision Workshop, 2014

   Bib PDF

   @inproceedings{KongECCVW2014,
     author = {Kong, Yu and Fu, Yun},
     booktitle = {European Conference on Computer Vision Workshop},
     organization = {Springer International Publishing},
     pages = {29--44},
     title = {Modeling supporting regions for close human interaction recognition},
     year = {2014}
   }

6. Recognising human interaction from videos by a discriminative model

   Yu Kong, Wei Liang, Zhen Dong, and Yunde Jia

   IET Computer Vision, 2014

   Bib

   @article{KongIETCV2014,
     author = {Kong, Yu and Liang, Wei and Dong, Zhen and Jia, Yunde},
     journal = {IET Computer Vision},
     number = {4},
     pages = {277--286},
     publisher = {IET},
     title = {Recognising human interaction from videos by a discriminative model},
     volume = {8},
     year = {2014}
   }

7. ECCV

   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

   Bib PDF

   @inproceedings{KongECCV2014,
     author = {Kong, Yu and Kit, Dmitry and Fu, Yun},
     booktitle = {European Conference on Computer Vision (ECCV)},
     date-modified = {2024-08-26 09:36:09 -0400},
     pages = {596--611},
     title = {A Discriminative Model with Multiple Temporal Scales for Action Prediction},
     year = {2014}
   }

2013

1. FG

   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

   Bib

   @inproceedings{HuFG2013,
     author = {Hu, Jie and Kong, Yu and Fu, Yun},
     booktitle = {Automatic Face and Gesture Recognition (FG), 2013 10th IEEE International Conference and Workshops on},
     organization = {IEEE},
     pages = {1--6},
     title = {Activity recognition by learning structural and pairwise mid-level features using random forest},
     year = {2013}
   }

2012

1. ICPR

   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

   Bib PDF

   @inproceedings{LiuICPR2012,
     author = {Liu, Cuiwei and Kong, Yu and Wu, Xinxiao and Jia, Yunde},
     booktitle = {Pattern Recognition (ICPR), 2012 21st International Conference on},
     organization = {IEEE},
     pages = {3366--3369},
     title = {Action recognition with discriminative mid-level features},
     year = {2012}
   }

2. BMVC

   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

   Bib PDF

   @inproceedings{YangBMVC2012,
     author = {Yang, Zhi and Kong, Yu and Fu, Yun},
     booktitle = {British Machine Vision Conference (BMVC)},
     date-modified = {2024-08-26 09:41:16 -0400},
     pages = {1--11},
     title = {Contour-HOG: A Stub Feature based Level Set Method for Learning Object Contour},
     year = {2012}
   }

3. ICPR

   Decomposed contour prior for shape recognition

   Zhi Yang, Yu Kong, and Yun Fu

   In Pattern Recognition (ICPR), 2012 21st International Conference on, 2012

   Bib PDF

   @inproceedings{yang2012decomposed,
     author = {Yang, Zhi and Kong, Yu and Fu, Yun},
     booktitle = {Pattern Recognition (ICPR), 2012 21st International Conference on},
     organization = {IEEE},
     pages = {767--770},
     title = {Decomposed contour prior for shape recognition},
     year = {2012}
   }

4. ICME

   A Hierarchical Model for Human Interaction Recognition

   Yu Kong and Yunde Jia

   In IEEE International Conference on Multimedia and Expo (ICME), 2012

   Bib PDF

   @inproceedings{KongICME2012,
     author = {Kong, Yu and Jia, Yunde},
     booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
     date-modified = {2024-08-26 09:40:07 -0400},
     pages = {1-6},
     title = {A Hierarchical Model for Human Interaction Recognition},
     year = {2012}
   }

5. ECCV

   Learning Human Interaction by Interactive Phrases

   Yu Kong, Yunde Jia, and Yun Fu

   In European Conference on Computer Vision (ECCV), 2012

   Bib PDF

   @inproceedings{KongECCV2012,
     author = {Kong, Yu and Jia, Yunde and Fu, Yun},
     booktitle = {European Conference on Computer Vision (ECCV)},
     comment = {ECCV},
     date-modified = {2024-08-26 09:39:21 -0400},
     pages = {300--313},
     title = {Learning Human Interaction by Interactive Phrases},
     year = {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

   Bib PDF

   @inproceedings{DongACPR2011,
     author = {Dong, Zhen and Kong, Yu and Liu, Cuiwei and Li, Hongdong and Jia, Yunde},
     booktitle = {Pattern Recognition (ACPR), 2011 First Asian Conference on},
     organization = {IEEE},
     pages = {77--81},
     title = {Recognizing human interaction by multiple features},
     year = {2011}
   }

2. PRL

   Adaptive learning codebook for action recognition

   Yu Kong, Xiaoqin Zhang, Weiming Hu, and Yunde Jia

   Pattern Recognition Letters, 2011

   Bib PDF

   @article{KongPRL2011,
     author = {Kong, Yu and Zhang, Xiaoqin and Hu, Weiming and Jia, Yunde},
     journal = {Pattern Recognition Letters},
     number = {8},
     pages = {1178--1186},
     publisher = {Elsevier},
     title = {Adaptive learning codebook for action recognition},
     volume = {32},
     year = {2011}
   }

2010

1. ICIP

   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

   Bib PDF

   @inproceedings{wei2010compact,
     author = {Wei, Qingdi and Zhang, Xiaoqin and Kong, Yu and Hu, Weiming and Ling, Haibin},
     booktitle = {International Conference on Image Processing (ICIP)},
     pages = {3805--3808},
     title = {Compact visual codebook for action recognition},
     year = {2010}
   }

2. A swarm intelligence based searching strategy for articulated 3D human body tracking

   Xiaoqin Zhang, Weiming Hu, Xiangyang Wang, Yu Kong, Nianhua Xie, Hanzi Wang, Haibin Ling, and 1 more author

   In IEEE Conference on Computer Vision and Pattern Recognition Workshop, 2010

   Bib PDF

   @inproceedings{ZhangCVPRW2010,
     author = {Zhang, Xiaoqin and Hu, Weiming and Wang, Xiangyang and Kong, Yu and Xie, Nianhua and Wang, Hanzi and Ling, Haibin and Maybank, Steve},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition Workshop},
     date-modified = {2024-08-20 15:37:08 -0400},
     pages = {45--50},
     title = {A swarm intelligence based searching strategy for articulated 3D human body tracking},
     year = {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

   Bib PDF

   @inproceedings{KongVSMM2010,
     author = {Kong, Yu and Zhang, Xiaoqin and Hu, Weiming and Jia, Yunde},
     booktitle = {Virtual Systems and Multimedia (VSMM), 2010 16th International Conference on},
     organization = {IEEE},
     pages = {13--20},
     title = {Learning human actions with an adaptive codebook},
     year = {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

   Bib PDF

   @inproceedings{wei2009group,
     author = {Wei, Qingdi and Zhang, Xiaoqin and Kong, Yu and Hu, Weiming and Ling, Haibin},
     booktitle = {Advances in Visual Computing},
     pages = {757--766},
     publisher = {Springer Berlin/Heidelberg},
     title = {Group action recognition using space-time interest points},
     year = {2009}
   }

2. ACCV

   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

   Bib PDF

   @inproceedings{KongACCV2009,
     author = {Kong, Yu and Hu, Weiming and Zhang, Xiaoqin and Wang, Hanzi and Jia, Yunde},
     booktitle = {Asian Conference on Computer Vision (ACCV)},
     organization = {Springer Berlin Heidelberg},
     pages = {103--112},
     title = {Learning group activity in soccer videos from local motion},
     year = {2009}
   }

2008

1. ICPR

   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

   Bib PDF

   @inproceedings{KongICPR2008,
     author = {Kong, Yu and Zhang, Xiaoqin and Wei, Qingdi and Hu, Weiming and Jia, Yunde},
     booktitle = {International Conference on Pattern Recognition (ICPR)},
     organization = {IEEE},
     pages = {1--4},
     title = {Group action recognition in soccer videos},
     year = {2008}
   }