@InProceedings{Hu_2023_VCIP,
  author={Shi, Huiying and Hu, Yaosi and Zhang, Yingxue and Chen, Zhenzhong},
  booktitle={2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)}, 
  title={A Lightweight No-reference Video Quality Assessment Method}, 
  year={2023},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/VCIP59821.2023.10402738}
}
                

@InProceedings{Hu_2022_CVPR,
    author    = {Hu, Yaosi and Luo, Chong and Chen, Zhenzhong},
    title     = {Make It Move: Controllable Image-to-Video Generation With Text Descriptions},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2022},
    pages     = {18219-18228}
}
                

@INPROCEEDINGS{9828647,
  author={Liu, Mengying and Joskowicz, Jose and Sotelo, Rafael and Hu, Yaosi and Chen, Zhenzhong and Yang, Lei},
  booktitle={2022 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)}, 
  title={Subjective Quality Assessment of One-to-One Video-Telephony Services}, 
  year={2022},
  volume={},
  number={},
  pages={1-6},
  doi={10.1109/BMSB55706.2022.9828647}}
                

@INPROCEEDINGS{Wu2022VCIP,
  author={Wei Wu, Yingxue Zhang, Yaosi Hu, Zhenzhong Chen, Shan Liu},
  booktitle={2022 International Conference on Visual Communications and Image Processing (VCIP)}, 
  title={Video Quality Assessment based on Quality Aggregation Networks}, 
  year={2022},
  volume={},
  number={},
  pages={}
}
                

@INPROCEEDINGS{9675397,
  author={Tao, Yiran and Hu, Yaosi and Chen, Zhenzhong},
  booktitle={2021 International Conference on Visual Communications and Image Processing (VCIP)}, 
  title={Learn to Look Around: Deep Reinforcement Learning Agent for Video Saliency Prediction}, 
  year={2021},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/VCIP53242.2021.9675397}}                
                

@INPROCEEDINGS{9675348,
  author={Zou, Cong and Wang, Xuchen and Hu, Yaosi and Chen, Zhenzhong and Liu, Shan},
  booktitle={2021 International Conference on Visual Communications and Image Processing (VCIP)}, 
  title={MAPS: Joint Multimodal Attention and POS Sequence Generation for Video Captioning}, 
  year={2021},
  volume={},
  number={},
  pages={1-5},
  doi={10.1109/VCIP53242.2021.9675348}}
                

@INPROCEEDINGS{9175555,
  author={Hu, Yaosi and Zhang, Yingxue and Liu, Zizheng and Chen, Zhenzhong and Liu, Shan},
  booktitle={2020 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)}, 
  title={Subjective Study of Perceptual Quality for Micro-Video Applications}, 
  year={2020},
  volume={},
  number={},
  pages={229-232},
  doi={10.1109/MIPR49039.2020.00054}}
                

@inproceedings{10.1145/3366423.3380004,
author = {Xie, Jiayi and Zhu, Yaochen and Zhang, Zhibin and Peng, Jian and Yi, Jing and Hu, Yaosi and Liu, Hongyi and Chen, Zhenzhong},
title = {A Multimodal Variational Encoder-Decoder Framework for Micro-Video Popularity Prediction},
year = {2020},
isbn = {9781450370233},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
doi = {10.1145/3366423.3380004},
booktitle = {Proceedings of The Web Conference 2020},
pages = {2542–2548},
numpages = {7},
location = {Taipei, Taiwan},
series = {WWW '20}
}
                

@inproceedings{10.1145/3343031.3351072,
author = {Hu, Yaosi and Chen, Zhenzhong and Zha, Zheng-Jun and Wu, Feng},
title = {Hierarchical Global-Local Temporal Modeling for Video Captioning},
year = {2019},
isbn = {9781450368896},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
doi = {10.1145/3343031.3351072},
booktitle = {Proceedings of the 27th ACM International Conference on Multimedia},
pages = {774–783},
numpages = {10},
location = {Nice, France},
series = {MM '19}
}
                

@INPROCEEDINGS{8803653,
author={Liu, Di and Hu, Yaosi and Zhang, Kao and Chen, Zhenzhong},
booktitle={2019 IEEE International Conference on Image Processing (ICIP)}, 
title={Two-Stream Refinement Network for RGB-D Saliency Detection}, 
year={2019},
volume={},
number={},
pages={3925-3929},
doi={10.1109/ICIP.2019.8803653}
}
                

@INPROCEEDINGS{8551554,
author={Hu, Yaosi and Chen, Zhenzhong and Lin, Weiyao},
booktitle={2018 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)}, 
title={RGB-D Semantic Segmentation: A Review}, 
year={2018},
volume={},
number={},
pages={1-6},
doi={10.1109/ICMEW.2018.8551554}
}
                

@article{TAO2024104185,
title = {Memory-guided representation matching for unsupervised video anomaly detection},
journal = {Journal of Visual Communication and Image Representation},
volume = {101},
pages = {104185},
year = {2024},
issn = {1047-3203},
doi = {https://doi.org/10.1016/j.jvcir.2024.104185},
url = {https://www.sciencedirect.com/science/article/pii/S1047320324001408},
author = {Yiran Tao and Yaosi Hu and Zhenzhong Chen},
}
                

@ARTICLE{10148799,
  author={Hu, Yaosi and Luo, Chong and Chen, Zhenzhong},
  journal={IEEE Transactions on Multimedia}, 
  title={A Benchmark for Controllable Text-Image-to-Video Generation}, 
  year={2023},
  volume={},
  number={},
  pages={1-14},
  doi={10.1109/TMM.2023.3284989}}
                

@article{OUYANG2023126274,
title = {Multiple visual relationship forecasting and arrangement in videos},
journal = {Neurocomputing},
volume = {541},
pages = {126274},
year = {2023},
issn = {0925-2312},
doi = {https://doi.org/10.1016/j.neucom.2023.126274},
url = {https://www.sciencedirect.com/science/article/pii/S0925231223003971},
author = {Wanping Ouyang and Yaosi Hu and Yangjun Ou and Zhenzhong Chen},
}
                

@article{HU2022103686,
title = {Decomposing style, content, and motion for videos},
journal = {Journal of Visual Communication and Image Representation},
volume = {89},
pages = {103686},
year = {2022},
issn = {1047-3203},
doi = {https://doi.org/10.1016/j.jvcir.2022.103686},
url = {https://www.sciencedirect.com/science/article/pii/S1047320322002061},
author = {Yaosi Hu and Dacheng Yin and Yuwang Wang and Zhenzhong Chen and Chong Luo}
}
                

@ARTICLE{9474501,
  author={Gutiérrez, Jesús and Pérez, Pablo and Orduna, Marta and Singla, Ashutosh and Cortés, Carlos and Mazumdar, Pramit and Viola, Irene and Brunnström, Kjell and Battisti, Federica and Cieplińska, Natalia and Juszka, Dawid and Janowski, Lucjan and Leszczuk, Mikołaj and Adeyemi-Ejeye, Anthony and Hu, Yaosi and Chen, Zhenzhong and Wallendael, Glenn Van and Lambert, Peter and Díaz, César and Hedlund, John and Hamsis, Omar and Fremerey, Stephan and Hofmeyer, Frank and Raake, Alexander and César, Pablo and Carli, Marco and García, Narciso},
  journal={IEEE Transactions on Multimedia}, 
  title={Subjective Evaluation of Visual Quality and Simulator Sickness of Short 360$^\circ$ Videos: ITU-T Rec. P.919}, 
  year={2022},
  volume={24},
  number={},
  pages={3087-3100},
  doi={10.1109/TMM.2021.3093717}}
                

@ARTICLE{9796007,
  author={Tao, Leitian and Mi, Li and Li, Nannan and Cheng, Xianhang and Hu, Yaosi and Chen, Zhenzhong},
  journal={IEEE Transactions on Image Processing}, 
  title={Predicate Correlation Learning for Scene Graph Generation}, 
  year={2022},
  volume={31},
  number={},
  pages={4173-4185},
  doi={10.1109/TIP.2022.3181511}}
                

@article{WEI2020102751,
title = {Exploiting the local temporal information for video captioning},
journal = {Journal of Visual Communication and Image Representation},
volume = {67},
pages = {102751},
year = {2020},
issn = {1047-3203},
doi = {https://doi.org/10.1016/j.jvcir.2020.102751},
author = {Ran Wei and Li Mi and Yaosi Hu and Zhenzhong Chen}
}