Songyang Zhang

@article{an2023latent,
  title = {Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation},
  author = {An, Jie and Zhang, Songyang and Yang, Harry and Gupta, Sonal and Huang, Jia-Bin and Luo, Jiebo and Yin, Xi},
  journal = {arXiv preprint arXiv:2304.08477},
  year = {2023}
}

@inproceedings{zhang2022training,
  oral = {ture},
  talk = {www.youtube.com/watch?v=7caDMC24oro},
  title = {Learning a Grammar Inducer by Watching Millions of Instructional YouTube Videos},
  author = {Zhang, Songyang and Song, Linfeng and Jin, Lifeng and Mi, Haitao and Xu, Kun and Yu, Dong and Luo, Jiebo},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2022}
}

@inproceedings{singer2022make,
  news = {https://ai.facebook.com/blog/generative-ai-text-to-video/},
  title = {Make-A-Video: Text-to-video Generation without Text-Video Data},
  author = {Singer, Uriel and Polyak, Adam and Hayes, Thomas and Yin, Xi and An, Jie and Zhang, Songyang and Hu, Qiyuan and Yang, Harry and Ashual, Oron and Gafni, Oran and Parikh, Devi and Gupta, Sonal and Taigman, Yaniv},
  booktitle = {International Conference on Learning Representations},
  year = {2022}
}

@inproceedings{hayes2022mugen,
  news = {https://ai.facebook.com/blog/introducing-mugen-a-new-dataset-for-multimodal-research/},
  talk = {https://youtu.be/it0r6Q9a1jY},
  title = {MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration},
  author = {Hayes, Thomas and Zhang, Songyang and Yin, Xi and Pang, Guan and Sheng, Sasha and Yang, Harry and Ge, Songwei and Hu, Qiyuan and Parikh, Devi},
  booktitle = {European Conference on Computer Vision},
  year = {2022}
}

@inproceedings{ni2022expanding,
  oral = {true},
  title = {Expanding Language-Image Pretrained Models for General Video Recognition},
  author = {Ni, Bolin and Peng, Houwen and Chen, Minghao and Zhang, Songyang and Meng, Gaofeng and Fu, Jianlong and Xiang, Shiming and Ling, Haibin},
  booktitle = {European Conference on Computer Vision},
  year = {2022}
}

@inproceedings{yang2021sau,
  oral = {true},
  title = {SAT: 2D Semantics Assisted Training for 3D Visual Grounding},
  author = {Yang, Zhengyuan and Zhang, Songyang and Wang, Liwei and Luo, Jiebo},
  booktitle = {IEEE International Conference on Computer Vision},
  year = {2021}
}

@inproceedings{zhang2021video,
  talk = {https://underline.io/lecture/19921-video-aided-unsupervised-grammar-induction},
  news = {https://mp.weixin.qq.com/s/bzh7lbcEzfwzRsDmOA1GsQ},
  author = {Zhang, Songyang and Song, Linfeng and Jin, Lifeng and Xu, Kun and Yu, Dong and Luo, Jiebo},
  title = {Video-aided Unsupervised Grammar Induction},
  booktitle = {Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2021}
}

@article{zhang2020multi,
  title = {Multi-Scale 2D Temporal Adjacency Networks for Moment Localization with Natural Language},
  author = {Zhang, Songyang and Peng, Houwen and Fu, Jianlong and Lu, Yijuan and Luo, Jiebo},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2021}
}

@article{zhang2019learning,
  title = {Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization},
  author = {Zhang, Songyang and Peng, Houwen and Yang, Le and Fu, Jianlong and Luo, Jiebo},
  journal = {arXiv preprint arXiv:1912.03612},
  year = {2019}
}

@inproceedings{zhang2020learning,
  news = {https://zhuanlan.zhihu.com/p/269968876},
  author = {Zhang, Songyang and Peng, Houwen and Fu, Jianlong and Luo, Jiebo},
  title = {Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language},
  booktitle = {the AAAI Conference on Artificial Intelligence},
  year = {2020}
}

@inproceedings{zhang2019exploiting,
  title = {Exploiting Temporal Relationships in Video Moment Localization with Natural Language},
  author = {Zhang, Songyang and Su, Jinsong and Luo, Jiebo},
  booktitle = {ACM International Conference on Multimedia},
  year = {2019}
}

@article{zhang2018fusing,
  title = {Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks},
  author = {Zhang, Songyang and Yang, Yang and Xiao, Jun and Liu, Xiaoming and Yang, Yi and Xie, Di and Zhuang, Yueting},
  journal = {IEEE Transactions on Multimedia},
  year = {2018}
}

@inproceedings{zhang2017geometric,
  title = {On Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks},
  author = {Zhang, Songyang and Liu, Xiaoming and Xiao, Jun},
  booktitle = {IEEE Winter Conference on Applications of Computer Vision},
  year = {2017}
}