Publications

2024

1. 

   The Amazon Nova family of models: Technical report and model card

   Amazon Artificial General Intelligence

   Amazon Technical Reports, 2024

   PDF Website

2023

1. 

   Possible Worlds VQA: Cross Modality Bias Reduction in Visual Question Answering Systems from a Causal View

   Ali Vosoughi, Shijian Deng, Songyang Zhang, Yapeng Tian, Chenliang Xu, and Jiebo Luo

   In TMM, 2023

   PDF
2. arXiv

   

   Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation

   Jie An^*, Songyang Zhang^*, Harry Yang, Sonal Gupta, Jia-Bin Huang, Jiebo Luo, and Xi Yin

   arXiv preprint arXiv:2304.08477, 2023

   Bib PDF Website

   @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}
   }

2022

1. EMNLP

   

   Learning a Grammar Inducer by Watching Millions of Instructional YouTube Videos

   Songyang Zhang, Linfeng Song, Lifeng Jin, Haitao Mi, Kun Xu, Dong Yu, and Jiebo Luo

   In Conference on Empirical Methods in Natural Language Processing, 2022

   Bib PDF Code Slides

   @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}
   }

2. ICLR

   

   Make-A-Video: Text-to-video Generation without Text-Video Data

   Uriel Singer, Adam Polyak, Thomas Hayes, Xi Yin, Jie An, Songyang Zhang, Qiyuan Hu, Harry Yang, Oron Ashual, Oran Gafni, Devi Parikh, Sonal Gupta, and Yaniv Taigman

   In International Conference on Learning Representations, 2022

   Bib PDF Website

   @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}
   }

3. BMVC

   

   Rethinking the Evaluation of Unbiased Scene Graph Generation

   Xingchen Li, Long Chen, Jian Shao, Shaoning Xiao, Songyang Zhang, and Jun Xiao

   In British Machine Vision Conference, 2022

   Bib PDF Code

   @inproceedings{li2022rethinking,
     oral = {true},
     title = {Rethinking the Evaluation of Unbiased Scene Graph Generation},
     author = {Li, Xingchen and Chen, Long and Shao, Jian and Xiao, Shaoning and Zhang, Songyang and Xiao, Jun},
     booktitle = {British Machine Vision Conference},
     year = {2022}
   }

4. ECCV

   

   MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration

   Thomas Hayes^*, Songyang Zhang^*, Xi Yin, Guan Pang, Sasha Sheng, Harry Yang, Songwei Ge, Qiyuan Hu, and Devi Parikh

   In European Conference on Computer Vision, 2022

   Bib PDF Supp Code Slides Website

   @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}
   }

5. ECCV

   

   Expanding Language-Image Pretrained Models for General Video Recognition

   Bolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, and Haibin Ling

   In European Conference on Computer Vision, 2022

   Bib PDF Code

   @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}
   }

6. CVPR

   

   The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation

   Lin Li, Long Chen, Yifeng Huang, Zhimeng Zhang, Songyang Zhang, and Jun Xiao

   In IEEE Conference on Computer Vision and Pattern Recognition, 2022

   Bib PDF Code

   @inproceedings{li2022devil,
     oral = {true},
     talk = {https://www.youtube.com/watch?v=vMLPZB50Vtg},
     title = {The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation},
     author = {Li, Lin and Chen, Long and Huang, Yifeng and Zhang, Zhimeng and Zhang, Songyang and Xiao, Jun},
     booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},
     year = {2022}
   }

2021

1. ACMMM

   

   Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation

   Jiahui Li, Kun Kuang, Lin Li, Long Chen, Songyang Zhang, Jian Shao, and Jun Xiao

   In ACM International Conference on Multimedia, 2021

   Bib PDF

   @inproceedings{yang2021sat,
     title = {Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation},
     author = {Li, Jiahui and Kuang, Kun and Li, Lin and Chen, Long and Zhang, Songyang and Shao, Jian and Xiao, Jun},
     booktitle = {ACM International Conference on Multimedia},
     year = {2021}
   }

2. ICCV

   

   SAT: 2D Semantics Assisted Training for 3D Visual Grounding

   Zhengyuan Yang, Songyang Zhang, Liwei Wang, and Jiebo Luo

   In IEEE International Conference on Computer Vision, 2021

   Bib PDF Code

   @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}
   }

3. NAACL

   

   Video-aided Unsupervised Grammar Induction

   Songyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu, and Jiebo Luo

   In Conference of the North American Chapter of the Association for Computational Linguistics, 2021

   Awarded Bib PDF Code Poster Slides

   Best Long Paper Award

   @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}
   }

4. AAAI

   

   Boundary Proposal Network for Two-Stage Natural Language Video Localization

   Shaoning Xiao, Long Chen, Songyang Zhang, Wei Ji, Jian Shao, Lu Ye, and Jun Xiao

   In the AAAI Conference on Artificial Intelligence, 2021

   Bib PDF

   @inproceedings{xiao2021boundary,
     title = {Boundary Proposal Network for Two-Stage Natural Language Video Localization},
     author = {Xiao, Shaoning and Chen, Long and Zhang, Songyang and Ji, Wei and Shao, Jian and Ye, Lu and Xiao, Jun},
     booktitle = {the AAAI Conference on Artificial Intelligence},
     year = {2021}
   }

5. BigData

   

   Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos

   Songyang Zhang, Tolga Aktas, and Jiebo Luo

   In IEEE Big Data, 2021

   Bib PDF Slides

   @inproceedings{zhang2021mi,
     title = {Mi YouTube es Su YouTube? Analyzing the Cultures using YouTube Thumbnails of Popular Videos},
     author = {Zhang, Songyang and Aktas, Tolga and Luo, Jiebo},
     booktitle = {IEEE Big Data},
     year = {2021}
   }

6. TPAMI

   

   Multi-Scale 2D Temporal Adjacency Networks for Moment Localization with Natural Language

   Songyang Zhang, Houwen Peng, Jianlong Fu, Yijuan Lu, and Jiebo Luo

   IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

   Bib PDF Code

   @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}
   }

2020

1. BigData

   

   Content-based Analysis of the Cultural Differences between TikTok and Douyin

   Li Sun^*, Haoqi Zhang^*, Songyang Zhang, and Jiebo Luo

   In IEEE Big Data, 2020

   Bib PDF

   @inproceedings{sun2020content,
     title = {Content-based Analysis of the Cultural Differences between TikTok and Douyin},
     author = {Sun, Li and Zhang, Haoqi and Zhang, Songyang and Luo, Jiebo},
     booktitle = {IEEE Big Data},
     year = {2020}
   }

2. ICPR

   

   Global Image Sentiment Transfer

   Jie An, Tianlang Chen, Songyang Zhang, and Jiebo Luo

   In International Conference on Pattern Recognition, 2020

   Bib PDF

   @inproceedings{an2020global,
     news = {https://www.jiqizhixin.com/articles/2020-11-09-4},
     title = {Global Image Sentiment Transfer},
     author = {An, Jie and Chen, Tianlang and Zhang, Songyang and Luo, Jiebo},
     booktitle = {International Conference on Pattern Recognition},
     year = {2020}
   }

3. AAAI

   

   Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language

   Songyang Zhang, Houwen Peng, Jianlong Fu, and Jiebo Luo

   In the AAAI Conference on Artificial Intelligence, 2020

   Bib PDF Code Poster Slides

   @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}
   }

2019

1. arXiv

   

   Learning Sparse 2D Temporal Adjacent Networks for Temporal Action Localization

   Songyang Zhang, Houwen Peng, Le Yang, Jianlong Fu, and Jiebo Luo

   arXiv preprint arXiv:1912.03612, 2019

   Awarded Bib PDF Website

   Winner of HACS Temporal Action Localization Challenge at ICCV 2019

   @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}
   }

2. ACMMM

   

   Exploiting Temporal Relationships in Video Moment Localization with Natural Language

   Songyang Zhang, Jinsong Su, and Jiebo Luo

   In ACM International Conference on Multimedia, 2019

   Bib PDF Code Poster Slides

   @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}
   }

2018

1. TMM

   

   Fusing Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks

   Songyang Zhang, Yang Yang, Jun Xiao, Xiaoming Liu, Yi Yang, Di Xie, and Yueting Zhuang

   IEEE Transactions on Multimedia, 2018

   Bib PDF

   @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}
   }

2017

1. WACV

   

   On Geometric Features for Skeleton-Based Action Recognition Using Multilayer LSTM Networks

   Songyang Zhang, Xiaoming Liu, and Jun Xiao

   In IEEE Winter Conference on Applications of Computer Vision, 2017

   Bib PDF Code Poster Slides

   @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}
   }