Publications

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. 

   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

   In Submission, 2023

   PDF Website

2022

1. 

   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

   EMNLPOral

   Bib PDF Code Slides Talk

   @inproceedings{zhang2022training,
     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. 

   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

   ICLR

   Bib PDF Website News

   @inproceedings{singer2022make,
     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. 

   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

   BMVCOral

   Bib PDF Code

   @inproceedings{li2022rethinking,
     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. 

   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

   ECCV

   Bib PDF Supp Code Slides Website Talk News

   @inproceedings{hayes2022mugen,
     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. 

   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

   ECCVOral

   Bib PDF Code

   @inproceedings{ni2022expanding,
     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. 

   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

   CVPROral

   Bib PDF Code Talk

   @inproceedings{li2022devil,
     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. 

   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

   ACMMM

   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. 

   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

   ICCVOral

   Bib PDF Code

   @inproceedings{yang2021sau,
     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. 

   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

   NAACLBest Long Paper Award

   Bib PDF Code Poster Slides Talk News

   @inproceedings{zhang2021video,
     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. 

   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

   AAAI

   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. 

   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

   BigData

   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. 

   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

   TPAMI

   Bib PDF Code

   @article{zhang2020multi,
     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. 

   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

   BigData

   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. 

   Global Image Sentiment Transfer

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

   In International Conference on Pattern Recognition, 2020

   ICPR

   Bib PDF News

   @inproceedings{an2020global,
     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. 

   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

   AAAI

   Bib PDF Code Poster Slides News

   @inproceedings{zhang2020learning,
     author = {Zhang, Songyang and Peng, Houwen and Fu, Jianlong and Luo, Jiebo},
     booktitle = {the AAAI Conference on Artificial Intelligence},
     year = {2020}
   }

2019

1. 

   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

   arXivWinner of HACS Temporal Action Localization Challenge at ICCV 2019

   Bib PDF Website

   @article{zhang2019learning,
     author = {Zhang, Songyang and Peng, Houwen and Yang, Le and Fu, Jianlong and Luo, Jiebo},
     journal = {arXiv preprint arXiv:1912.03612},
     year = {2019}
   }

2. 

   Exploiting Temporal Relationships in Video Moment Localization with Natural Language

   Songyang Zhang, Jinsong Su, and Jiebo Luo

   In ACM International Conference on Multimedia, 2019

   ACMMM

   Bib PDF Code Poster Slides

   @inproceedings{zhang2019exploiting,
     author = {Zhang, Songyang and Su, Jinsong and Luo, Jiebo},
     booktitle = {ACM International Conference on Multimedia},
     year = {2019}
   }

2018

1. 

   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

   TMM

   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. 

   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

   WACV

   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}
   }