Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation


Nov 23, 2022
Tsu-Jui Fu, Licheng Yu, Ning Zhang, Cheng-Yang Fu, Jong-Chyi Su, William Yang Wang, Sean Bell

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning


Oct 26, 2022
Suvir Mirchandani, Licheng Yu, Mengjiao Wang, Animesh Sinha, Wenwen Jiang, Tao Xiang, Ning Zhang

Add code

* 14 pages, 4 figures. To appear at Conference on Empirical Methods in Natural Language Processing (EMNLP) 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

FashionViL: Fashion-Focused Vision-and-Language Representation Learning


Jul 17, 2022
Xiao Han, Licheng Yu, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang

Add code

* ECCV 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

GEB+: A benchmark for generic event boundary captioning, grounding and text-based retrieval


Apr 10, 2022
Yuxuan Wang, Difei Gao, Licheng Yu, Stan Weixian Lei, Matt Feiszli, Mike Zheng Shou

Add code

* 24 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval


Mar 10, 2022
Jie Lei, Xinlei Chen, Ning Zhang, Mengjiao Wang, Mohit Bansal, Tamara L. Berg, Licheng Yu

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment


Mar 01, 2022
Mingyang Zhou, Licheng Yu, Amanpreet Singh, Mengjiao Wang, Zhou Yu, Ning Zhang

Add code

* First two authors contributed equally. 13 pages, 11 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval


Feb 15, 2022
Licheng Yu, Jun Chen, Animesh Sinha, Mengjiao MJ Wang, Hugo Chen, Tamara L. Berg, Ning Zhang

Add code

* 10 pages, 7 figures. Commerce Multimodal Model towards Real Applications at Facebook 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation


Jun 08, 2021
Linjie Li, Jie Lei, Zhe Gan, Licheng Yu, Yen-Chun Chen, Rohit Pillai, Yu Cheng, Luowei Zhou, Xin Eric Wang, William Yang Wang, Tamara Lee Berg, Mohit Bansal, Jingjing Liu, Lijuan Wang, Zicheng Liu

Add code

* VALUE is available at https://value-leaderboard.github.io/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Connecting What to Say With Where to Look by Modeling Human Attention Traces


May 12, 2021
Zihang Meng, Licheng Yu, Ning Zhang, Tamara Berg, Babak Damavandi, Vikas Singh, Amy Bearman

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

What is More Likely to Happen Next? Video-and-Language Future Event Prediction


Oct 15, 2020
Jie Lei, Licheng Yu, Tamara L. Berg, Mohit Bansal

Add code

* EMNLP 2020 (17 pages) 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>