Publication and Pre-prints

Selected publications and pre-prints. For full list of publications refer to:  Google Scholar

SEED: Self-supervised Distillation For Visual Representation

Zhiyuan Fang, Jianfeng Wang, Lijuan Wang, Lei Zhang, Yezhou Yang and Zicheng Liu

International Conference on Learning Representations (ICLR), 2021

[BibTex]  [arXiv (pdf)]  [Code]

ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language

Zhe Wang, Zhiyuan Fang, Jun Wang, and Yezhou Yang

Conference on European Conference On Computer Vision (ECCV), 2020

[BibTex]  [arXiv (pdf)]  [Code]

Range Loss for Deep Face Recognition with Long-tailed Training Data

Xiao Zhang, Zhiyuan Fang, Yandong Wen, Zhifeng Li and Yu Qiao

Proceedings of the International Conference on Computer Vision (ICCV), 2017

[BibTex]  [arXiv (pdf)] 

Video2commonsense: Generating Commonsense Descriptions to Enrich Video Captioning

Zhiyuan Fang, Tejas Gokhale, Pratyay Banerjee, Chitta Baral, and Yezhou Yang

Empirical Methods in Natural Language Processing (EMNLP), 2020

[BibTex]  [arXiv (pdf)]  [Code]

Injecting Semantic Concepts into End-to-End Image Captioning

Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu, Lin Liang, Zhe Gan, Lijuan Wang, Yezhou Yang, Zicheng Liu

Conference on Computer Vision and Pattern Recognition (CVPR) 2022


[BibTex]  [arXiv (pdf)]  [Code]

Compressing Visual-linguistic Model via Knowledge Distillation

Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu, Lijuan Wang, Yezhou Yang, and Zicheng Liu

Proceedings of the International Conference on Computer Vision (ICCV), 2021

[BibTex]  [arXiv (pdf)] 

Modularized Textual Grounding for Counterfactual Resilience

Zhiyuan Fang, Shu Kong, Charless Fowlkes, and Yezhou Yang

Conference on Computer Vision and Pattern Recognition (CVPR) 2019

[BibTex]  [arXiv (pdf)] [Code]

End-to-end Knowledge Retrieval with Multi-modal Queries

Man Luo, Zhiyuan Fang, Tejas Gokhale, Yezhou Yang, Chitta Baral


The 61st Annual Meeting of the Association for Computational Linguistics (ACL) 2023

[BibTex]  [arXiv (pdf)] [Code]