Welcome! My name is Han Fang, I work at TeleAI （China Telecom）as a research engineer now in Beijing.

I am now working on video-text retrieval, video understanding, text-to-image generation and multimodal large language models. If you are seeking any form of academic cooperation, please feel free to email me at fanghan1996@outlook.com. We are hiring interns!

I obtained my Master’s degree in Information and Communication Engineering from BUPT in 2022 and Bachelor’s degree in Telecommunications Engineering with Management from BUPT in 2019.

My research interest includes face recognition, video/image-text understanding and text-to-image generation. I have published 10+ papers at the top international AI journals and conferences such as TMM, ECCV, ACM MM and ICME.

🔥 News

• 2024.07:  🎉🎉 One paper is accepted by ACM MM 2024.
• 2024.03:  🎉🎉 Two papers are accepted by ICME 2024 (oral presentation).
• 2023.07:  🎉🎉 Two papers are accepted by ACM MM 2023.
• 2022.12:  🎉🎉 Our paper about video-text retrieval (CLIP2Video) is accedpted by TMM 2022.

📝 Publications

TMM 2022

Transferring Image-CLIP to Video-Text Retrieval via Temporal Relations

Han Fang, Pengfei Xiong, Luhui Xu, Wenhan Luo

Project

CCBR 2022

MLFW: A Database for Face Recognition on Masked Faces

Chengrui Wang, Han Fang, Yaoyao Zhong, Weihong Deng

Dataset

• ACM MM 2024 GOAL: Grounded text-to-image Synthesis with Joint Layout Alignment Tuning, Yaqi Li, Han Fang, et al.
• ICME 2024 (Oral) ProTA: Probabilistic Token Aggregation for Text-Video Retrieval, Han Fang, et al.
• ICME 2024 (Oral) Disentangle and Denoise: Tackling Context Misalignment for Video Moment Retrieval, Kaijing Ma, Han Fang, et al.
• ICCVW 2023 Alignment and Generation Adapter for Efficient Video-text Understanding, Han Fang, et al.
• ICCVW 2023 LLaViLo: Boosting Video Moment Retrieval via Adapter-Based Multimodal Modeling, Kaijing Ma, Han Fang, et al.
• ACM MM 2023 Mask to Reconstruct: Cooperative Semantics Completion for Video-text Retrieval, Han Fang, et al.
• ACM MM 2023 A Baseline Investigation: Transformer-based Cross-view Baseline for Text-based Person Search, Xianghao Zang, Wei Gao, Ge Li, Han Fang, et al.
• TMM 2022 Transferring image-clip to video-text retrieval via temporal relations, Han Fang, et al.
• CCBR 2022 Mlfw: A database for face recognition on masked faces, ChengRui Wang, Han Fang, et al.
• FG 2021 (Oral) Augmented Face Representation Learning via Transitive Distillation, Han Fang, et al.
• TMM 2021 Dynamic training data dropout for robust deep face recognition, Yaoyao Zhong, Han Fang, et al.
• ICASSP 2021 Adaptive Re-Balancing Network with Gate Mechanism for Long-Tailed Visual Question Answering, Hongyu Chen, Ruifang Liu, Han Fang, et al.
• ECCV 2020 Generate to adapt: Resolution adaption network for surveillance face recognition, Han Fang, et al.
• CVPRW 2020 Triple-GAN: Progressive face aging with triple translation loss, Han Fang, et al.
• IGTA 2018 Semantic Segmentation of Aerial Image Using Fully Convolutional Network, Junli Yang, Yiran Jiang, Han Fang, et al.

🎖 Honors and Awards

• 2022.6 Beijing Excellent Graduate Award (Top 1%).
• 2021.12 First Class Scholarship.
• 2020.12 First Class Scholarship.
• 2019.12 First Class Scholarship.
• 2019.6 Beijing Excellent Graduate Award (Top 1%).
• 2019.5 Beijing Excellent Bachelor Dissertation Award (Top 3%).
• 2018.12 First Class Scholarship.
• 2017.12 First Class Scholarship.
• 2016.12 First Class Scholarship.

📖 Educations

• 2019.09 - 2022.06, Master, Beijing University Of Posts And Telecommunications, Beijing.
• 2015.09 - 2019.06, Undergraduate, Beijing University Of Posts And Telecommunications and Queen Mary University of London, Beijing.

💻 Internships

• 2021.03 - 2021.09, PCG, Tencent, Beijing.
• 2020.12 - 2021.02, MIG, SenseTime, Beijing.