Hao Zhu ("朱昊" in Chinese)

Hao Zhu is currently researcher at SenseTime Research, where he works on AIGC and Neural Rendering.

He received his master degree from Anhui University and is also a joint master student at CRIPAC, CASIA, supervised by Prof. Ran He and Prof. Aihua Zheng.

Please feel free to contact me through email if you have any questions.

Email  /  Google Scholar  /  Github

profile photo

[Mar 2023] 1 paper was accepted by CVPR 2023.

[Jul 2022] 1 paper was accepted by ECCV 2022.

[Jul 2021] Join SenseTime as a fulltime researcher working on generative models and neural rendering. If you are interested in a research internship position, please contact us.

[Oct 2020] 1 paper on face swapping was accepted by NeurIPS 2020.

[Mar 2020] 1 paper on talking face was accepted by IJCAI 2020.

[Sep 2018] Start my graduate study and research at Anhui University and CRIPAC CASIA.

Selected Publications [full list]

I'm interested in machine learning, computer vision, and neural rendering. Much of my research is about high-quality generative models.

CelebV-Text: A large-scale facial text-video datase
Jianhui Yu*, Hao Zhu*, Liming Jiang, Chen Change Loy, Weidong Cai, Wayne Wu
CVPR, 2023
Project Page / Dataset / arXiv

A rich and high relavance text and facial video dataset containing 70,000 video clips.

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
Hao Zhu*, Wayne Wu*, Wentao Zhu, Liming Jiang, Siwei Tang, Li Zhang, Ziwei Liu, and Chen Change Loy
ECCV, 2022
Project Page / Dataset / arXiv

A large-scale, high-quality, and diverse video dataset with rich facial attribute annotations. CelebV-HQ contains 35,666 video clips with the resolution of 512x512 at least. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion.

Deep audio-visual learning: A survey
Hao Zhu, Mandi Luo, Rui Wang, Aihua Zheng, and Ran He
IJAC, 2021

we provide a comprehensive survey of recent audio-visual learning development.

AOT: Appearance Optimal Transport Based Identity Swapping for Forgery Detection
Hao Zhu* Chaoyou Fu*, Qianyi Wu, Wayne Wu, Chen Qian, and Ran He
NeurIPS, 2020
project page / Code & Dataset / arXiv

A new identity swapping algorithm with large differences in appearance for forgery detection.

Arbitrary Talking Face Generation via Attentional Audio-visual Coherence Learning
Hao Zhu, Huaibo Huang, Yi Li, Aihua Zheng, and Ran He
IJCAI, 2020

A novel arbitrary talking face generation framework by discovering the audio-visual coherence via the proposed Asymmetric Mutual Information Estimator (AMIE).


ACF Outstanding Master's Thesis. 2021

Outstanding Master's Graduate, Anhui Province, China. 2021

National Scholarship, AHU. 2020.

Template credits: Jon Barron