CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

By Haoning Zhu, Wayne Wu, Wentao Zhu, Liming Jiang, Siwei Tang, Li Zhang, Ziwei Liu, Chen Change Loy. European Conference on Computer Vision, 2022

325 citations recorded by the source corpus.

Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields. However, the academic community still lacks a video dataset with diverse facial attribute annotations, which is crucial for the research on face-related videos. In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset (CelebV-HQ). CelebV-HQ contains 35,666 video clips with the resolution of 512x512 at least, involving 15,653 identities. All clips are labeled manually with 83 facial attributes, covering appearance, action, and emotion. We conduct a comprehensive analysis in terms of age, ethnicity, brightness stability, motion smoothness, head pose diversity, and data quality to demonstrate the diversity and temporal coherence of CelebV-HQ. Besides, its versatility and potential are validated on two representative tasks, i.e., unconditional video generation and video facial attribute editing. Furthermore, we envision the future potential of CelebV-HQ, as well as the new opportunities and challenges it would bring to related research directions. Data, code, and models are publicly available. Project page: https://celebv-hq.github.io.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6c6c996ba34fc02d00bc945b8d5c49807a3a552c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Kepan Nan
2. Xiang Li
3. Ying Tai
4. Rui Xie
5. Tiehan Fan
6. Zhenheng Yang
7. Jian Yang
8. Penghao Zhou

Citations in the corpus

• OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation (2024, methodology): “OpenVid - 1M is curated from ChronoMagic, CelebvHQ [26], Open-Sora-plan [3] and Panda 3 .”