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, ...
CelebV-HQ Follow CelebV-HQ Follow 10 followers · 0 following Achievements x2Block or Report Earned achievements Starstruck x2 Footer © 2025 GitHub, Inc. Footer navigation Terms Privacy Security Status Docs Contact Manage cookies Do not share my personal information ...
Breadcrumbs CelebV-HQ / README.mdTop File metadata and controls Preview Code Blame 157 lines (120 loc) · 7.56 KB Raw CelebV-HQ: A Large-Scale Video Facial Attributes Dataset (ECCV 2022) CelebV-HQ: A Large-Scale Video Facial Attributes Dataset Hao Zhu*, Wayne Wu*, Wentao Zhu, Liming...
You agree not to further copy, publish or distribute any portion of the CelebV-HQ dataset. Except, for internal use at a single site within the same organization it is allowed to make copies of the dataset. Download TL;DR: Thisissueis helpful. ...
I have downloaded and processed the video into 35,666 clips (~40GB). Since the timestamps provided by the author in the json file are in seconds, this caused a "scene change" problem in some clips. I further used the scenedetect tool to ...
History for CelebV-HQ README.md onmain User selector All users DatepickerAll time Commit History End of commit history for this fileFooter © 2025 GitHub, Inc. Footer navigation Terms Privacy Security Status Docs Contact Manage cookies Do not share my personal information ...