TikTok's AI advancements: from depth perception to generative avatars.
TL;DR Summary
Researchers are using TikTok dances and the Mannequin Challenge to train AI for computer vision. The diversity of movement, clothing types, backgrounds, and people in TikTok datasets provide "ground truth" real-world examples that can be used to train or grade AI on its guesses. The Mannequin Challenge also provides more real-world data for AI training than researchers could have hoped for.
Topics:technology#ai-training#artificial-intelligence#computer-vision#mannequin-challenge#real-world-data#tiktok
- How TikTok dances trained AI to perceive depth Vox.com
- Leak: TikTok is launching generative AI avatars, and here's what they look like The Verge
- TikTok is testing a new option to create AI-generated avatars for profile pictures CNN
- TikTok is testing an in-app tool that creates generative AI avatars TechCrunch
- TikTok Adds AI Avatar Generation Feature Gizmodo
Reading Insights
Total Reads
0
Unique Readers
0
Time Saved
1 min
vs 1 min read
Condensed
66%
178 → 61 words
Want the full story? Read the original article
Read on Vox.com