Unverified50% confidenceFactExact time
The facial recognition introduced in Google Photos after 2017 uses deep learning models such as FaceNet, which maps faces into a 128-dimensional Euclidean space for face clustering.
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified谷歌的Best Take功能于2023年随Pixel 8系列推出，可以合成多张照片中最佳的面部表情67% similarVerifiedMediaPipe is a cross-platform machine learning framework developed by Google; its face detection module is based on the BlazeFace lightweight neural network architecture and can output 468 facial keypoint coordinates.67% similarUnverified吴恩达曾在Google Brain主导「猫脸识别」项目并创办Coursera深度学习专项课程62% similarUnverifiedGoogle has previously faced regulatory scrutiny in multiple regions over the facial recognition feature in Google Photos.60% similarUnverifiedGoogle Lens 基于卷积神经网络（CNN）与视觉Transformer架构，其核心技术来源于对比学习范式（如CLIP模型）60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/873038API
curl https://kongchang.com/api/v1/knowledge/claims/873038MCP
get_claim(id=873038)