Sapiensid
No description available
Install / Use
/learn @mk-minchul/SapiensidREADME
SapiensID
SapiensID is an official repository for SapiensID: Foundation for Human Recognition CVPR 2025 (https://arxiv.org/pdf/2504.04708).
@inproceedings{kim2025sapiensid,
title={SapiensID: Foundation for Human Recognition},
author={Kim, Minchul and Ye, Dingqiang and Su, Yiyang and Liu, Feng and Liu, Xiaoming},
booktitle={CVPR},
year={2025}
}
There are two main components:
- SapiensID: modeling
- WebBody: dataset
SapiensID
The core modeling and evaluation framework that provides:
- Person re-identification models and pipelines
- Pretrained models included
- Comprehensive evaluation on multiple datasets including:
- PRCC
- WebBody
- Market-1501
- MSMT17
- LTCC
- CelebReID
- DeepChange
- CCDA
- CCVID
- (we provide code for creating validation sets for each dataset but do not distribute the datasets)
- Support for both single and multi-GPU evaluation
- Feature extraction and metric computation
- Model training and inference pipelines
Refer to tasks/sapiensID/README.md for more details.
WebBody
A dataset creation and management tool that:
- Downloads and processes images from web sources
- Handles image resizing and quality control
- Manages data organization and storage
- Supports parallel processing for large-scale dataset creation
- Integrates with wandb for monitoring download progress
Refer to WebBody/README.md for more details.
Related Skills
node-connect
349.0kDiagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps
frontend-design
109.4kCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
openai-whisper-api
349.0kTranscribe audio via OpenAI Audio Transcriptions API (Whisper).
qqbot-media
349.0kQQBot 富媒体收发能力。使用 <qqmedia> 标签,系统根据文件扩展名自动识别类型(图片/语音/视频/文件)。
