Develop/Python1 인물특징+색상 관련 VLM-PAR PyTorch 구현 https://arxiv.org/abs/2512.22217 VLM-PAR: A Vision Language Model for Pedestrian Attribute RecognitionPedestrian Attribute Recognition (PAR) involves predicting fine-grained attributes such as clothing color, gender, and accessories from pedestrian imagery, yet is hindered by severe class imbalance, intricate attribute co-dependencies, and domain shifts. Warxiv.org 2025년 12월에 발표된 VLM-PAR 논문은 Sig.. 2026. 3. 27. 이전 1 다음