Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)

ECCV 2018 Yifan SunLiang ZhengYi YangQi TianShengjin Wang

Employing part-level features for pedestrian image description offers fine-grained information and has been verified as beneficial for person retrieval in very recent literature. A prerequisite of part discovery is that each part should be well located... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Person Re-Identification DukeMTMC-reID PCB (RPP) Rank-1 83.3 # 13
Person Re-Identification DukeMTMC-reID PCB (RPP) MAP 69.2 # 15
Person Re-Identification DukeMTMC-reID PCB (UP) Rank-1 81.8 # 14
Person Re-Identification DukeMTMC-reID PCB (UP) MAP 66.1 # 17
Person Re-Identification Market-1501 PCB + RPP Rank-1 93.8 # 13
Person Re-Identification Market-1501 PCB + RPP MAP 81.6 # 17
Person Re-Identification Market-1501 PCB Rank-1 92.3 # 17
Person Re-Identification Market-1501 PCB MAP 77.4 # 20