Context-Aware Crowd Counting

CVPR 2019 Weizhe LiuMathieu SalzmannPascal Fua

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. They typically use the same filters over the whole image or over large image patches... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Crowd Counting ShanghaiTech A CAN MAE 62.3 # 2
Crowd Counting ShanghaiTech B CAN MAE 7.8 # 2
Crowd Counting UCF CC 50 CAN MAE 212.2 # 2
Crowd Counting UCF-QNRF CAN MAE 107 # 1
Crowd Counting Venice ECAN MAE 20.5 # 1
Crowd Counting Venice CAN MAE 23.5 # 2
Crowd Counting WorldExpo’10 CAN Average MAE 7.4 # 2
Crowd Counting WorldExpo’10 ECAN Average MAE 7.2 # 1