Our results show that (i) mistakes on background are substantial and they are responsible for 18-49% of the total error, (ii) models do not generalize well to different kinds of backgrounds and perform poorly on completely background images, and (iii) models make many more mistakes than those captured by the standard Mean Absolute Error (MAE) metric, as counting on background compensates considerably for misses on foreground.
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance.
However, current networks extract fixed representations for each image regardless of other images which are paired with it and the comparison with other images is done only at the final level.
Ranked #97 on Person Re-Identification on Market-1501
This paper addresses the problem of matching pedestrians across multiple camera views, known as person re-identification.
We model color feature generation as a learning problem by jointly learning a linear transformation and a dictionary to encode pixel values.