# Pedestrian Detection aided by Deep Learning Semantic Tasks

Yonglong TianPing LuoXiaogang WangXiaoou Tang

Deep learning methods have achieved great success in pedestrian detection, owing to its ability to learn features from raw pixels. However, they mainly capture middle-level representations, such as pose of pedestrian, but confuse positive with hard negative samples, which have large ambiguity, e.g. the shape and appearance of tree trunk' or wire pole' are similar to pedestrian in certain viewpoint... (read more)

PDF Abstract

No code implementations yet. Submit your code now