Pose-driven Deep Convolutional Model for Person Re-identification

TL;DR

This paper introduces a pose-driven deep convolutional model for person re-identification that leverages human part cues and adaptive feature fusion to handle pose variations and improve matching accuracy.

Contribution

It proposes an end-to-end deep architecture that explicitly uses human part cues and a pose-driven feature weighting network for robust feature extraction and matching.

Findings

Significant performance improvements over state-of-the-art methods.

Effective handling of pose variations and view changes.

Robust feature representations from global and local parts.

Abstract

Feature extraction and matching are two crucial components in person Re-Identification (ReID). The large pose deformations and the complex view variations exhibited by the captured person images significantly increase the difficulty of learning and matching of the features from person images. To overcome these difficulties, in this work we propose a Pose-driven Deep Convolutional (PDC) model to learn improved feature extraction and matching models from end to end. Our deep architecture explicitly leverages the human part cues to alleviate the pose variations and learn robust feature representations from both the global image and different local parts. To match the features from global human body and local body parts, a pose driven feature weighting sub-network is further designed to learn adaptive feature fusions. Extensive experimental analyses and results on three popular datasets demonstrate significant performance improvements of our model over all published state-of-the-art methods.