Pose-driven Deep Convolutional Model for Person Re-identification
This work improves person re-identification for surveillance and security applications, but it is incremental as it builds on existing deep learning approaches with pose-driven enhancements.
The paper tackles the problem of person re-identification by addressing pose deformations and view variations, proposing a Pose-driven Deep Convolutional model that uses human part cues to learn robust features, achieving significant performance improvements on three datasets.
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.