Journal
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 2285-2294Publisher
IEEE
DOI: 10.1109/CVPR.2018.00243
Keywords
-
Categories
Funding
- China Scholarship Council
- Royal Society Newton Advanced Fellowship Programme [NA150459]
- InnovateUK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for Public Safety
- Vision Semantics Ltd
Ask authors/readers for more resources
Existing person re-identification (re-id) methods either assume the availability of well-aligned person bounding box images as model input or rely on constrained attention selection mechanisms to calibrate misaligned images. They are therefore sub-optimal for re-id matching in arbitrarily aligned person images potentially with large human pose variations and unconstrained auto-detection errors. In this work, we show the advantages of jointly learning attention selection and feature representation in a Convolutional Neural Network (CNN) by maximising the complementary information of different levels of visual attention subject to re-id discriminative learning constraints. Specifically, we formulate a novel Harmonious Attention CNN (HA-CNN) model for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images. Extensive comparative evaluations validate the superiority of this new HACNN model for person re-id over a wide variety of state-of-the-art methods on three large-scale benchmarks including CUHK03, Market-1501, and DukeMTMC-ReID.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available