Re-identify people in images using multi-stage transformers with COAT

Re-identify people in images using multi-stage transformers with COAT

Cascade Transformers for End-to-End Person Search

arXiv paper abstract https://arxiv.org/abs/2203.09642v1

arXiv PDF paper https://arxiv.org/pdf/2203.09642v1.pdf

GitHub https://github.com/kitware/coat

The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions.

... propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search.

... three-stage cascade ... focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification.

At each stage the occluded attention transformer applies tighter intersection over union thresholds, forcing the network to learn coarse-to-fine pose/scale invariant features.

... calculate each detection's occluded attention to differentiate a person's tokens from other people or the background.

... demonstrate the benefits of ... method by achieving state-of-the-art performance on two benchmark datasets.

Please like and share this post if you enjoyed it using the buttons at the bottom! Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact Web site with my other posts by category https://morrislee1234.wixsite.com/website LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b #ComputerVision #Surveillance #AINewsClips #AI #ML #ArtificialIntelligence #MachineLearning