Query-Guided End-To-End Person Search
| Autor: | Fabio Galasso, Sikandar Amin, Federico Tombari, Bharti Munjal |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Information retrieval Similarity (geometry) Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 020207 software engineering Context (language use) Sample (statistics) 02 engineering and technology Task (computing) Categorization End-to-end principle Margin (machine learning) computer vision machine learning detection recognition re-identification siamese deep neural networks 0202 electrical engineering electronic engineering information engineering Leverage (statistics) 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2019.00090 |
| Popis: | Person search has recently gained attention as the novel task of finding a person, provided as a cropped sample, from a gallery of non-cropped images, whereby several other people are also visible. We believe that i. person detection and re-identification should be pursued in a joint optimization framework and that ii. the person search should leverage the query image extensively (e.g. emphasizing unique query patterns). However, so far, no prior art realizes this. We introduce a novel query-guided end-to-end person search network (QEEPS) to address both aspects. We leverage a most recent joint detector and re-identification work, OIM [37]. We extend this with i. a query-guided Siamese squeeze-and-excitation network (QSSE-Net) that uses global context from both the query and gallery images, ii. a query-guided region proposal network (QRPN) to produce query-relevant proposals, and iii. a query-guided similarity subnetwork (QSimNet), to learn a query-guided reidentification score. QEEPS is the first end-to-end query-guided detection and re-id network. On both the most recent CUHK-SYSU [37] and PRW [46] datasets, we outperform the previous state-of-the-art by a large margin. Comment: Accepted as poster in CVPR 2019 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|