Skip to Main content Skip to Navigation
Conference papers

End-to-end person search sequentially trained on aggregated dataset

Abstract : In video surveillance applications, person search is a challenging task consisting in detecting people and extracting features from their silhouette for re-identification (re-ID) purpose. We propose a new end-to-end model that jointly computes detection and feature extraction steps through a single deep Convolutional Neural Network architecture. Sharing feature maps between the two tasks for jointly describing people commonalities and specificities allows faster runtime, which is valuable in real-world applications. In addition to reaching state-of-the-art accuracy, this multi-task model can be sequentially trained task-by-task, which results in a broader acceptance of input dataset types. Indeed, we show that aggregating more pedestrian detection datasets without costly identity annotations makes the shared feature maps more generic, and improves re-ID precision. Moreover, these boosted shared feature maps result in re-ID features more robust to a cross-dataset scenario.
Complete list of metadata
Contributor : Angelique Loesch Connect in order to contact the contributor
Submitted on : Monday, June 7, 2021 - 12:08:29 PM
Last modification on : Saturday, February 19, 2022 - 3:13:47 AM
Long-term archiving on: : Wednesday, September 8, 2021 - 6:38:57 PM


Files produced by the author(s)


  • HAL Id : cea-03251768, version 1


Angelique Loesch, Jaonary Rabarisoa, Romaric Audigier. End-to-end person search sequentially trained on aggregated dataset. ICIP 2019 - 2019 IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. ⟨cea-03251768⟩



Record views


Files downloads