End-to-end person search sequentially trained on aggregated dataset - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Papers Year :

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


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.
Fichier principal
Vignette du fichier
loesch.pdf (451.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

cea-03251768 , version 1 (07-06-2021)


  • 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⟩
49 View
54 Download


Gmail Facebook Twitter LinkedIn More