We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative feature matching solution based on Reverse Nearest Neighbour and a feature forgetting strategy that detect redundant features and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information. Code will be publicly available.

Memory Based Online Learning of Deep Representations from Video Streams / Federico Pernici; Federico Bartoli; Matteo Bruni; Alberto Del Bimbo. - ELETTRONICO. - (2018), pp. 1-8. (Intervento presentato al convegno CVPR 2018).

Memory Based Online Learning of Deep Representations from Video Streams

Federico Pernici;Federico Bartoli;Matteo Bruni;Alberto Del Bimbo
2018

Abstract

We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative feature matching solution based on Reverse Nearest Neighbour and a feature forgetting strategy that detect redundant features and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams. Experimental results show that the proposed method achieves comparable results in the task of multiple face tracking and better performance in face identification with offline approaches exploiting future information. Code will be publicly available.
2018
CVPR 2018
CVPR 2018
Federico Pernici; Federico Bartoli; Matteo Bruni; Alberto Del Bimbo
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1118548
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 23
  • ???jsp.display-item.citation.isi??? 16
social impact