ENHANCING TEMPORAL SEGMENTATION BY NONLOCAL SELF-SIMILARITY - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

ENHANCING TEMPORAL SEGMENTATION BY NONLOCAL SELF-SIMILARITY

Résumé

Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing. This paper proposes a new approach to improve the temporal segmentation of photo-streams. The method consists in enhancing image representations by encoding long-range temporal dependencies. Our key contribution is to take advantage of the temporal station-arity assumption of photostreams for modeling each frame by its nonlocal self-similarity function. The proposed approach is put to test on the EDUB-Seg dataset, a standard benchmark for egocentric photostream temporal segmentation. Starting from seven different (CNN based) image features, the method yields consistent improvements in event segmentation quality , leading to an average increase of F-measure of 3.71% with respect to the state of the art.
Fichier principal
Vignette du fichier
Dimiccoli_ICIP2019.pdf (3.02 Mo) Télécharger le fichier
Loading...

Dates et versions

hal-02346583 , version 1 (07-11-2019)

Identifiants

  • HAL Id : hal-02346583 , version 1

Citer

Mariella Dimiccoli, Herwig Wendt. ENHANCING TEMPORAL SEGMENTATION BY NONLOCAL SELF-SIMILARITY. IEEE International Conference on Image Processing (ICIP), Sep 2019, Taipei, Taiwan. ⟨hal-02346583⟩
43 Consultations
61 Téléchargements

Partager

Gmail Facebook X LinkedIn More