TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Non-parametric contextual relationship learning for semantic video object segmentation

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProgress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 23rd Iberoamerican Congress, CIARP 2018, Proceedings
ToimittajatRuben Vera-Rodriguez, Julian Fierrez, Aythami Morales
KustantajaSpringer Verlag
Sivut325-333
Sivumäärä9
ISBN (painettu)9783030134686
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIberoamerican Congress on Pattern Recognition - Madrid, Espanja
Kesto: 19 marraskuuta 201822 marraskuuta 2018

Julkaisusarja

NimiLecture Notes in Computer Science
Vuosikerta11401
ISSN (painettu)0302-9743
ISSN (elektroninen)1611-3349

Conference

ConferenceIberoamerican Congress on Pattern Recognition
MaaEspanja
KaupunkiMadrid
Ajanjakso19/11/1822/11/18

Tiivistelmä

We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal contexts to facilitate the semantic labeling of local regions. We introduce an exemplar-based nonparametric view of contextual cues, where the inherent relationships implied by object hypotheses are encoded on a similarity graph of regions. Contextual relationships learning and propagation are performed to estimate the pairwise contexts between all pairs of unlabeled local regions. Our algorithm integrates the learned contexts into a Conditional Random Field (CRF) in the form of pairwise potentials and infers the per-region semantic labels. We evaluate our approach on the challenging YouTube-Objects dataset which shows that the proposed contextual relationship model outperforms the state-of-the-art methods.

Julkaisufoorumi-taso