Tampere University of Technology

TUTCRIS Research Portal

Non-parametric contextual relationship learning for semantic video object segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Original languageEnglish
Title of host publicationProgress in Pattern Recognition, Image Analysis, Computer Vision, and Applications - 23rd Iberoamerican Congress, CIARP 2018, Proceedings
EditorsRuben Vera-Rodriguez, Julian Fierrez, Aythami Morales
PublisherSpringer Verlag
Number of pages9
ISBN (Print)9783030134686
Publication statusPublished - 2019
Publication typeA4 Article in a conference publication
EventIberoamerican Congress on Pattern Recognition - Madrid, Spain
Duration: 19 Nov 201822 Nov 2018

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceIberoamerican Congress on Pattern Recognition


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.

Publication forum classification

Field of science, Statistics Finland