Tampere University of Technology

TUTCRIS Research Portal

Cross-granularity graph inference for semantic video object segmentation

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

Details

Original languageEnglish
Title of host publication26th International Joint Conference on Artificial Intelligence, IJCAI 2017
Pages4544-4550
Number of pages7
ISBN (Electronic)9780999241103
Publication statusPublished - 2017
Publication typeA4 Article in a conference publication
EventINTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE -
Duration: 1 Jan 1900 → …

Publication series

Name
ISSN (Electronic)1045-0823

Conference

ConferenceINTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
Period1/01/00 → …

Abstract

We address semantic video object segmentation via a novel cross-granularity hierarchical graphical model to integrate tracklet and object proposal reasoning with superpixel labeling. Tracklet characterizes varying spatial-temporal relations of video object which, however, quite often suffers from sporadic local outliers. In order to acquire highquality tracklets, we propose a transductive inference model which is capable of calibrating shortrange noisy object tracklets with respect to longrange dependencies and high-level context cues. In the center of this work lies a new paradigm of semantic video object segmentation beyond modeling appearance and motion of objects locally, where the semantic label is inferred by jointly exploiting multi-scale contextual information and spatialtemporal relations of video object. We evaluate our method on two popular semantic video object segmentation benchmarks and demonstrate that it advances the state-of-the-art by achieving superior accuracy performance than other leading methods.

ASJC Scopus subject areas

Publication forum classification

Field of science, Statistics Finland