TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Graph-boosted attentive network for semantic body parsing

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoArtificial Neural Networks and Machine Learning – ICANN 2019
AlaotsikkoImage Processing - 28th International Conference on Artificial Neural Networks, 2019, Proceedings
ToimittajatIgor V. Tetko, Pavel Karpov, Fabian Theis, Vera Kurková
KustantajaSpringer Verlag
Sivut267-280
ISBN (painettu)9783030305079
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaInternational Conference on Artificial Neural Networks - Munich, Saksa
Kesto: 17 syyskuuta 201919 syyskuuta 2019

Julkaisusarja

NimiLecture Notes in Computer Science
Vuosikerta11729
ISSN (painettu)0302-9743
ISSN (elektroninen)1611-3349

Conference

ConferenceInternational Conference on Artificial Neural Networks
MaaSaksa
KaupunkiMunich
Ajanjakso17/09/1919/09/19

Tiivistelmä

Human body parsing remains a challenging problem in natural scenes due to multi-instance and inter-part semantic confusions as well as occlusions. This paper proposes a novel approach to decomposing multiple human bodies into semantic part regions in unconstrained environments. Specifically we propose a convolutional neural network (CNN) architecture which comprises of novel semantic and contour attention mechanisms across feature hierarchy to resolve the semantic ambiguities and boundary localization issues related to semantic body parsing. We further propose to encode estimated pose as higher-level contextual information which is combined with local semantic cues in a novel graphical model in a principled manner. In this proposed model, the lower-level semantic cues can be recursively updated by propagating higher-level contextual information from estimated pose and vice versa across the graph, so as to alleviate erroneous pose information and pixel level predictions. We further propose an optimization technique to efficiently derive the solutions. Our proposed method achieves the state-of-art results on the challenging Pascal Person-Part dataset.

Julkaisufoorumi-taso