Active object detection on graphs via locally informative trees

Daphney Stavroula Zois, Maxim Raginsky

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Active object detection refers to the problem of determining the existence and location of objects in an image by actively selecting which regions of the image to explore. Herein, an object detection algorithm is proposed that models image regions as vertices and overlap relationships as edges in a directed weighted graph. Information is propagated from labeled vertices through graph edges that operate as noisy channels via message passing over locally informative trees that are extracted from the original graph using an information-theoretic criterion. Influential vertices are determined by an appropriate centrality index. Our algorithm can be applied on top of any state-of-the-art region proposal method as it treats it as a black box. The effectiveness of the proposed algorithm is illustrated on different scenarios, where in some cases only 0.45% of the total regions is evaluated.

Original languageEnglish (US)
Title of host publication2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings
EditorsKostas Diamantaras, Aurelio Uncini, Francesco A. N. Palmieri, Jan Larsen
PublisherIEEE Computer Society
ISBN (Electronic)9781509007462
DOIs
StatePublished - Nov 8 2016
Event26th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings - Vietri sul Mare, Salerno, Italy
Duration: Sep 13 2016Sep 16 2016

Publication series

NameIEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume2016-November
ISSN (Print)2161-0363
ISSN (Electronic)2161-0371

Other

Other26th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings
CountryItaly
CityVietri sul Mare, Salerno
Period9/13/169/16/16

Fingerprint

Directed graphs
Message passing
Object detection

Keywords

  • active object detection
  • degree centrality
  • graphs
  • locally informative trees
  • mutual information

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing

Cite this

Zois, D. S., & Raginsky, M. (2016). Active object detection on graphs via locally informative trees. In K. Diamantaras, A. Uncini, F. A. N. Palmieri, & J. Larsen (Eds.), 2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings [7738876] (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2016-November). IEEE Computer Society. https://doi.org/10.1109/MLSP.2016.7738876

Active object detection on graphs via locally informative trees. / Zois, Daphney Stavroula; Raginsky, Maxim.

2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings. ed. / Kostas Diamantaras; Aurelio Uncini; Francesco A. N. Palmieri; Jan Larsen. IEEE Computer Society, 2016. 7738876 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zois, DS & Raginsky, M 2016, Active object detection on graphs via locally informative trees. in K Diamantaras, A Uncini, FAN Palmieri & J Larsen (eds), 2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings., 7738876, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2016-November, IEEE Computer Society, 26th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings, Vietri sul Mare, Salerno, Italy, 9/13/16. https://doi.org/10.1109/MLSP.2016.7738876
Zois DS, Raginsky M. Active object detection on graphs via locally informative trees. In Diamantaras K, Uncini A, Palmieri FAN, Larsen J, editors, 2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings. IEEE Computer Society. 2016. 7738876. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). https://doi.org/10.1109/MLSP.2016.7738876
Zois, Daphney Stavroula ; Raginsky, Maxim. / Active object detection on graphs via locally informative trees. 2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings. editor / Kostas Diamantaras ; Aurelio Uncini ; Francesco A. N. Palmieri ; Jan Larsen. IEEE Computer Society, 2016. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).
@inproceedings{052a09459bb34cd4a41265a3a6047337,
title = "Active object detection on graphs via locally informative trees",
abstract = "Active object detection refers to the problem of determining the existence and location of objects in an image by actively selecting which regions of the image to explore. Herein, an object detection algorithm is proposed that models image regions as vertices and overlap relationships as edges in a directed weighted graph. Information is propagated from labeled vertices through graph edges that operate as noisy channels via message passing over locally informative trees that are extracted from the original graph using an information-theoretic criterion. Influential vertices are determined by an appropriate centrality index. Our algorithm can be applied on top of any state-of-the-art region proposal method as it treats it as a black box. The effectiveness of the proposed algorithm is illustrated on different scenarios, where in some cases only 0.45{\%} of the total regions is evaluated.",
keywords = "active object detection, degree centrality, graphs, locally informative trees, mutual information",
author = "Zois, {Daphney Stavroula} and Maxim Raginsky",
year = "2016",
month = "11",
day = "8",
doi = "10.1109/MLSP.2016.7738876",
language = "English (US)",
series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",
publisher = "IEEE Computer Society",
editor = "Kostas Diamantaras and Aurelio Uncini and Palmieri, {Francesco A. N.} and Jan Larsen",
booktitle = "2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings",

}

TY - GEN

T1 - Active object detection on graphs via locally informative trees

AU - Zois, Daphney Stavroula

AU - Raginsky, Maxim

PY - 2016/11/8

Y1 - 2016/11/8

N2 - Active object detection refers to the problem of determining the existence and location of objects in an image by actively selecting which regions of the image to explore. Herein, an object detection algorithm is proposed that models image regions as vertices and overlap relationships as edges in a directed weighted graph. Information is propagated from labeled vertices through graph edges that operate as noisy channels via message passing over locally informative trees that are extracted from the original graph using an information-theoretic criterion. Influential vertices are determined by an appropriate centrality index. Our algorithm can be applied on top of any state-of-the-art region proposal method as it treats it as a black box. The effectiveness of the proposed algorithm is illustrated on different scenarios, where in some cases only 0.45% of the total regions is evaluated.

AB - Active object detection refers to the problem of determining the existence and location of objects in an image by actively selecting which regions of the image to explore. Herein, an object detection algorithm is proposed that models image regions as vertices and overlap relationships as edges in a directed weighted graph. Information is propagated from labeled vertices through graph edges that operate as noisy channels via message passing over locally informative trees that are extracted from the original graph using an information-theoretic criterion. Influential vertices are determined by an appropriate centrality index. Our algorithm can be applied on top of any state-of-the-art region proposal method as it treats it as a black box. The effectiveness of the proposed algorithm is illustrated on different scenarios, where in some cases only 0.45% of the total regions is evaluated.

KW - active object detection

KW - degree centrality

KW - graphs

KW - locally informative trees

KW - mutual information

UR - http://www.scopus.com/inward/record.url?scp=85002142074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002142074&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2016.7738876

DO - 10.1109/MLSP.2016.7738876

M3 - Conference contribution

AN - SCOPUS:85002142074

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2016 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2016 - Proceedings

A2 - Diamantaras, Kostas

A2 - Uncini, Aurelio

A2 - Palmieri, Francesco A. N.

A2 - Larsen, Jan

PB - IEEE Computer Society

ER -