Object instance search in videos

Jingjing Meng; Junsong Yuan; Gang Wang; Jianbo Xu

doi:10.1109/ICICS.2013.6782862

Object instance search in videos

Jingjing Meng
, Junsong Yuan
, Gang Wang
, Jianbo Xu

Department of Computer Science and Engineering

Nanyang Technological University
Hunan University of Science and Technology

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

In this paper, we propose a novel approach for object instance search in videos. Employing discriminative mutual information score and inferring the location of target object centers from matched local feature descriptors using Hough voting, we achieve robust matching and per-frame localization despite orientation and scale variations. We then leverage Max-Path search [1] to efficiently find the globally optimal spatio-temporal trajectory of the object center in each video sequence. Experimental results on a collection of mobile-captured videos in real-world environments demonstrate the effectiveness and accuracy of our method.

Original language	English
DOIs	https://doi.org/10.1109/ICICS.2013.6782862
State	Published - 2013
Event	9th International Conference on Information, Communications and Signal Processing, ICICS 2013 - Tainan, Taiwan, Province of China Duration: Dec 10 2013 → Dec 13 2013

Conference

Conference	9th International Conference on Information, Communications and Signal Processing, ICICS 2013
Country/Territory	Taiwan, Province of China
City	Tainan
Period	12/10/13 → 12/13/13

Access to Document

10.1109/ICICS.2013.6782862

Cite this

@conference{8751d205fe964658a5b4819cc7a1505b,

title = "Object instance search in videos",

abstract = "In this paper, we propose a novel approach for object instance search in videos. Employing discriminative mutual information score and inferring the location of target object centers from matched local feature descriptors using Hough voting, we achieve robust matching and per-frame localization despite orientation and scale variations. We then leverage Max-Path search [1] to efficiently find the globally optimal spatio-temporal trajectory of the object center in each video sequence. Experimental results on a collection of mobile-captured videos in real-world environments demonstrate the effectiveness and accuracy of our method.",

author = "Jingjing Meng and Junsong Yuan and Gang Wang and Jianbo Xu",

year = "2013",

doi = "10.1109/ICICS.2013.6782862",

language = "English",

note = "9th International Conference on Information, Communications and Signal Processing, ICICS 2013 ; Conference date: 10-12-2013 Through 13-12-2013",

}

TY - CONF

T1 - Object instance search in videos

AU - Meng, Jingjing

AU - Yuan, Junsong

AU - Wang, Gang

AU - Xu, Jianbo

PY - 2013

Y1 - 2013

N2 - In this paper, we propose a novel approach for object instance search in videos. Employing discriminative mutual information score and inferring the location of target object centers from matched local feature descriptors using Hough voting, we achieve robust matching and per-frame localization despite orientation and scale variations. We then leverage Max-Path search [1] to efficiently find the globally optimal spatio-temporal trajectory of the object center in each video sequence. Experimental results on a collection of mobile-captured videos in real-world environments demonstrate the effectiveness and accuracy of our method.

AB - In this paper, we propose a novel approach for object instance search in videos. Employing discriminative mutual information score and inferring the location of target object centers from matched local feature descriptors using Hough voting, we achieve robust matching and per-frame localization despite orientation and scale variations. We then leverage Max-Path search [1] to efficiently find the globally optimal spatio-temporal trajectory of the object center in each video sequence. Experimental results on a collection of mobile-captured videos in real-world environments demonstrate the effectiveness and accuracy of our method.

UR - https://www.scopus.com/pages/publications/84899116759

U2 - 10.1109/ICICS.2013.6782862

DO - 10.1109/ICICS.2013.6782862

M3 - Paper

AN - SCOPUS:84899116759

T2 - 9th International Conference on Information, Communications and Signal Processing, ICICS 2013

Y2 - 10 December 2013 through 13 December 2013

ER -

Object instance search in videos

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this