XJTU at TRECVID2008 high-level feature extraction

Zhe Wang; Guizhong Liu; Xueming Qian; Zhi Li; Dan Ping Guo; Nan Nan; Huaixia Jiang

XJTU at TRECVID2008 high-level feature extraction

Zhe Wang
, Guizhong Liu
, Xueming Qian
, Zhi Li
, Dan Ping Guo
, Nan Nan
, Huaixia Jiang

Faculty of Electronic and Information Engineering

Xi'an Jiaotong University

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

Abstract

In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture descriptor and the Compact-SIFT Codeword histogram. Our system applied well-known LIBSVM to train the SVM classifier for the basic classifier. In fusion step, some methods were employed such as the Voting, SVM-base, HCRF and Bootstrap Average AdaBoost(BAAB).

Original language	English
State	Published - 2008
Event	TREC Video Retrieval Evaluation, TRECVID 2008 - Gaithersburg, MD, United States Duration: 17 Nov 2008 → 18 Nov 2008

Conference

Conference	TREC Video Retrieval Evaluation, TRECVID 2008
Country/Territory	United States
City	Gaithersburg, MD
Period	17/11/08 → 18/11/08

Keywords

Classifier fusion
High-level feature
Low-level feature
Multiple classifiers model
Semantic concept
Support vector machines

Cite this

@conference{66e1301eaee94ad28f3a12e2baabca5d,

title = "XJTU at TRECVID2008 high-level feature extraction",

abstract = "In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture descriptor and the Compact-SIFT Codeword histogram. Our system applied well-known LIBSVM to train the SVM classifier for the basic classifier. In fusion step, some methods were employed such as the Voting, SVM-base, HCRF and Bootstrap Average AdaBoost(BAAB).",

keywords = "Classifier fusion, High-level feature, Low-level feature, Multiple classifiers model, Semantic concept, Support vector machines",

author = "Zhe Wang and Guizhong Liu and Xueming Qian and Zhi Li and Guo, \{Dan Ping\} and Nan Nan and Huaixia Jiang",

year = "2008",

language = "英语",

note = "TREC Video Retrieval Evaluation, TRECVID 2008 ; Conference date: 17-11-2008 Through 18-11-2008",

}

TY - CONF

T1 - XJTU at TRECVID2008 high-level feature extraction

AU - Wang, Zhe

AU - Liu, Guizhong

AU - Qian, Xueming

AU - Li, Zhi

AU - Guo, Dan Ping

AU - Nan, Nan

AU - Jiang, Huaixia

PY - 2008

Y1 - 2008

N2 - In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture descriptor and the Compact-SIFT Codeword histogram. Our system applied well-known LIBSVM to train the SVM classifier for the basic classifier. In fusion step, some methods were employed such as the Voting, SVM-base, HCRF and Bootstrap Average AdaBoost(BAAB).

AB - In this paper, we present our experiments in TRECVID 2008 about High-Level feature extraction task. This is the first year for our participation in TRECVID, our system adopts some popular approaches that other workgroups proposed before. We proposed 2 advanced low-level features NEW Gabor texture descriptor and the Compact-SIFT Codeword histogram. Our system applied well-known LIBSVM to train the SVM classifier for the basic classifier. In fusion step, some methods were employed such as the Voting, SVM-base, HCRF and Bootstrap Average AdaBoost(BAAB).

KW - Classifier fusion

KW - High-level feature

KW - Low-level feature

KW - Multiple classifiers model

KW - Semantic concept

KW - Support vector machines

UR - https://www.scopus.com/pages/publications/84905196537

M3 - 论文

AN - SCOPUS:84905196537

T2 - TREC Video Retrieval Evaluation, TRECVID 2008

Y2 - 17 November 2008 through 18 November 2008

ER -

XJTU at TRECVID2008 high-level feature extraction

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this