Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014

J. Raitoharju; H. Zhang; E. C. Ozan; M. A. Waris; M. Faisal; G. Cao; M. Roininen; I. Ahmad; R. Shetty; S. Uhlmann; K. Samiee; S. Kiranyaz; M. Gabbouj

doi:10.1109/ICMEW.2014.6890600

Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014

J. Raitoharju, H. Zhang, E. C. Ozan, M. A. Waris, M. Faisal, G. Cao, M. Roininen, I. Ahmad, R. Shetty, S. Uhlmann, K. Samiee, S. Kiranyaz, M. Gabbouj

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

Abstract

This paper presents our system designed for MSR-Bing Image Retrieval Challenge @ ICME 2014. The core of our system is formed by a text processing module combined with a module performing PCA-assisted perceptron regression with random sub-space selection (P²R²S²). P²R²S² uses Over-Feat features as a starting point and transforms them into more descriptive features via unsupervised training. The relevance score for each query-image pair is obtained by comparing the transformed features of the query image and the relevant training images. We also use a face bank, duplicate image detection, and optical character recognition to boost our evaluation accuracy. Our system achieves 0.5099 in terms of DCG₂₅ on the development set and 0.5116 on the test set.

Translated title of the contribution	TUT Muvis Image Retrieval System Proposal for MSR-BING Challenge 2014
Original language	English
Title of host publication	IEEE International Conference on Multimedia and Expo, ICME 2014, Chengdu, China, July 14-18, 2014
Place of Publication	Piscataway
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Print)	9781479947171
DOIs	https://doi.org/10.1109/ICMEW.2014.6890600
Publication status	Published - 3 Sept 2014
Publication type	A4 Article in conference proceedings
Event	IEEE International Conference on Multimedia and Expo - Duration: 1 Jan 1900 → …

Conference

Conference	IEEE International Conference on Multimedia and Expo
Period	1/01/00 → …

Keywords

Data Partitioning
Face Bank
Image Retrieval
Relevance Evaluation

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Human-Computer Interaction

Access to Document

10.1109/ICMEW.2014.6890600

Cite this

Raitoharju, J., Zhang, H., Ozan, E. C., Waris, M. A., Faisal, M., Cao, G., Roininen, M., Ahmad, I., Shetty, R., Uhlmann, S., Samiee, K., Kiranyaz, S., & Gabbouj, M. (2014). Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014. In IEEE International Conference on Multimedia and Expo, ICME 2014, Chengdu, China, July 14-18, 2014 (pp. 1-6). IEEE. https://doi.org/10.1109/ICMEW.2014.6890600

@inproceedings{511dfcef63e941bf9bcf4641fdddf7c2,

title = "Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014",

abstract = "This paper presents our system designed for MSR-Bing Image Retrieval Challenge @ ICME 2014. The core of our system is formed by a text processing module combined with a module performing PCA-assisted perceptron regression with random sub-space selection (P2R2S2). P2R2S2 uses Over-Feat features as a starting point and transforms them into more descriptive features via unsupervised training. The relevance score for each query-image pair is obtained by comparing the transformed features of the query image and the relevant training images. We also use a face bank, duplicate image detection, and optical character recognition to boost our evaluation accuracy. Our system achieves 0.5099 in terms of DCG25 on the development set and 0.5116 on the test set.",

keywords = "Data Partitioning, Face Bank, Image Retrieval, Relevance Evaluation",

author = "J. Raitoharju and H. Zhang and Ozan, {E. C.} and Waris, {M. A.} and M. Faisal and G. Cao and M. Roininen and I. Ahmad and R. Shetty and S. Uhlmann and K. Samiee and S. Kiranyaz and M. Gabbouj",

note = "Contribution: organisation=sgn,FACT1=1<br/>Portfolio EDEND: 2014-09-25; IEEE International Conference on Multimedia and Expo ; Conference date: 01-01-1900",

year = "2014",

month = sep,

day = "3",

doi = "10.1109/ICMEW.2014.6890600",

language = "English",

isbn = "9781479947171",

pages = "1--6",

booktitle = "IEEE International Conference on Multimedia and Expo, ICME 2014, Chengdu, China, July 14-18, 2014",

publisher = "IEEE",

address = "United States",

}

Raitoharju, J, Zhang, H, Ozan, EC, Waris, MA, Faisal, M, Cao, G, Roininen, M, Ahmad, I, Shetty, R, Uhlmann, S, Samiee, K, Kiranyaz, S & Gabbouj, M 2014, Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014. in IEEE International Conference on Multimedia and Expo, ICME 2014, Chengdu, China, July 14-18, 2014. IEEE, Piscataway, pp. 1-6, IEEE International Conference on Multimedia and Expo, 1/01/00. https://doi.org/10.1109/ICMEW.2014.6890600

TY - GEN

T1 - Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014

AU - Raitoharju, J.

AU - Zhang, H.

AU - Ozan, E. C.

AU - Waris, M. A.

AU - Faisal, M.

AU - Cao, G.

AU - Roininen, M.

AU - Ahmad, I.

AU - Shetty, R.

AU - Uhlmann, S.

AU - Samiee, K.

AU - Kiranyaz, S.

AU - Gabbouj, M.

N1 - Contribution: organisation=sgn,FACT1=1<br/>Portfolio EDEND: 2014-09-25

PY - 2014/9/3

Y1 - 2014/9/3

N2 - This paper presents our system designed for MSR-Bing Image Retrieval Challenge @ ICME 2014. The core of our system is formed by a text processing module combined with a module performing PCA-assisted perceptron regression with random sub-space selection (P2R2S2). P2R2S2 uses Over-Feat features as a starting point and transforms them into more descriptive features via unsupervised training. The relevance score for each query-image pair is obtained by comparing the transformed features of the query image and the relevant training images. We also use a face bank, duplicate image detection, and optical character recognition to boost our evaluation accuracy. Our system achieves 0.5099 in terms of DCG25 on the development set and 0.5116 on the test set.

AB - This paper presents our system designed for MSR-Bing Image Retrieval Challenge @ ICME 2014. The core of our system is formed by a text processing module combined with a module performing PCA-assisted perceptron regression with random sub-space selection (P2R2S2). P2R2S2 uses Over-Feat features as a starting point and transforms them into more descriptive features via unsupervised training. The relevance score for each query-image pair is obtained by comparing the transformed features of the query image and the relevant training images. We also use a face bank, duplicate image detection, and optical character recognition to boost our evaluation accuracy. Our system achieves 0.5099 in terms of DCG25 on the development set and 0.5116 on the test set.

KW - Data Partitioning

KW - Face Bank

KW - Image Retrieval

KW - Relevance Evaluation

UR - http://www.scopus.com/inward/record.url?scp=84937152405&partnerID=8YFLogxK

U2 - 10.1109/ICMEW.2014.6890600

DO - 10.1109/ICMEW.2014.6890600

M3 - Conference contribution

SN - 9781479947171

SP - 1

EP - 6

BT - IEEE International Conference on Multimedia and Expo, ICME 2014, Chengdu, China, July 14-18, 2014

PB - IEEE

CY - Piscataway

T2 - IEEE International Conference on Multimedia and Expo

Y2 - 1 January 1900

ER -

Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014

Abstract

Conference

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this