Discovering similarities for content-based recommendation and browsing in multimedia collections
- Author
- Taras Lehinevych, Nikolaos Kokkinis-Ntrenis, Giorgos Siantikos, A. Seza Doğruöz (UGent) , Theodoros Giannakopoulos and Stasinos Konstantopoulos
- Organization
- Abstract
- The purpose of the research described in this paper is to examine the existence of correlation between low level audio, visual and textual features and movie content similarity. In order to focus on a well defined and controlled case, we have built a small dataset of movie scenes from three sequel movies. In addition, manual annotations have led to a ground-truth similarity matrix between the adopted scenes. Then, three similarity matrices (one for each medium) have been computed based on Gaussian Mixture Models (audio and visual) and Latent Semantic Indexing (text). We have evaluated the automatically extracted similarities along with two simple fusion approaches and results indicate that the low-level features can lead to an accurate representation of the movie content. In addition, the fusion approach seems to outperform the individual modalities, which is a strong indication that individual modules lead to diverse similarities (in terms of content). Finally, we have evaluated the extracted similarities for different groups of human annotators, based on what a human interprets as similar and the results show that different groups of people correlate better with different modalities. This last result is very important and can be either used in (a) a personalized content-based retrieval and recommender system and (b) in a local weighted fusion approach, in future research.
- Keywords
- recommendation systems, multimedia signal analysis, movies, audio features, visual features, optical flow, fusion, similarity, recommender systems, Lt3
Downloads
-
Dogruoz SITIS14.pdf
- full text (Published version)
- |
- open access
- |
- |
- 689.40 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8694803
- MLA
- Lehinevych, Taras, et al. “Discovering Similarities for Content-Based Recommendation and Browsing in Multimedia Collections.” 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014, edited by K. Yetongnon et al., 2014, pp. 237–43, doi:10.1109/sitis.2014.98.
- APA
- Lehinevych, T., Kokkinis-Ntrenis, N., Siantikos, G., Doğruöz, A. S., Giannakopoulos, T., & Konstantopoulos, S. (2014). Discovering similarities for content-based recommendation and browsing in multimedia collections. In K. Yetongnon, A. Dipanda, & R. Chbeir (Eds.), 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014 (pp. 237–243). https://doi.org/10.1109/sitis.2014.98
- Chicago author-date
- Lehinevych, Taras, Nikolaos Kokkinis-Ntrenis, Giorgos Siantikos, A. Seza Doğruöz, Theodoros Giannakopoulos, and Stasinos Konstantopoulos. 2014. “Discovering Similarities for Content-Based Recommendation and Browsing in Multimedia Collections.” In 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014, edited by K. Yetongnon, A. Dipanda, and R. Chbeir, 237–43. https://doi.org/10.1109/sitis.2014.98.
- Chicago author-date (all authors)
- Lehinevych, Taras, Nikolaos Kokkinis-Ntrenis, Giorgos Siantikos, A. Seza Doğruöz, Theodoros Giannakopoulos, and Stasinos Konstantopoulos. 2014. “Discovering Similarities for Content-Based Recommendation and Browsing in Multimedia Collections.” In 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014, ed by. K. Yetongnon, A. Dipanda, and R. Chbeir, 237–243. doi:10.1109/sitis.2014.98.
- Vancouver
- 1.Lehinevych T, Kokkinis-Ntrenis N, Siantikos G, Doğruöz AS, Giannakopoulos T, Konstantopoulos S. Discovering similarities for content-based recommendation and browsing in multimedia collections. In: Yetongnon K, Dipanda A, Chbeir R, editors. 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014. 2014. p. 237–43.
- IEEE
- [1]T. Lehinevych, N. Kokkinis-Ntrenis, G. Siantikos, A. S. Doğruöz, T. Giannakopoulos, and S. Konstantopoulos, “Discovering similarities for content-based recommendation and browsing in multimedia collections,” in 10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014, Marrakesh, MOROCCO, 2014, pp. 237–243.
@inproceedings{8694803,
abstract = {{The purpose of the research described in this paper is to examine the existence of correlation between low level audio, visual and textual features and movie content similarity. In order to focus on a well defined and controlled case, we have built a small dataset of movie scenes from three sequel movies. In addition, manual annotations have led to a ground-truth similarity matrix between the adopted scenes. Then, three similarity matrices (one for each medium) have been computed based on Gaussian Mixture Models (audio and visual) and Latent Semantic Indexing (text). We have evaluated the automatically extracted similarities along with two simple fusion approaches and results indicate that the low-level features can lead to an accurate representation of the movie content. In addition, the fusion approach seems to outperform the individual modalities, which is a strong indication that individual modules lead to diverse similarities (in terms of content). Finally, we have evaluated the extracted similarities for different groups of human annotators, based on what a human interprets as similar and the results show that different groups of people correlate better with different modalities. This last result is very important and can be either used in (a) a personalized content-based retrieval and recommender system and (b) in a local weighted fusion approach, in future research.}},
author = {{Lehinevych, Taras and Kokkinis-Ntrenis, Nikolaos and Siantikos, Giorgos and Doğruöz, A. Seza and Giannakopoulos, Theodoros and Konstantopoulos, Stasinos}},
booktitle = {{10TH INTERNATIONAL CONFERENCE ON SIGNAL-IMAGE TECHNOLOGY AND INTERNET-BASED SYSTEMS SITIS 2014}},
editor = {{Yetongnon, K. and Dipanda, A. and Chbeir, R.}},
isbn = {{9781479979783}},
keywords = {{recommendation systems,multimedia signal analysis,movies,audio features,visual features,optical flow,fusion,similarity,recommender systems,Lt3}},
language = {{eng}},
location = {{Marrakesh, MOROCCO}},
pages = {{237--243}},
title = {{Discovering similarities for content-based recommendation and browsing in multimedia collections}},
url = {{http://doi.org/10.1109/sitis.2014.98}},
year = {{2014}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: