Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Using visual features based on MPEG-7 and deep learning for movie recommendation

Using visual features based on MPEG-7 and deep learning for movie recommendation Item features play an important role in movie recommender systems, where recommendations can be generated by using explicit or implicit preferences of users on traditional features (attributes) such as tag, genre, and cast. Typically, movie features are human-generated, either editorially (e.g., genre and cast) or by leveraging the wisdom of the crowd (e.g., tag), and as such, they are prone to noise and are expensive to collect. Moreover, these features are often rare or absent for new items, making it difficult or even impossible to provide good quality recommendations. In this paper, we show that users’ preferences on movies can be well or even better described in terms of the mise-en-scène features, i.e., the visual aspects of a movie that characterize design, aesthetics and style (e.g., colors, textures). We use both MPEG-7 visual descriptors and Deep Learning hidden layers as examples of mise-en-scène features that can visually describe movies. These features can be computed automatically from any video file, offering the flexibility in handling new items, avoiding the need for costly and error-prone human-based tagging, and providing good scalability. We have conducted a set of experiments on a large catalog of 4K movies. Results show that recommendations based on mise-en-scène features consistently outperform traditional metadata attributes (e.g., genre and tag). http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Multimedia Information Retrieval Springer Journals

Using visual features based on MPEG-7 and deep learning for movie recommendation

Download PDF
13 pages

Loading next page...
 
/lp/springer-journals/using-visual-features-based-on-mpeg-7-and-deep-learning-for-movie-4PcMxIBCrz
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer-Verlag London Ltd., part of Springer Nature
Subject
Computer Science; Multimedia Information Systems; Information Storage and Retrieval; Information Systems Applications (incl.Internet); Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Database Management
ISSN
2192-6611
eISSN
2192-662X
DOI
10.1007/s13735-018-0155-1
Publisher site
See Article on Publisher Site

Abstract

Item features play an important role in movie recommender systems, where recommendations can be generated by using explicit or implicit preferences of users on traditional features (attributes) such as tag, genre, and cast. Typically, movie features are human-generated, either editorially (e.g., genre and cast) or by leveraging the wisdom of the crowd (e.g., tag), and as such, they are prone to noise and are expensive to collect. Moreover, these features are often rare or absent for new items, making it difficult or even impossible to provide good quality recommendations. In this paper, we show that users’ preferences on movies can be well or even better described in terms of the mise-en-scène features, i.e., the visual aspects of a movie that characterize design, aesthetics and style (e.g., colors, textures). We use both MPEG-7 visual descriptors and Deep Learning hidden layers as examples of mise-en-scène features that can visually describe movies. These features can be computed automatically from any video file, offering the flexibility in handling new items, avoiding the need for costly and error-prone human-based tagging, and providing good scalability. We have conducted a set of experiments on a large catalog of 4K movies. Results show that recommendations based on mise-en-scène features consistently outperform traditional metadata attributes (e.g., genre and tag).

Journal

International Journal of Multimedia Information Retrieval – Springer Journals

Published: Jun 14, 2018

References

  • Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions
    Adomavicius, G; Tuzhilin, A
  • Bilvideo-7: an mpeg-7-compatible video indexing and retrieval system
    Bastan, M; Cam, H; Gudukbay, U; Ulusoy, O
  • Unifying low-level and high-level music similarity measures
    Bogdanov, D; Serrà, J; Wack, N; Herrera, P; Serra, X
  • Techniques for cold-starting context-aware mobile recommender systems for tourism
    Braunhofer, M; Elahi, M; Ricci, F
  • Automatic video classification: a survey of the literature
    Brezeale, D; Cook, DJ
  • What does the statistical style analysis of film involve? A review of moving into pictures. More on film history, style, and analysis
    Buckland, W
  • User interface patterns in recommendation-empowered content intensive multimedia applications
    Cremonesi, P; Elahi, M; Garzotto, F
  • A low-cost infrared-optical head tracking solution for virtual 3d audio environment using the nintendo wii-remote
    Deldjoo, Y; Atani, RE
  • Content-based video recommendation system based on stylistic visual features
    Deldjoo, Y; Elahi, M; Cremonesi, P; Garzotto, F; Piazzolla, P; Quadrana, M
  • Lecture Notes in Business Information Processing
    Deldjoo, Yashar; Elahi, Mehdi; Cremonesi, Paolo; Moghaddam, Farshad Bakhshandegan; Caielli, Andrea Luigi Edoardo
  • Computational media aesthetics: finding meaning beautiful
    Dorai, C; Venkatesh, S
  • Active learning strategies for rating elicitation in collaborative filtering: a system-wide perspective
    Elahi, M; Ricci, F; Rubens, N
  • A survey of active learning in collaborative filtering recommender systems
    Elahi, M; Ricci, F; Rubens, N
  • How should i explain? A comparison of different explanation types for recommender systems
    Gedikli, F; Jannach, D; Ge, M
  • Fully automatic face normalization and single sample face recognition in unconstrained environments
    Haghighat, M; Abdel-Mottaleb, M; Alhalabi, W
  • Canonical correlation analysis: an overview with application to learning methods
    Hardoon, DR; Szedmak, S; Shawe-Taylor, J
  • The movielens datasets: history and context
    Harper, FM; Konstan, JA
  • A survey on visual content-based video indexing and retrieval
    Hu, W; Xie, N; Li, L; Zeng, X; Maybank, S
  • Facing the cold start problem in recommender systems
    Lika, B; Kolomvatsos, K; Hadjiefthymiades, S
  • Color and texture descriptors
    Manjunath, BS; Ohm, JR; Vasudevan, VV; Yamada, A
  • Introduction to MPEG-7: multimedia content description interface
    Manjunath, BS; Salembier, P; Sikora, T
  • On the use of computable features for film classification
    Rasheed, Z; Sheikh, Y; Shah, M
  • Current challenges and visions in music recommender systems research
    Schedl, M; Zamani, H; Chen, CW; Deldjoo, Y; Elahi, M
  • Collaborative filtering beyond the user-item matrix: a survey of the state of the art and future challenges
    Shi, Y; Larson, M; Hanjalic, A
  • Content-based image retrieval by integrating color and texture features
    Wang, XY; Zhang, BB; Yang, HY
  • Video semantic models: survey and evaluation
    Wang, Y; Xing, C; Zhou, L
  • Media computing. The Springer international series in video computing
    Zettl, H
  • Sight, sound, motion: applied media aesthetics
    Zettl, H
  • Solving the cold-start problem in recommender systems with social tags
    Zhang, ZK; Liu, C; Zhang, YC; Zhou, T