Published July 2, 2019 | Version 1
Dataset Open

MA14KD [ORIGINAL] Dataset: Visual Attraction of Movie Trailers

Authors/Creators

  • 1. Free University of Bozen - Bolzano
  • 2. Karlsruhe Institute of Technology
  • 3. Vaillant Business Services
  • 4. University of Bergen

Description

MA14KD (Movie Attract 14K Dataset) provides a set of 10 VISUAL features extracted from 14074 movie and tv series trailers. The movie IDs are in agreement with the movie IDs provided by another rating dataset that also contains movie genres and tags (see the description within the file). More details can be found in the following publication:

Farshad B. Moghaddam, Mehdi Elahi, Reza Hosseini, Christoph Trattner, Marko Tkalcic, Predicting Movie Popularity and Ratings with Visual Features, IEEE SMAP’19, 9-10 June 2019, Larnaca, Cyprus

Files

MA14KD_[ORIGINAL].zip

Files (225.8 MB)

Name Size Download all
md5:ca9b9c7dd8bf0dd1c50040491052ac43
225.8 MB Preview Download

Additional details

Related works

Has part
10.13140/RG.2.2.11594.00961 (DOI)
Is supplement to
978-1-7281-3634-9/19$31.00 (Handle)
Is supplemented by
10.13140/RG.2.2.14110.59203 (DOI)
10.13140/RG.2.2.27532.36486 (DOI)

References

  • Farshad B. Moghaddam, Mehdi Elahi, Reza Hosseini, Christoph Trattner, Marko Tkalcic, Predicting Movie Popularity and Ratings with Visual Features, IEEE SMAP'19, 9-10 June 2019, Larnaca, Cyprus
  • Elahi, Mehdi and Deldjoo, Yashar and Bakhshandegan Moghaddam, Farshad and Cella, Leonardo and Cereda, Stefano and Cremonesi, Paolo, Exploring the semantic gap for movie recommendations, Proceedings of the Eleventh ACM Conference on Recommender Systems, 326–330, 2017 ACM
  • San Pedro, Jose, and Stefan Siersdorfer. "Ranking and classifying attractive