Trailer Generation via a Point Process-Based Visual Attractiveness Model

Authors: Hongteng Xu, Yi Zhen, Hongyuan Zha

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate that our approach outperforms the state-of-the-art trailer generators in terms of both quality and efficiency.
Researcher Affiliation Academia Hongteng Xu1,2, Yi Zhen2, Hongyuan Zha2,3 1School of ECE, Georgia Institute of Technology, Atlanta, GA, USA 2College of Computing, Georgia Institute of Technology, Atlanta, GA, USA 3Software Engineering Institute, East China Normal University, Shanghai, China
Pseudocode Yes Algorithm 1 Learning Proposed Attractiveness Model
Open Source Code No The paper provides a link to 'representative trailers' on Vimeo, but no statement or link to the source code for their described methodology.
Open Datasets No Our data set consists of 16 publicly available movies including 3 animation movies, 2 fantasy movies, 2 action movies, 5 fiction action movies and 4 dramas in 2012 and 2014. We also collect the movies, their theme music and official trailers.
Dataset Splits Yes The experimental settings are as follows: we first select 8 of the trailers as the training set and collect the fixation data from 14 volunteers. Then, we learn our attractiveness model as described in Section 3.3. Finally, based on the attractiveness model, we produce trailers for the remaining 8 movies following Section 4.
Hardware Specification Yes Both methods are implemented by MATLAB and run on the same platform (Core i7 CPU @3.40GHz with 32GB memory).
Software Dependencies No The paper only states 'implemented by MATLAB' without specifying a version number for MATLAB or any other software dependencies with versions.
Experiment Setup Yes The maximum number of iteration M = 500, the parameter µ = 0.5. The gradient descent step size: δα = 10 4, δβ = 10 5.