This paper presents a novel model for multimodal learning based on gated neu-ral networks. The Gated Multimodal Unit (GMU) model is intended to be used as an internal unit in a neural network architecture whose purpose is to find an intermediate representation based on a combination of data from different modalities. The GMU learns to decide how modalities influence the activation of the unit u...

We present a novel technique to characterize and index violent scenes in general TV drama and movies. Our goal is to identify violent signatures and localize violent events within a movie to support \high-level" video indexing. In particular, we exploit multiple \audiovisual" signatures to create a perceptual relation for conceptually meaningful violent scene identi cation. Potential applicatio...

Hallmark movies are a hit. While most broadcast networks in the United States and Canada struggling to maintain an audience, has launched three additional cable services past four years. Much of this success can be attributed Hallmark’s investment—both ideological economic—in made-for-TV movie, form programing that re-popularized re-branded—and transformed into genre. To work through my suggest...

IMDb is a widely known online movie platform that offers movie information, allows to rate movies and recommends interesting movies to users. The IMDb movie recommendations do not however offer any means for interactivity or user control, which inherently limits their contextual adaptability. In this work we describe our Google Chrome extension – called MovieBrain – which offers interactive mov...

Definition: Multimedia personalization is tailoring digital audiovisual content to its users, based on personal details or characteristics they provide. It allows a content provider to adapt specific multimedia content in accordance with individual standards, tastes and preferences. For example, movies can be personalized based on genre, cast, director, etc.

Popular movies are spatiotemporal arrays of light and motion, but almost nothing is known about their distributions across whole films. Psychological research shows that the center of the screen is the most important region, but is light and motion most prominent there? I confirm that they are while exploring a sample of 160 movies released from 1935 to 2010. Concerning how light bathes the scr...

We examine localised sound energy patterns, or events, that we associate with high level affect experienced with films. The study of sound energy events in conjunction with their intended affect enable the analysis of film at a higher conceptual level, such as genre. The various affect/emotional responses we investigate in this paper are brought about by well established patterns of sound energ...

In this paper, we propose an audio-visual approach to video genre categorization. It exploits audio, color, temporal and contour information, which are in general genre specific. Audio information is extracted at block-level, which has the advantage of capturing local temporal information. At temporal level, we asses action contents with respect to human perception. Further, color perception is...

Leong and Silva have likened the sexually violent predator (SVP) laws to fictional serial slashers in horror movies. Like Jason in Friday the 13th, these cannot be vanquished and reappear in sequel after sequel, meaner and naughtier. The latest episode of the SVP trilogy premiered on January 22, 2002, in the chambers of the U.S. Supreme Court. The analogy with serial slasher movies, although on...

Item features play an important role in movie recommender systems, where recommendations can be generated by using explicit or implicit preferences of users on attributes such as genres. Traditionally, movie features are human-generated, either editorially or by leveraging the wisdom of the crowd. In this short paper, we present a recommender system for movies based of Factorization Machines th...