This paper presents an audio-visual data representation for violent scenes detection in Hollywood movies. Existing works in this field consider either the audio or the visual information; or their shallow fusion. None has yet explored their joint dependence for violent scenes detection. We propose a feature which provides strong multimodal audio and visual cues by first joining the audio and th...

If we engineered systems like we produce movies, would our enterprise and endeavors prove leaner and more agile? We daydream on the greener pastures of movie making, an industry whose signature practices were born out of necessity, to adapt to major regulatory upheavals in the 30’s Hollywood, and have since proved remarkably effective & resilient. We journey through odd ways of tackling strange...

This paper presents a new learning algorithm for audiovisual fusion and demonstrates its application to video classification for film database. The proposed system utilized perceptual features for content characterization of movie clips. These features are extracted from different modalities and fused through a machine learning process. More specifically, in order to capture the spatio-temporal...

This paper describes the LIG participation to the MediaEval 2012 Affect Task on violent scenes’ detection in Hollywood movies. We submitted four runs at the shot level: hierarchical fusion of descriptors and classifier combinations (LIG-4), the same with conceptual feedback (LIG-3), and the same two with reranking (LIG-2 and LIG-1). Our reference run obtained a performance slightly above the me...

Exposing students to current biotechnological and medical issues is eye-opening for many students in a way that is not always achieved through lecture-based learning. Lecture or investigative teaching styles provide a tremendous knowledge base for the students, but sometimes these teaching styles do not allow the student to fully develop, especially personal attitudes to issues in bioethics. Th...

Semantic scene segmentation is a crucial step in movie video analysis and extensive research efforts have been devoted to this area. However, previous methods are heavily relying on video content itself, which are lack of objective evaluation criterion and necessary semantic link due to the semantic gap. In this paper, we propose a novel role-based approach for movie scene segmentation using sc...

ded systems software for planetary space exploration. The high degree of reliability, autonomy, and flexibility these systems require, combined with demanding mission requirements and the high cost of failure, place extraordinary demands on the systems produced. In September 1993, we began our attempt at the Jet Propulsion Laboratory to land a spacecraft on the planet Mars. This spacecraft, Mar...

While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semanticallydefined categories such as “pursuit” or “romance” remains challenging. We introduce a new dataset, Action Movie Franchises, consisting of a collection of Hollywood action mov...

Accepting the common lay definition of nightmare as any form of upsetting, dreamlike cognition occurring in the midst of sleep, the author argues for a classification of nightmares that would be based, not on physiological findings, but on what the upsetting nocturnal occurrence turns out to mean to the dreamer. Three types of nightmare identified on this basis are illustrated through dream seq...

This paper describes the LIG participation to the MediaEval 2013 Affect Task on violent scenes detection in Hollywood movies. We submitted four runs at the shot level for each subtasks: objective violent scenes detection and subjective violent scenes detection. Our four runs are: hierarchical fusion of descriptors and classifier combinations, the same with joint audio-visual words, and the same...