Due to video data exponential growth supported by quick advances in multimedia
technology, it became difficult for the user to retrieve information from a large videos …

In this paper, we introduce the DEEP-HEAR framework, a multimodal dynamic subtitle
positioning system designed to increase the accessibility of deaf and hearing impaired …

In this work we propose a new key frame extraction method based on SIFT local features.
We extracted feature vectors from a carefully selected group of frames from a video shot …

Abstract Video Shot Boundary Detection (SBD) is the fundamental process towards video
summarization and retrieval. A fast and efficient SBD algorithm is necessary for real-time …

In this paper we introduce an automatic subtitle positioning approach designed to enhance
the video accessibility of deaf and hearing impaired people to multimedia documents. By …

Key frames are the most representative images of a video. They are used in different areas
in video processing, such as indexing, retrieval and summarization. In this paper we …

One of the main approaches for video scene segmentation is based on shot clustering.
However, shot characterization has been left in background by researches related to video …

Keyframe extraction process consists on presenting an abstract of the entire video with the
most representative frames. It is one of the basic procedures relating to video retrieval and …

La description compacte du contenu d'une vidéo est actuellement une tâche dif-ficile à
cause de la très grande quantité de données qu'elle contient. La construction des résumés …

This paper tackles the issue of retrieving different instances of an object of interest within a
given video document or in a video database. The principle consists of considering a semi …