S
Sid-Ahmed Berrani
Researcher at Orange S.A.
Publications - 77
Citations - 1192
Sid-Ahmed Berrani is an academic researcher from Orange S.A.. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has an hindex of 17, co-authored 75 publications receiving 1071 citations. Previous affiliations of Sid-Ahmed Berrani include Institut de Recherche en Informatique et Systèmes Aléatoires & Dublin City University.
Papers
More filters
Patent
Triggering an action relative to a flow
TL;DR: In this article, the authors present a method for transmitting time information relative to a flow during broadcast of multimedia content, where the action is a restitution of content complementary to content of the flow during restoration on the restitution device.
Proceedings Article
Boosting-based approaches for Arabic text detection in news videos
TL;DR: Two boosting-based approaches for Arabic embedded text detection in news videos using Multi-Block Local Binary Patterns features and a multiexit asymmetric boosting cascade are proposed.
Proceedings ArticleDOI
Audio Recurrence Contribution to a Video-based TV Program Structuring Approach
TL;DR: This work addresses the structuring of recurrent TV programs like news, entertainment programs, TV shows, TV magazines by extending the study to audio recurrences and verifying their influence on the final structuring.
Patent
Method of analyzing a multimedia content, a computer program product and corresponding analysis device
TL;DR: The invention relates to a method for analyzing multimedia content, comprising a temporal succession of elementary entities to verify that the media content or may not comprise at least one reference content referenced in a basic contenus.
Patent
Digital data stream processing
Xavier Naturel,Sid-Ahmed Berrani +1 more
TL;DR: In this paper, a method for processing a digital data stream including sequences and intersequences is proposed, which comprises a step (E1) of cutting the stream into segments on the fly and calculating signatures for said segments, and a step(E2) of detecting intersequence during which the following operations are applied to said stream on the run: a first detection of intersequENCE by separation detection; the supply of a reference base (BR) with at least the signatures of the intersequenced detected by the first detection; a second detection of the stream segments obtained