Benoit Huet

Followers

Following

Co-authors

Public Views

Dr. Benoit Huet is Assistant Professor in the multimedia information processing group of Eurecom (France). He received his BSc degree in computer science and engineering from the École Supérieure de Technologie Électrique (Groupe ESIEE, France) in 1992. In 1993, he was awarded the MSc degree in Artificial Intelligence from the University of Westminster (UK) with distinction, where he then spent two years working as a research and teaching assistant. He received his DPhil degree in Computer Science from the University of York (UK) for his research on the topic of object recognition from large databases. He was awarded the HDR (Habilitation to Direct Research) from the University of Nice Sophia Antipolis, France, in October 2012 on the topic of Multimedia Content Understanding: Bringing Context to Content. He is associate editor for IEEE Multimedia, IEEE Trans. on Multimedia, Multimedia Tools and Application (Springer) and Multimedia Systems (Springer) and has been guest editor for a number of special issues (IEEE Multimedia, IEEE trans. on Multimedia, Springer Multimedia Tools and Application, EURASIP Journal on Image and Video Processing, Elsevier Ecological Informatics, etc..). He regularly serves on the technical program committee of the top conferences of the field (ACM MM/ICMR, IEEE ICME/ICIP). He has chaired the IEEE MMTC Interest Group on Visual Analysis, Interaction and Content Management (VAIG) from 2010 to 2014. He has co-authored over 150 papers in Books, Journals and International conferences. His current research interests include Large Scale Multimedia Content Analysis, Mining and Indexing - Multimodal Fusion - Socially-Aware Multimedia.

less

Thiên Nguyễn Bá

John Fox

Dr. Anuj Gupta

Punjab Technical University

Vasant G Honavar

Pennsylvania State University

Rohitash Chandra

University of the South Pacific

Garen Arevian

University of Sunderland

Daan Wierstra

Ivilin P Stoianov

Consiglio Nazionale delle Ricerche (CNR)

Axel Cleeremans

Université libre de Bruxelles

Eduardo Pablo

Instituto Tecnológico de Morelia

InterestsView All (19)

Uploads

Papers by Benoit Huet

SAMMI

by M. Paleari and Benoit Huet

Recurrent Neural Networks for Temporal Sequences Recognition

Time is the center of many human tasks. To talk, to listen, to read or to write are examples of t... more Time is the center of many human tasks. To talk, to listen, to read or to write are examples of time related tasks. To integrate the time notion into neural network is very important in order to deal with such tasks. This report presents various tasks that are based on temporal pattern processing and the different neural network architectures, simulated to tackle the problem. We examine the main components of connectionist models that process time varying patterns: the memory that records past informations, the pattern of connectivity among units of the network, and the rule used to update connection strength during training. We explore two different network architectures, one presented by Elman [8] and the other by Stornetta et al. , and analyze their ability to learn and recognize a finite state machine. Variant of these architectures are explored in order to know whether better results may be reached or not. We finally compare the results obtained by these architectures for the particular task of learning contingencies implied by a finite state machine.

Download

Modelling and simulation of information systems on computer: methodological advantages

Modelling and simulation of information systems by the means of miniatures on computer aim at two... more Modelling and simulation of information systems by the means of miniatures on computer aim at two general objectives: (a) as an aid to design and realization of information systems; and (b) a tool to improve the dialogue between the designer and the users. An operational information system has two components bound by a dynamic relationship, an information system and a behavioural system. Thanks to the behaviour system, modelling and simulation allow the designer to integrate into the projects a large proportion of the system&#39;s implicit specification. The advantages of modelling to the information system relate to: (a) The conceptual phase: initial objectives are compared with the results of simulation and sometimes modified. (b) The external specifications: simulation is particularly useful for personalising man-machine relationships in each application. (c) The internal specifications: if the miniatures are built on the concept of process, the global design and the software are tested and also the simulation refines the configuration and directs the choice of hardware. (d) The implementation: stimulation reduces costs, time and allows testing. Progress in modelling techniques will undoubtedly lead to better information systems.

EURASIP Journal on Applied Signal Processing 2003:1, 48--55

... Popular Tags. Add a tag: No tags have been applied to this document. BibTeX | Add To MetaCart... more

Exploring Video Hyperlinking in Broadcast Media

Proceedings of the Third Edition Workshop on Speech, Language & Audio in Multimedia - SLAM '15, 2015

EventEnricher

Proceedings of the 3rd ACM conference on International conference on multimedia retrieval - ICMR '13, 2013

Exploiting event context to organize social media draws lots of interest from the multimedia comm... more Exploiting event context to organize social media draws lots of interest from the multimedia community. In this paper, we present our system, called EventEnricher, to infer the semantics behind events and explore social media to illustrate events. We extend the set of illustrating images for a particular event by querying social media with diverse multimodal features and subsequently pruning the results using content based visual analysis. We integrate the solution into an intelligent interface that enables the user to browse the media collection illustrating events in an easy, effective and informative way.

Download

Advances in Multimedia Information Processing – PCM 2014

Lecture Notes in Computer Science, 2014

K-Space at Trecvid 2008

Proceedings of the …

Wilkins, P. et al. (2008) K-Space at TRECVID 2008. In: TRECVID 2008, 17-18 November 2008, Gaither... more

Download

USING EMOTIONS TO TAG MEDIA

by M. Paleari and Benoit Huet

manmachine.org

Multimedia information indexing and retrieval is about developing techniques which allow people t... more Multimedia information indexing and retrieval is about developing techniques which allow people to effectively find the media they are looking for. Content-based methods become necessary when dealing with big databases due to the limitations inherent in metadata-based systems. Current technology allows researchers to explore the emotional space which is known to carry very interesting semantic information, but emotion recognition systems, however, lack sufficient reliability when dealing with real world data. A possible solution to this problem resides in the multimodal fusion paradigm which aims at improving robustness to real world noise. We state the need for an integrated methodology which extracts reliable affective information through a multimodal fusion system and tags this semantic information to the medium itself. A framework, EMMA, currently under development in our laboratory, will be described.

Download

EIC's Message

Event-based Summarization for Media Hyperlinking

Event-centric HyperLinking of Socially Contributed Multimedia Content

Event-Based Media Enrichment Using an Adaptive Probabilistic Hypergraph Model

Nowadays, with the continual development of digital capture technologies and social media service... more Nowadays, with the continual development of digital capture technologies and social media services, a vast number of media documents are captured and shared online to help attendees record their experience during events. In this paper, we present a method combining semantic inference and multimodal analysis for automatically finding media content to illustrate events using an adaptive probabilistic hypergraph model. In this model, media items are taken as vertices in the weighted hypergraph and the task of enriching media to illustrate events is formulated as a ranking problem. In our method, each hyperedge is constructed using the K-nearest neighbors of a given media document. We also employ a probabilistic representation, which assigns each vertex to a hyperedge in a probabilistic way, to further exploit the correlation among media data. Furthermore, we optimize the hypergraph weights in a regularization framework, which is solved as a second-order cone problem. The approach is initiated by seed media and then used to rank the media documents using a transductive inference process. The results obtained from validating the approach on an event dataset collected from EventMedia demonstrate the effectiveness of the proposed approach.

Semantic Affect-enhanced MultiMedia Indexing

... SAMMI Semantic Affect-enhanced MultiMedia Indexing Marco Paleari1, Benoit Huet1 and Brian Duf... more

Poster Session-ALICIA: An Architecture for Intelligent Affective Agents

1st International Workshop on Web-Scale Multimedia Corpus, WSMC 09, Co-located with the 2009 ACM International Conference on Multimedia, MM 09: Foreword

VLS-MCMR'10-Proceedings of the 2010 ACM International Workshop on Very-Large-Scale Multimedia Corpus, Mining and Retrieval, Co-located with ACM Multimedia 2010: Foreword

The Role of Explicit Semantics in Search and Browsing

In recent years several Semantic Web applications have been developed that support some form of s... more In recent years several Semantic Web applications have been developed that support some form of search. These applications provide different types of search functionality and make use of the explicit semantics present in the data in various ways. The aim of this chapter is to give an overview of the semantic search functionalities provided by the current state of the art in Semantic Web applications. Excluding search based on structured query languages such as SPARQL (Prud'homme and Seaborne 2007), we focus on queries based on simple textual entry forms and queries constructed by navigation (e.g. faceted browsing). We provide a systematic understanding of the different design dimensions that play a role in supporting search on Semantic Web data. Using the required insights, we describe the design decisions made in two of our own tools with practical use cases.

Download

Multimedia Content Understanding: Bringing Context to Content

Interlinking and visualizing linked open data with geospatial reference data

SAMMI

by M. Paleari and Benoit Huet

Recurrent Neural Networks for Temporal Sequences Recognition

Download

Modelling and simulation of information systems on computer: methodological advantages