Service (updt Nov'21, non exhaustive lists, some old stuff is missing,)

Supervision   (go to top)

• PhD
• PhD in progress: Shashanka Venkataramanan, Metric learning for instance- and category-level visual representations. Started in Dec. 2020. Yannis Avrithis, Ewa Kijak, Laurent Amsaleg
• PhD in progress: Raquel Almeida, Learning hierarchichal models for multimedia data. Started Jan. 2019, Ewa Kijak, Simon Malinowski, Laurent Amsaleg
• Marzieh Gheisari Khorasgani, Secure identification in the Internet of Things., defended Jul. 2021.
• Hanwei Zhang, Deep Learning in Adversarial Contexts., defended Jun. 2021.
• Antoine Perquin, Universal speech synthesis through embeddings of massive heterogeneous data, defended Feb. 2021.
• Ricardo Carlini-Sperandio, Unsupervised motif mining in multimedia time series, defended Dec. 2019
• Cédric Maigrot, Détection de fausses informations dans les réseaux sociaux, defended Apr. 2019
• Raghavendran Balu, Privacy-preserving data aggregation and service personalization using highly-scalable data indexing techniques, defended Nov. 2016.
• Gylfi Þór Guðmundsson, Parallelism and Distribution for Very Large Scale Content Based Image Retrieval, defended Sept. 2013.
• Thanh-Toan Do, Security analysis of image copy detection systems based on SIFT descriptors, defended Sept. 2012.
• Romain Tavenard (ENS), Indexation de séquences de descripteurs, defended Jul. 2011.
• Sid-Ahmed Berrani, Recherche approximative de plus proches voisins avec contrôle probabiliste de la précision ; application à la recherche d'images par le contenu, defended Feb. 2004. Best French Thesis in Computer Science.


• Post Doc
• Vanessa Pena-Araya, 2 years (ongoing), supervision with the ILDA Inria Team.
• Gylfi Þór Guðmundsson, 1.5 year (working at the AMPLab, UC Berkeley). Now with Reykjavik University.
• Weng Li, 2.5 year. Now with IGN, France.
• Denis Shestakov, 1 year. Now with Big Data Scoring.
• Panagiotis Hadjidoukas, 1 year. Now with ETH.
• Antoine Doucet, 1 year. Now with the university of La Rochelle.
• Hervé Jégou, 9 months. Now with Facebook.


• Working with Visiting Professors
• Kári Harðarson, Visiting Professor (Reykjavik University), 2*4 months.
• Michael E. Houle, NII, Tokyo, Japan
• Björn Þór Jónsson, Reykjavík University, Reykjavík, Iceland
• Silvio Jamil Ferzoli Guimarães, PUC Minas, Brazil


• Engineer
• Arthur Masson, 1.5 year.
• Diana Moise, 1 year.
• Sophie Le Delliou, 1 year.
• Pierre-Hugues Joalland, 2 years.


• Master
• Dominique Barbe, Master (ENS)
• Arnaud Lods, ISTIC.
• Corentin Hardy, ISTIC.
• Paul Temple, ISTIC.
• Romain Tavenard, ENS.
• Loic Paulevé, ENS.
• Yacine Belkadi.
• François Le Lay.


• Intern
• Agni Delvinioti, Intern, 4 months.
• Priyank Bagrecha, Intern, 4 months.
• Sébastien Tonon, Intern (INSA), 4 months.
• Nicolas Basset, Intern (ENS), 4 months.
• Jia Zhen, Intern, 9 months.
• Brahm Kiran Singh, Intern, 4 months.
• Sylvain Bié, Intern, 9 months.

Committees   (go to top)

• Program committee member
• ACM Multimedia 2008, 2011, 2015, 2020, 2021
• MMM 2008--2022
• SISAP 2013--2021
• ICMR 2011--2021
• ICME 2012--2021
• CBMI 2012--2021
• VLDB PhD workshop 2011
• SITIS 2013, 2014, 2015, 2016
• EGC, 2018, 2019
• EUSIPCO, 2018<\li>
• VLDB 2010
• LIVA 2010
• EDBT 2010
• BDA 2004, 2005, 2006, 2007, 2008, 2009, 2012
• CORIA 2005, 2006, 2007, 2009
• ACM Sigmod 2009
• MDM 2007, 2008
• WWW 2008
• CORIA 2005, 2006, 2007
• AIMS 2007
• ExpDB 2007
• Europar 2007
• Majestic 2005
• IEEE EMMA'05
• MIS 2004, 2005
• PCM 2004


• Reviewing for journals
• Guest Editor, Information Systems, 2018
• Guest Editor, Multimedia Tools and Applications, 2017
• Multimedia Tools and Applications, 2017
• IEEE Transactions on Dependable and Secure Computing, 2021
• IEEE Transactions on Knowledge and Data Engineering, 2017
• ACM Transactions on Information Systems, 2017, 2018, 2019
• IEEE Transactions on Circuits and Systems for Video Technology, 2016, 2017
• IEEE Transactions on Multimedia, 2016, 2017
• Pattern Recognition Letters, 2016
• IEEE Transactions on Information Forensics & Security, 2016--2021
• IEEE Transactions on Image Processing, 2016, 2021
• Knowledge and Information Systems, 2015
• Information Systems, 2013
• MultiMedia Tools and Applications, 2013, 2014
• IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
• Advances in Multimedia, 2012
• IET Information Security, 2011
• ACM Computing Surveys 2011


• Organization of Scientific Events
• Member of the Steering Committee of ACM Multimedia for the 2020-2023 term
• Area Chair for ACM Multimedia 2020
• General co-chair, ACM Multimedia, 2019
• Organization committee member, CORIA, 2018
• Member of the steering committee of SISAP 2016-2020
• Program committee co-chair, MMM, 2017
• Program committee co-chair, SISAP, 2016
• Social Media Chair, ACM Multimedia, 2011
• Publicity Chair, ACM Multimedia, 2011
• Chair of the workshops, EDBT, 2008
• Organization chair, CORIA, 2008
• ACM Sigmod workshop coordinator, 2006, 2007, 2008
• First ACM Sigmod workshop coordinator, 2005
• Organization chair, BDA, 2005
• Workshop Co-Chair, Computer Vision meets Databases Workshop (CVDB), 2004, 2005, 2007
• Publicity Chair, ACM Sigmod, 2004


• PhD committee member
• Zhengyu Zhao, Rethinking Realism: Advances in Transferability and Imperceptibility for Adversarial, Radboud University, Feb 2022
• Solène Bernard, Stéganographie d'images numériques via l'utilisation de réseaux de neurones sous présence d'un adversaire - Digital images steganography using adversarial embedding, Centrale Lille, Oct. 2021
• André Belchior Mourão, Towards an Architecture for Efficient Distributed Search of Multimodal Information, Universidade Nova de Lisboa, April 2018
• Herwig Lejsek, NV-tree: A Scalable Disk-Based High-Dimensional Index., Reykjavík University, June 2015.
• Zineddine Kouahla, Indexation dans les espaces métriques, Index arborescent et parallélisation., Univ. Nantes, Feb. 2013.
• Eduardo alves do Valle Jr., Local-Descriptor Matching for Image Identification Systems., Univ. Cergy-Pontoise, June 2008.


• MsC committee member
• Grímur Tómas Tómasson, ObjectCube: A Generic Multi-Dimensional Model for Media Browsing, M.Sc. thesis, Reykjavík University, June 2011
• Haukur Pálmason, Large-Scale Music Classification using an Approximate k-NN Classifier, M.Sc. thesis, Reykjavík University, January 2011
• Stefán Freyr Stefánsson, Using Range Information to Reduce Local Descriptor Computations, M.Sc. thesis, Reykjavík University, January 2011
• Arnar Ólafsson, Dynamic Behavior of Balanced NV-trees, M.Sc. thesis, Reykjavík University, May, 2008.
• Friðrik Heiðar Ásmundsson, The NV-Network: A Distributed Architecture for High Throughput, August 2006, University of Reykjavík.
• Hafþór Guðnason, Median Rank Aggregation in Face Recognition, June 2006, University of Reykjavík.
• Herwig Lejsek, The PvS-index, June 2005, University of Reykjavík.


• Misc.
• Laurent Amsaleg has been involved in the writing of the "Rapport de la mission sur les outils de reconnaissance des contenus protégés et les plateformes de partage en ligne : état de l art et propositions. Conseil supérieur de la propriété littéraire et artistique, Hadopi".
• Elected Member of the "Conseil de Laboratoire", Irisa, 2017
• Member of the "Comité de Département Média et Interactions", Irisa, 2016
• Expert Evaluator for the Luxembourg National Research Fund, 2016
• Expert Evaluator for the Swiss National Science Foundation, 2009
• Expert Evaluator for the French ANR, 2009, 2014
• Membre du comité des utilisateurs des moyens informatiques, Irisa-Inria Rennes
• Membre de la commission formation permanente, Irisa-Inria Rennes
• National expert, ARA, 2006.
• National expert, MDCA, 2006.

Valorization, Contracts and Contacts with Industry (main and recent items only)    (go to top)

• CIFRE PhD: Semantic multimodal question answering in domestic environments.
  Duration: 3 years, started in June 2020. Industrial Partner: InterDigital.
  This is a CIFRE PhD thesis project aiming at designing novel deep learning based multimedia question answering techniques that take in to account rich information from different sensors to facilitate living condition at home. Advances in artificial intelligence boost research towards visual question answering as well as multimodal analysis.



• Name: INRIA-BNF: Classification d'images patrimoniales (CIP).
  Duration: 1 year, started in Dec 2018. Extended to May 2020.
  This project is within the context of the collaborations between INRIA and the French Ministry of Culture. In that context, we have started a collaboration with the French National Library (BNF) which collects, preserves and makes known the national documentary heritage. This collaboration aims at facilitating the automatic classification of heritage images through the use of recent deep-learning techniques. Such images are quite specific: they are not at all similar with what deep-learning techniques are used to work with, that is, the classification of heritage images does not target modern categories such as planes, cars, cats and dogs because this is irrelevant and because heritage collections do not include images of contemporary objects. Furthermore, heritage images come in vast quantities, but they are little annotated and deep-learning techniques can hardly rely on massive annotations to easily learn. Last, the learning has to be continuous as curators may need to add or modify existing classes, without re-learning everything from scratch. The techniques of choice to reach that goal include the semi-supervised learning, low-shot learning techniques, knowledge transfer, fine tuning existing models, etc. \textbf{Project leader.}



• Name: ANR Archival: Multimodal machine comprehension of language for new intelligent interfaces of scientific and cultural mediation.
  Duration: 3.5 year, started in Dec. 2019.
  The multidisciplinary and multi-actor ARCHIVAL project aims at yielding collaborations between researchers from the fields of Information and Communication Sciences as well as Computer Sciences around archive value enhancing and knowledge sharing for arts, culture and heritage. ARCHIVAL teams will explore heterogeneous document collection structuration in order to explicitly reveal implicit links, to explain the nature of these links and to promote them in an intelligible way towards ergonomic mediation interfaces that will guarantee a successful appropriation of contents. A corpus has been delimited from the FMSH self-management collection, recently awarded as Collex, which will be completed from the large Canal-U academic audiovisual portal. The analysis and enhancement of this collection is of particular interest for Humanities and Social Sciences in a context where it becomes a necessity to structurally reconsider new models of socioeconomic development.



• Name: ANR MEERQAT: MultimEdia Entity Representation and Question Answering Tasks.
  Duration: 3.5 year, started in April 2020. Partners: Inria project-teams Linkmedia, CEA LIST, LIMSI, IRIT.
  The overall goal of the project is to tackle the problem of ambiguities of visual and textual content by learning then combining their representations. As a final use case, we propose to solve a Multimedia Question Answering task, that requires to rely on three different sources of information to answer a (textual) question with regard to visual data as well as an external knowledge base containing millions of unique entities, each being represented by textual and visual content as well as some links to other entities. An important work will deal with the representation of entities into a common tri-modal space, in which one should determine the content to associate to an entity to adequately represent it. The challenge consists in defining a representation that is compact (for performance) while still expressive enough to reflect the potential links between the entity and a variety of others.



• Name: STIC-AMSUD Project : TRANSFORM
  Participants: Simon Malinowski, Guillaume Gravier, Laurent Amsaleg.
  TRANSFORM is a research project that involves Linkmedia Team, PUC Minas, Brazil and Univ. of Chile. It aims at studying complex transformations of multimedia data in order to facilitate its manipulation. TRANSFORM focuses on transforming multimedia data into compact representations that are suited for indexing and retrieval purposes.



• Name: iCODA: Knowledge-mediated content and data analytics, Inria Project Lab. 2017--2020
  The project, which started Jun. 17, seeks to develop the scientific and technological foundations for knowledge-mediated user-in-the-loop collaborative data analytics on heterogenous information sources, taking a data journalism use-case. In addition to the Linkmedia team which focuses on the multimedia facet of the project, knowledge engineering (GraphIK), data management (CEDAR) and data visualization (ILDA) are teamed up with key media players (AFP, Le Monde, Ouest-France).
  Project leader.



• Name: Chist Era ID\_IOT: Secure and scalable Identification for Internet-Of-Things devices. 2016--2019
  Partners: Eindhoven Univ. of Technology, Univ. of Geneva.



• Name: ANR Secular---Secure and Large image databases indexing.
  Partners: Morpho, Univ. Caen GREYC, Telecom ParisTech, Inria Rennes.
  
  
• Name: FIIA: Forensic Image Identifier and Analyser.
  Partners: Videntifier Forensic Tech, Forensic Pathways, TexMex.
  Main Workpackage: Ultrafast logo detection
  
  
• Name: Quaero.
  Main Partners: Quaero Consortium.
  Main Workpackage: Indexing Multimedia Objects
  
  
• Name: Eff² Tech.
  Main Partners: Eff² Tech, TexMex, University of Reykjavík.
  Technology Transfer: Our multidimensional indexing technique has been transfered to the Eff² Tech startup company. It is known now as the Videntifier^TM Forensic
  
  
• Name: Morgunbladid image bank.
  Main Partners: TexMex, University of Reykjavík, Morgunbladid.
  Duration: 24 months, starting Jan. 2006.
  Goal: Access granted to the image archive (300.000 images).
  
  
• Name: CNRS image bank.
  Partner: TexMex.
  Duration: 12 months, starting Jul. 2006.
  Goal: Access granted to the image archive (32.000).
  
  
• Name: MP2P -- Gestion de masses de documents dans les systèmes P2P.
  Partners: ATLAS (INRIA Rennes & IRIN-Nantes), GEMO (INRIA Futur, Saclay), PARIS (IRISA), TEXMEX (IRISA).
  Duration: 36 months, starting Sept 2003. Funded by the French Ministry of Research.
  Goal: Investigate issues related to the management of huge collections of multimedia documents within peer-to-peer systems.
  
  
• Name: REMIX -- Mémoire Reconfigurable pour l'Indexation de Masses de Données.
  Partners: SYMBIOSE (IRISA), TEXMEX (IRISA), EQUIPAGE (VALORIA, Vannes), R2D2 (IRISA).
  Duration: 36 months, starting Sept. 2003. Funded by the French Ministry of Research.
  Goal: Investigate the use of FPGA to facilitate multidimensional indexing.
  
  
• Name: Diphonet -- Diffusion de photos par Internet.
  Partners: TEXMEX (IRISA), Canon Research Center France, Andia Presse, CODES (INRIA), L2S.
  Duration: 33 months, starting Jan. 2001. Funded by the French Ministry of Research.
  Goal: Initial studies related to copyright infringment for professional photograpers.
  
  
• Network of Excellence, FP6: MUSCLE (Multimedia Understanding through Semantics, Computation and Learning).
  
  
• Integrated Project, FP6: AceMedia -- Integrating knowledge, semantics and content for user-centered intelligent media services.
  Partners: Motorola Ldt (prime), Philips Research, Thomson, Queen Mary University of London, Fraunhofer FIT, Universidad Autónoma de Madrid, Alinari, Telefónica Investigación y Desarollo, Dublin City University, CERTH-ITI, INRIA, France Télécom R&D, Belgavox, Karlsruhe University, Motorola Semiconductor SAS.
  Goal: Embedd smart media-tailored code within muldimedia documents to automatically adapt to varying users, network, display or encoding constraints.