Quaero: five years of scientific excellence

 

  • More than 800 publications including 70 scientific journals, magazines and books.
  • Participation in more than 200 conferences and workshops worldwide, including more than 50 in France. Interactive maps of the conferences and workshops: map of the world, map of France.
  • 50 current theses among which 30 will be supported before the end of the program
  • 70 participations in national and international evaluation campaigns (mostly ranked in the top 3)
  • 25 scientific awards (best paper, young researcher award, thesis prize,  CNRS crystal medal) and industrial awards (ACM Multi-media  Grand Challenge, Golden Mobile Award, TV Innovations Awards at CES 2012, etc.)
  • 12 Corpora made available to the scientific community
 
 
Thesis Evaluation campaigns Publications Awards Available corpora
 
Ph. D Laboratory/Company Title Director Date Research field
Alhalah Ziad KIT   Rainer Stiefelhagen 01/04/2011  
Ben Abacha, Asma LIMSI Finding precise answers to medical questions: the question-answering system MEANS Pierre Zweigenbaum 1/10/2008 – 1/05/2012 Question answering – Information extraction – Information retrieval – Natural Language Processing – Medical Informatics
Bender, Oliver RWTH Robust Machine Translation for Multi-Domain Tasks Hermann Ney, Francisco Casacuberta 1/01/2003 – 1/10/2008 Natural language processing, statistical machine translation
Ben Jabeur, Lamjed IRIT Leveraging social relevance: Using social networks to enhance literature access and microblog search Lynda Tamine, Mohand Boughanem 01/09/2009- 08/10/2013  Information retrieval, Social networks
Bluche, Theodore A2ia/RWTH/LIMSI New models based on networks of neurons and hidden Markov models for  recognition of manuscript writing in wide vocabulary Prof Hermann Ney, Dr. Christopher Kermorvant 1/12/2011 – 1/12/2014 Computer Science – Machine Learning
Codocedo, Victor Inria Extracting and Using Knowledge for guiding Information Retrieval and Recommendation Amedeo Napoli 1/07/2011 – 30/06/2014 Information Retrieval, Artificial Intelligence
Derbas, Nadia UJF Event Detection in videos Georges Quénot 1/11/2010 – 1/11/2013 Semantic indexing, video indexing
Ebadat, Ali Reza Inria Toward Robust Information  Extraction Models for Multimedia Documents Vincent Claveau, Pascale Sébillot 1/10/2009 – 30/09/2012 Machine Learning, Text mining, Information Extraction, Natural Language Processing
Ekenel, Hazim Kemal KIT A Robust Face Recognition Algorithm for Real-World Applications Alex Waibel, Josef Kittler 1/06/2004 – 1/02/2009 Computer vision, pattern recognition
Fayolle, Julien INRIA-TEXMEX Lexical-phonetic representations for spoken indexing and retrieval Fabienne Moreau, Christian Raymond, Guillaume Gravier, Patrick Gros 12/10/2009 – 11/04/2013 Spoken Content Extraction and Retrieval; Information Retrieval; Natural Language Processing; Automatic Speech Recognition
Fenet, Sébastien Telecom ParisTech Quasi-exact Audio Identification Methods and approached by print extraction Gaël Richard 1/01/2010 – 1/01/2013 Audio Signal Processing
Fischer, Mika KIT Method for face identification from different viewpoints Hazım Kemal Ekenel, Rainer Stiefelhagen 01/06/2008  
Fortun, Denis Inria Optical flow estimation for live cell imaging Charles Kervrann 2/11/2010 – 31/12/2013 computer vision, optical flow
Foucard, Rémi Telecom ParisTech   Gaël Richard 1/10/2009 – 1/10/2012  
Fraga da Silva, Thiago LIMSI Learning methods for Speech Recognition Jean-Luc Gauvain 1/09/2010 – 1/09/2013 Unsupervised training
Galibert, Olivier LIMSI  Approaches and methodologies for the automatic answer to questions adapted to an interactive framework in open field  Martine Adda  01/10/2008 – 04/06/2009  Information retrieval
Gao Hua KIT Discriminative Appearance Models for Face Alignment Rainer Stiefelhagen, Timothy F. Cootes, Hazim Kemal Ekenel 15/07/2008 – 30/06/2013 Facial image alignment, Facial feature detection, Face recognition
Gudmundsson, Gylfi Inria Parallelism and Distribution for Very Large Scale Content-Based Multimedia Retrieval Systems Patrick Gros, Laurent Amsaleg 25/03/2010 – 24/03/2013 Content-based Image Retrieval, Distributed computing
Guinaudeau, Camille Inria Automatic Structuring of TV Stream Pascale Sébillot, Guillaume Gravier 1/10/2008 – 1/10/2011 Natural Language Processing, Spoken Language Processing & Multimedia Document Structuring
Hahn, Stefan RWTH Monotone string-to-string translation for grapheme-to-phoneme conversion and concept tagging Prof Hermann Ney 01/05/2006 Automatic Speech Recognition, Statistical Monotone

Translation, Grapheme-to-Phoneme Conversion, Natural Language

Understanding, particularly concept tagging

Hamadi, Abdelkader UJF Using context for semantic indexing of images and videos Georges Quénot, Philippe Mulhem 1/11/2010 – 1/10/2013 Information indexing and retrieval, classification, fusion
Hasan, Saša RWTH Triplet Lexicon Models for Statistical Machine Translation Prof Hermann Ney 1/09/2003 – 1/09/2009 machine translation, lexicon modeling, natural language processing, pattern recognition
Huck, Matthias RWTH   Hermann Ney 01/09/2008 Statistical Machine Translation
Karanasou, Panagiota LIMSI Exploration of a variety of approaches to improve pronunciation modeling for automatic speech recognition Lori Lamel, François Yvon 1/09/2009 – 1/06/2013 Pronunciation modelling, speech recognition, machine learning
Fort, Karën INIST   Adeline Nazarenko 1/12/2008 – 1/10/2012 Natural Language Processing
Lehnen, Patrick RWTH Extending Conditional Random fields for Natural Language Processing Prof Hermann Ney 01/07/2007  
Leusch, Gregor RWTH Evaluation and System Combination in Machine Translation Prof Hermann Ney 1/12/2005 – 1/11/2011  
Liutkus, Antoine Telecom ParisTech Informed separation of sources Roland Badeau, Gaël Richard 1/01/2010 – 2013  
Amr Ibrahim El-Desoky, Mousa RWTH Large vocabulary continuous speech recognition: language modeling Prof Hermann Ney 01/04/2007  
Mouton, Claire LIMSI/Exalead/CEA Resources and Semi-Supervised Methods for the Semantic Analysis of French Text Anne Vilnat, Gael de Chalendar, Gregory Grefenstette 1/01/2008 – 1/12/2010 Semantic analysis of text
Muscariello, Armando Inria Variability tolerant discovery of arbitrary repeating patterns in audio data with template matching Guillaume Gravier, Frédéric Bimbot 1/11/2007 – 31/01/2011 Unsupervised, language and domain-independent, not model-based speech processing
Nussbaum-Thom, Markus RWTH     01/08/2008 Unsupervised, language and domain-independent, not model-based speech processing
Oneata, Dan Inria Automatic annotation of videos with semantically meaningful terms Cordelia Schmid, Jakob Verbeek 17/10/2011 – 30/04/2013 Computer vision, machine learning
Papadopoulos, Hélène IRCAM, University Paris VI Joint Estimation of Musical Content Information Cordelia Schmid, Jakob Verbeek End: 1/07/2010 Computer vision, machine learning
Peitz, Stephan RWTH   Hermann Ney 01/07/2010  
Plahl, Christian RWTH Neural Network based Feature Extraction Speech and Image Recognition Prof Dr. - Ing. Hermann Ney, PD Dr. - Ing. habil. Björn W. Schuller 1/11/2005 – 19/02/2013 Speech recognition, neural networks
Poignant, Johann UJF Person recognition from audiovisual broadcasts Laurent Besacier, Georges Quénot 1/11/2011 – 1/11/2013 multi-modal fusion, video OCR, persons recognition in audio-visual documents
Potapov, Danila Inria Learning video from data Cordelia Schmid, Zaid Harchaoui 1/09/2011 – 31/08/2014 Computer vision and machine learning
Prest, Alessandro Inria Weakly supervised methods for learning actions and objects Vittorio Ferrari, Cordelia Schmid 1/03/2010 – 30/11/2011 Video Analysis, Object detection, Action Recognition
Ratkovic, Zorana INRA Predicative analysis for information extraction: application to the biology domain Claire Nédellec, Thierry Poibeau 1/10/2010 – 1/10/2013 computational linguistics
Rybach, David RWTH Search Techniques for Speech Recognition with Weighted Finite-State Transducers Prof Hermann Ney 01/10/2006  
Safadi, Bahjat UJF Image and Video Semantic Indexing by Active Learning Georges Quénot 1/04/2009 – 1/03/2012 Information Retrieval, Multimedia Indexing, Annotations, Machine Learning, Active Learning, Evaluation
Sargent, Gabriel PANAMA Research Team (ex-METISS), IRISA, Rennes Music structure estimate by multi-criteria analysis and regularity constraint Frédéric Bimbot, Emmanuel Vincent 1/11/2009 – 1/02/2013 Music Information Retrieval
Sundermeyer, Martin RWTH Language modeling Prof Hermann Ney 01/11/2008 Language modeling
Tapaswi, Makarand KIT Semantic Analysis and Understanding of Multimedia Videos Rainer Stiefelhagen 10/1/2011 – 2015-16 (expected) Multimedia analysis using textual information, Person identification in multimedia data
Ullah, Muhammad Muneeb Inria Supervised Statistical Representations for Human Action Recognition in Video Ivan Laptev, Patrick Perez 2/03/2009 – 30/06/2012 Computer Vision
Valsamou, Dialekti INRA MIG, LIMSI-CNRS Information extraction from scientific articles for the reconstruction of the biological regulatory network during the seed development phase of Arabidopsis Thaliana Claire Nédellec, Pierre Zweigenbaum 1/01/2012 – 1/07/2015 Information extraction from scientific articles on biology
Vo, Dong-Bach Telecom ParisTech Design and evaluation of new interaction techniques for interactive television Eric Lecolinet 1/12/2009 – 1/11/2012 Human-computer interaction
Wiesler, Simon RWTH Optimization of discriminative models for automatic speech recognition Hermann Ney 1/10/2008 – 1/10/2014 automatic speech recognition

 
Organization Year Campaign
A2iA 2010 OpenHaRT2010 (Not Scored)
A2iA 2011 ICDAR' 11: Ranked 1st  in Worldwide Handwriting Recognition Competition
Beijing, China, September 2011
GREYC 2011 IMAGECLEF 2011: 2nd Place – Photo Annotation Task (recognition of concepts by image)
Amsterdam, The Netherlands, September 2011
GREYC   “Labeled Faces in the News”: similarity between faces
GREYC   FERRET: face recognition
GREYC   JAFFE: recognition of facial expression
GREYC   VIPER + iLIDS: reidentification of people in videos
GREYC   HATDB: recognition of features specific to people
INRA 2011 Best result at BioNLP ST' 11, BB Task.
Inria 2008 Excellent Results on Trecvid 2008 copy detection task, Inria Lear
Gaithersburg, USA, November 2008
Inria 2008 1st in PASCAL Visual Object Classes Challenge (VOC2008)
Marseille, France, March 2008
Inria 2009 ImageCLEF' 09 second place among the 19 participating teams for Photo Annotation and Image Retrieval tasks – Inria Lear
Corfu, Greece, September-October 2009
Inria 2010 PASCAL VOC 2010: INRIA-LEAR' S work on human action recognition achieved best results on three out of nine action classes, and best average results.
Inria 2012 TRECVID MED challenge 2012: First and second. The Multimedia Event Detection (MED) evaluation track is part of the TRECVID Evaluation.
IRCAM 2008 Best results in several categories at MIREX 2008
Philadelphia, USA, September 2008
IRCAM 2009 MIREX' 09
Kobe, Japan, October 2009
IRCAM 2010 1st rank at MIREX' 10 in several different categories
Utrecht, The Netherlands, August 2010
IRCAM 2011 1st rank at MIREX' 11 in several different categories
Miami, USA, October 2011
IRCAM 2012 1st rank at MIREX' 12 in several different categories
Porto, Portugal, October 2012
IRIT 2012 TREC' 12: Ranked 1st out of 14 participants for the two official measures (P@5 and MRR). “Contextual Suggestion” task
Gaithersburg, the USA, November 2012
JOUVE 2010 2nd rank in CLEF-IP evaluation campaign
Padua, Italy, September 2010
JOUVE 2011 ICDAR 2011: 1st in category “Historical Document Layout Analysis”
Beijing, China, September 2011
KIT 2011 IWSLT Talk Task ASR Evaluation, 2011 second place, MT first place
San Francisco, USA, December 2011
KIT 2011 WMT 2011,3 times constrained winner
Edinburgh, UK, July 2011
KIT 2012 IWSLT Talk Task Evaluation, 2012, second place, SLT-Task first place
Hong Kong, December 2012
KIT 2012 WMT 2012, 4 times constrained winner
Montreal, Canada, June 2012
LIMSI 2008 1st in QA@CLEF ' 08 (main track and audio track – QAST evaluation)
Aarhus, Denmark, September 2008
LIMSI 2008 CLEF' 08: LIMSI system ranked 1st in Answer Validation Exercise (AVE) 2008 for French, 2nd among all systems (all languages)
Aarhus, Denmark, September 2008
LIMSI 2008 Gale 2008, part of the Agile team led by BBN
LIMSI 2008 2008 NIST Speaker Recognition Evaluation
Montreal, Canada, June 2008
LIMSI 2009 1st in QA@CLEF ' 09 (main track and audio track – QAST evaluation)
Corfu, Greece, September-October 2009
LIMSI 2009 Ester2 evaluation campaign 2009 (segmentation, speaker diarization, STT, top ranked results for all submissions)
LIMSI 2009 Gale 2009, part of the Agile team led by BBN
LIMSI 2009 2009 Language Recognition Evaluation
LIMSI 2010 Gale 2010, part of the Agile team led by BBN
LIMSI 2010 2010 NIST Speaker Recognition Evaluation
LIMSI 2011 Gale 2011, part of the Agile team led by BBN
LIMSI 2011 2011 Language Recognition Evaluation
LIMSI 2011 WMT 2011: Best MT system for English to French translation
Edinburgh, UK, July 2011
LIMSI 2011 IWSLT 2011: Best MT system for English to French translation
San Francisco, USA, December 2011
LIMSI 2012 2012 NIST Speaker Recognition Evaluation
LIMSI 2012 REPERE dry run
January 2012
LIMSI 2012 WMT' 12: 1st French/English MT system
Montreal, Canada, June 2012
LIMSI   Etape Speaker diarization, Named entities
LIMSI/RWTH/KIT/Systran 2011 Jointly (with Aachen, KIT and Systran) best German/English system At WMT 2011
Edimbourg, UK, July 2011
LIMSI/RWTH/KIT/Systran 2012 Jointly (with Aachen, KIT and Systran) best German/English system at WMT 2012
Montreal, Canada, June 2012
LIMSI/Vocapia 2008 1st in Technolangue ESTER' 08
Aarhus, Denmark, September 2008
LIMSI/Vocapia 2008 NBest 2008 with Vocapia (top ranked results for all submissions)
LIMSI/Vocapia 2011 1st rank at ASR benchmark task of Evalita 2011
RWTH 2009 3rd At the ICDAR' 09 Arabic Handwriting Recognition Competition
Barcelona, Spain, July 2009
RWTH 2010 BLUE Best Score for English to German translation in the WMT 2010 Shared Translation Task and many other top positions in translation and system combination tasks
Uppsala, Sweden, July 2010
RWTH 2010 2nd rank in ICFHR 2010 (Arabic Handwriting Recognition Competition)
Kolkata, India, November 2010
RWTH 2010 2nd rank in IWSLT 2010: BTEC Arabic to English translation task among 13 participants, according to the automatic evaluation
Paris, France, December 2010
RWTH 2012 IWSLT 2012: RWTH best system (Ar->En)
Hong Kong, December 2012
Synapse 2008 1st in QA@CLEF ' 08 (main track and audio track – QAST evaluation)
Aarhus, Denmark, September 2008
Synapse 2009 1st in QA@CLEF ' 09 (main track and audio track – QAST evaluation)
Corfu, Greece, September-October 2009
Télécom ParisTech 2008 Participation to MIREX' 08 Evaluation campaign
Multiple Fundamental Frequency Estimate & Tracking (Rank 5th/10)
Philadelphia, USA, September 2008
Télécom ParisTech 2008 Participation to MIREX' 08 Evaluation campaign
Melody Extraction (Rank 2nd/5)
Philadelphia, USA, September 2008
Télécom ParisTech 2008 Participation in the 2008 French evaluation campaign ESTER 2 one audio segmentation task (very good results)
Télécom ParisTech 2009 MIREX' 09 evaluation campaign: Chord Detection (rank 2nd/9 for score 1, rank 1st/8 for score 2)
Kobe, Japan, October 2009
Télécom ParisTech 2009 MIREX' 09 evaluation campaign: Melody Extraction (rank 2nd/9)
Kobe, Japan, October 2009
Télécom ParisTech 2010 MIREX' 10 evaluation campaign: Chord Detection (Rank 7th/12)
Utrecht, The Netherlands, August 2010
Télécom ParisTech 2011 MIREX' 11 evaluation campaign: Beat Tracking (Rank 2nd/6 on MCK dataset)
Miami, USA, October 2011
Télécom ParisTech 2011 Participation in SiSEC 2011 Signal Separation Evaluation Campaign (The technique was the only one able of achieving high performances on large files).
Télécom ParisTech 2012 Participation in MIREX' 12 evaluation campaign: Beat Tracking (Rank 3rd/9 on MCK dataset)
Porto, Portugal, October 2012
Télécom ParisTech 2012 Participation in MIREX' 12 evaluation campaign: Multiple Fundamental Frequency Estimation & Tracking (Rank 1st/6 on Note tracking task)
Porto, Portugal, October 2012
Université Joseph Fourier 2011 3rd at the TRECVID semantic indexing task in 2011
Université Joseph Fourier 2012 3rd at the TRECVID semantic indexing task in 2011 and 2012

 

Research

 
Organization Year Awards
Exalead 2009 « Most Practical presentation » at the ACM Multimedia Grand Challenge 2009 Beijing, China, October 2009
Exalead 2010 3rd at ACM Multimedia Grand Challenge 2010 – Florence, Italy, October 2010
Exalead 2011 META-Prize for outstanding contribution to a multilingual Europe – Budapest, Hungary, June 2011
INRIA 2010 3rd at ACM Multimedia Grand Challenge 2010 – Florence, Italy, October 2010
INRIA 2008 Amongst the 5 finalists in the STAR Challenge 2008 – Singapore, October 2008
INRIA 2010 Best demo award at the RFIA 2010 conference – Caen, France, January 2010
INRIA 2010 Prix Bretagne Jeunes Chercheurs 2010 in « Science, technology and interdisciplinarity » to Hervé Jégou – Brittany, France, 2010
KIT 2012 Alcatel-Lucent Research Award 2012 for Technical Communication for Tanja Schultz – Stuttgart, Germany, October 2012
KIT 2008 Best Demo Award at the IEEE International Conference on Automatic Face and Gesture Recognition 2008 (FG’08) – Amsterdam, The Netherlands, September 2008
KIT 2012 Best Scientific Paper Award at the 21st International Conference on Pattern Recognition (ICPR 2012) – Tsukuba, Japan, November 2012
KIT 2012 Best Student Paper Award at the 12th IEEE Workshop on the Applications of Computer Vision (WACV 2012) – Breckenridge, CO, USA, January 2012
KIT 2010 Finalist for the Best Paper Award, AVSS’10 – Boston, MA, USA, September 2010
KIT 2008 «EBF European Research Award 2008″ for Hazim Kemal Ekenel – Brussels, Belgium, October 2008
LIMSI 2010 3rd at ACM Multimedia Grand Challenge 2010 – Florence, Italy, October 2010
LIMSI 2010 CNRS Crystal medal 2010 for Gilles Adda – Paris, France, February 2010
LIMSI 2009 Most Practical presentation at ACM Multimedia Grand Challenge 2009 – Beijing, China, October 2009
LTU Technologies 2011 Best use of NY times API at the Times Open Hack Day 2011 – New York, NY, USA, December 2011
LTU Technologies 2010 Golden Mobile Award 2010
Paris, France, November 2010
Movea 2011 ConnectedWorldTV Awards 2011 at IBC – Finalist for Building Block Award with MoveTV
Movea 2011 CSI Awards at IBC - Finalist for Best Interactive TV Technology gold Application for MoveTV
Movea 2012 TV Innovations Awards at CES 2012-Finalist for Immersive TV for MoveTV
Movea 2012 UBM Ace Award Finalist 2012
RWTH 2009 Best student paper award at ASRU' 09 – Merano, Italy, December 2009
RWTH 2012 Hermann Ney: ISCA Distinguished Lecturer 2012
Télécom ParisTech 2010 Thesis Prize 2010 Signal-Image-Vision for Nancy Bertin – Paris, France, June 2010
Université Joseph Fourier 2008 Amongst the 5 finalists in the STAR Challenge 2008 Singapore, October 2008
Vocapia 2010 3rd at ACM Multimedia Grand Challenge 2010
Vocapia 2012 Meta Seal of recognition awarded to VoxSigma software suite – June 2012
Technicolor – INRIA – IRISA 2013 Best paper award at CBMI' 13, 11th International Workshop one Content Based Multimedia Indexing

 
Corpus Description Link and contact
Quaero Old Press Extended Named Entity corpus (WP 3.2-2) This corpus consists of the manual annotation of 76 newspaper issues published in 1890-1891 and provided by the French National Library (Bibliothèque Nationale de France). Three different titles are used (Le Temps, La Croix and Le Figaro) for a total of 295 pages. The corpus is fully manually annotated according to the Quaero extended and structured named entity definition.

Sophie Rosset (LIMSI-CNRS)
rosset@limsi.fr

Catalog Reference: ELRA-W0073

 

Broadcast News Extended Named Entity corpus (WP 3.2-3) This corpus consists of the manual annotation of (i) the ESTER 2 (see also ELRA-S0338) manual transcription corpus and (ii) the Quaero Speech Recognition Evaluation corpus (manual and automatic transcriptions coming from 3 different ASR systems). The corpus is fully manually annotated according to the Quaero extended and structured named entity definition.

Sophie Rosset (LIMSI-CNRS)
rosset@limsi.fr

Catalog Reference: ELRA-S0349

Named Entity Recognition in Modern/Contemporary Newspapers (WP 3.2-5) Annotation Corpus on contemporary press, associated with a gender transfer study and debates in French and English. Sophie Rosset (LIMSI-CNRS)
rosset@limsi.fr
Q&A Systems (WP 3.5) Corpus of 2000 spoken and written questions, associated with answers and documents Sophie Rosset (LIMSI-CNRS)
rosset@limsi.fr
Music Content Extraction (WP 6.2) The QUASI corpus (QUaero Audio Signals) was made publicly available for research in the area of music content description.

Gaël Richard (GET)
gael.richard@telecom-paristech.fr

http://www.tsi.telecom-paristech.fr/aao/en/2012/03/12/quasi/

Music Structure/Summary (WP 6.5) Music tracks in the form of PCM, 16bit, 44.1 audio Khz signal. Music structure: small size database (200) of music titles
Music summary generation: medium size database (1000) of music titles

 Fréderic Bimbot (INRIA)

frederic.bimbot@irisa.fr

The Quaero Still Images Dataset (WP 8.1) This corpus contains 518 visual concepts, with about 1000 images per concept. The concepts in this dataset are very diverse, including animal, plant, scene, object, event, people and some general concepts. For each concept, at most 1000 images were downloaded by querying Google image search. Images in the dataset were manually annotated as relevant, irrelevant or ambiguous to their corresponding concepts.

Frédéric Jurie (GREYC)
frederic.jurie@unicaen.fr

QUAERO’s visual concepts image dataset

Corpus of TV Programs (WP 9.1)

Audio Track Annotation (WP 9.2)

Still Images (Key Frames) Annotation (WP 9.3)

Image Sequence (Image Track Only) Annotation (WP 9.4)

(Note: Tasks 9.1-9.4 refer to different aspects of the same corpus. – Half of the corpus is INA, half is TRECVID.)

INA part:
Will not be publicly distributed but made available on a case by case basis. Institutes can contact INA directly. E.g. for the BEFIT evaluation, INA has published part of the corpus. In the scientific community, this can be communicated. – Usage after Quaero: the same principle. Concerning the INA part, for distribution outside, one needs an extra license on case by case from INA. One can talk with INA whether they would on case-by-case basis give license.

130 concepts were annotated on the JT_F2 collection and 346 were annotated on the F2_WEEKS collection by UJF-LIG.

Faces were annotated on the JT_F2 collection by KIT (UKA).

Jean Carrive (INA)
jcarrive@ina.fr

 

Georges Quénot (UJF)

Georges.Quenot@imag.fr

Corpus of TV Programs (WP 9.1)

Audio Track Annotation (WP 9.2)

Still Images (Key Frames) Annotation (WP 9.3)

Image Sequence (Image Track Only) Annotation (WP 9.4)

 (Note: Tasks 9.1-9.4 refer to different aspects of the same corpus. – Half of the corpus is INA, half is TRECVID.)

TRECVID part:
There was a significant Quaero contribution to the TRECVID evaluation corpus (in cooperation with NIST). TRECVID 2007-2013 annotations are available. The older corpus (before 2010) has copyright issues but is obsolete given the new corpus.

Georges Quénot (UJF), Georges.Quenot@imag.fr
Video Sequence (Multimodal) Annotation (WP 9.5) Annotations can be published (without the original video material; see task 9.1)
Face tracks and identities for the Big Bang Theory Season 1.17 episodes. Buffy the Vampire Slayer Season 5.22 episodes. Game of Thrones Season 1.10 episodes. Harry Potter one movie.

Rainer Stiefelhagen (UKA/KIT)

rainer.stiefelhagen@kit.edu

Audio, Visual and Audiovisual Corpus for Repurposing Technologies (WP 10.1) Annotated music and video clips as well as advertisings
acquired 24/7 on French TV & radio stations from January 1st 2008.
Political shows and news also acquired 24/7 on radio and TV stations from January 1st 2009
 

Izabela Orlac (Technicolor)
izabela.orlac@technicolor.com