selected publications

• academic article

  • Vision-Text Cross-Modal Fusion for Accurate Video Captioning.  IEEE Access.  11:115477-115492. 2023
  • FasterAI: A Lightweight Library for Neural Networks Compression.  Electronics.  11:3789-3789. 2022
  • Active learning to measure opinion and violence in French newspapers.  Procedia Computer Science.  192:202-211. 2021
  • An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network.  arXiv (Cornell University).  2021
  • DEEP-AD: A Multimodal Temporal Video Segmentation Framework for Online Video Advertising.  IEEE Access.  8:99582-99597. 2020
  • DEEP-HEAR: A Multimodal Subtitle Positioning System Dedicated to Deaf and Hearing-Impaired People.  IEEE Access.  7:88150-88162. 2019
  • DEEP-SEE FACE: A Mobile Face Recognition System Dedicated to Visually Impaired People.  IEEE Access.  6:51975-51985. 2018
  • Laban movement analysis and hidden Markov models for dynamic 3D gesture recognition.  EURASIP Journal on Image and Video Processing.  2017. 2017
  • A computer vision-based perception system for visually impaired.  Multimedia Tools and Applications.  76:11771-11807. 2016
  • Laban descriptors for gesture recognition and emotional analysis.  The Visual Computer.  32:83-98. 2015
  • Scribble-based object segmentation with modified gaussian mixture models.  Pattern Analysis and Applications.  19:593-609. 2014
  • ARTEMIS at TRECVID 2013: Instance Search Task.  HAL (Le Centre pour la Communication Scientifique Directe).  2013
  • ARTEMIS @ MediaEval 2013: A Content - Based Image Clustering Method for Public Image Repositories.  HAL (Le Centre pour la Communication Scientifique Directe).  2013
  • Multi-modal query expansion for video object instances retrieval.  HAL (Le Centre pour la Communication Scientifique Directe).  2013
  • Video Segmentation and Structuring for Indexing Applications.  .  2012
  • 3D Model-Based Semantic Categorization of Still Image 2D Objects.  International Journal of Multimedia Data Engineering and Management.  2:19-37. 2011
  • TFAN: A low complexity 3D mesh compression algorithm.  Computer Animation and Virtual Worlds.  20:343-354. 2009
  • Multiresolution volumetric 3D object reconstruction for collaborative interactions.  Pattern Recognition and Image Analysis.  18:621-637. 2008
  • A skinning approach for dynamic 3D mesh compression.  Computer Animation and Virtual Worlds.  17:337-346. 2006
  • Progressive 3D mesh compression: a B-spline approach.  HAL (Le Centre pour la Communication Scientifique Directe).  2005

• blog posting

  • Induced Feature Selection by Structured Pruning.  arXiv (Cornell University). 2023
  • La plateforme INVENIO.  HAL (Le Centre pour la Communication Scientifique Directe). 2009
  • La plateforme INVENIO.  HAL (Le Centre pour la Communication Scientifique Directe). 2009
  • La plateforme INVENIO.  HAL (Le Centre pour la Communication Scientifique Directe). 2009
  • La plateforme INVENIO.  HAL (Le Centre pour la Communication Scientifique Directe). 2009
  • La plateforme INVENIO.  HAL (Le Centre pour la Communication Scientifique Directe). 2009

• chapter

  • An Industry-Adapted AR Training Method for Manual Assembly Operations.  Lecture notes in computer science. 282-304. 2021
  • Deep Active Learning with Simulated Rationales for Text Classification.  Lecture notes in computer science. 363-379. 2020
  • Public Transportation Prediction with Convolutional Neural Networks.  Springer eBooks. 150-161. 2020
  • Automatic Segmentation of TV News into Stories Using Visual and Temporal Information.  Lecture notes in computer science. 648-660. 2016
  • Using Computer Vision to See.  Lecture notes in computer science. 375-390. 2016
  • 3D Model-Based Semantic Categorization of Still Image 2D Objects.  IGI Global eBooks. 151-169. 2013
  • Video Segmentation and Structuring for Indexing Applications.  IGI Global eBooks. 205-225. 2013
  • OVIDIUS: A Web Platform for Video Browsing and Search.  Lecture notes in computer science. 649-651. 2012
  • Retrieval of Multiple Instances of Objects in Videos.  Lecture notes in computer science. 358-369. 2012
  • Direct Spherical Parameterization of 3D Triangular Meshes Using Local Flattening Operations.  Lecture notes in computer science. 607-618. 2011
  • High Level Video Temporal Segmentation.  Lecture notes in computer science. 224-235. 2011
  • Scene Change Detection with Temporally Constrained Clustering.  ASME Press eBooks. 71-76. 2011
  • Normes de description des contenus multimédias.  . 2007
  • Descripteurs visuels dans le standard MPEG-7.  . 2004

• conference paper

  • Data-Driven Control of a Weakly-Instrumented Excavator with Deep Learning.  . 1-8. 2024
  • Simplification of Continuous Chains in 3D CAD Models for Industrial AR Applications.  . 171-176. 2023
  • Smart AR workstation configuration in industrial assembly lines.  2022 IEEE International Conference on Industrial Technology (ICIT). 1-4. 2023
  • Conditional Cross Correlation Network for Video Question Answering.  . 25-32. 2023
  • A new database for image retrieval of camera filmed printed documents.  . 1-4. 2022
  • Document Segmentation for WebAR application.  . 1-4. 2022
  • Industrial Use-Case : Digital Twin for Autonomous Earthwork in Virtual-Reality.  . 1-4. 2022
  • Affine Transformation-Based Color Compression For Dynamic 3D Point Clouds.  2022 IEEE International Conference on Image Processing (ICIP). 2022
  • One-Cycle Pruning: Pruning Convnets With Tight Training Budget.  2022 IEEE International Conference on Image Processing (ICIP). 2022
  • ATOFIS, an AR Training System for Manual Assembly: A Full Comparative Evaluation against Guides.  . 558-567. 2022
  • Exploring Low-Cost Visual Assets for Conveying Assembly Instructions in AR.  2021 International Conference on INnovations in Intelligent SysTems and Applications (INISTA). 1-6. 2021
  • Fake-buster: a lightweight solution for deepfake detection.  . 2021
  • A Deep Learning-Based Approach for Camera Motion Classification.  . 1-6. 2021
  • Analysis of 3D CAD MESH Simplification Approaches within the Framework of AR Applications for Industrial Assembly Lines.  . 1-6. 2021
  • An AR Work Instructions Authoring Tool for Human-Operated Industrial Assembly Lines.  . 174-183. 2020
  • Skeleton-based motion estimation for Point Cloud Compression.  . 1-6. 2020
  • Real-Time Public Transportation Prediction with Machine Learning Algorithms.  2023 IEEE International Conference on Consumer Electronics (ICCE). 1-4. 2020
  • Dynamic Subtitles: A Multimodal Video Accessibility Enhancement Dedicated to Deaf and Hearing Impaired Users.  . 2558-2566. 2019
  • 3D Point Cloud Compression.  . 2019
  • Image Compression at Very Low Bitrate Based on Deep Learned Super-Resolution.  . 128-133. 2019
  • Face Recognition in Video Streams for Mobile Assistive Devices Dedicated to Visually Impaired.  . 137-142. 2018
  • Single object tracking using offline trained deep regression networks.  . 1-6. 2017
  • Local feature selection for urban image retrieval.  . 1-4. 2017
  • Automatic extraction of story units from TV news.  2023 IEEE International Conference on Consumer Electronics (ICCE). 414-415. 2017
  • Building recognition with adaptive interest point selection.  2023 IEEE International Conference on Consumer Electronics (ICCE). 29-32. 2017
  • Dynamic Gesture Recognition with Laban Movement Analysis and Hidden Markov Models.  . 21-24. 2016
  • Laban movement analysis for real-time 3D gesture recognition.  HAL (Le Centre pour la Communication Scientifique Directe). 2016
  • TV News Retrieval Based on Story Segmentation and Concept Association.  . 327-334. 2016
  • "An Outdoor Cognition System Integrated on a Regular Smartphone Device".  HAL (Le Centre pour la Communication Scientifique Directe). 2015
  • An Obstacle Categorization System for Visually Impaired People.  . 147-154. 2015
  • Efficient graph spanning structures for large database image retrieval.  . 594-598. 2015
  • Buildings detection from lidar data.  . 1-2. 2015
  • A fully automatic framework for building 3D animated avatars.  . 36-40. 2014
  • A gesture expressive model based on Laban qualities.  . 168-172. 2014
  • Multi-object recognition and tracking with feature points matching and spatial layout consistency.  . 355-359. 2014
  • Recognition of urban buildings with spatial consistency and a small-sized vocabulary tree.  . 350-354. 2014
  • Laban movement analysis for action recognition.  HAL (Le Centre pour la Communication Scientifique Directe). 2014
  • Real time static/dynamic obstacle detection for visually impaired persons.  2023 IEEE International Conference on Consumer Electronics (ICCE). 394-395. 2014
  • A pseudo metamesh approach for 3D mesh morphing.  2023 IEEE International Conference on Consumer Electronics (ICCE). 306-309. 2013
  • Dynamic detection of visual entities.  European Signal Processing Conference. 2392-2396. 2012
  • 2D-3D semantic categorization of visual objects.  . 2012
  • 3D Model-Based Sematic Labeling of 2D Objects.  . 152-157. 2011
  • Detection of Multiple Instances of Video Objects.  . 446-453. 2011
  • 3D model-based still image object categorization.  Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 81360C-81360C. 2011
  • Interactive region-based retrieval.  Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 81360E-81360E. 2011
  • A complete framework for temporal video segmentation.  . 156-160. 2011
  • Automatic Multilevel Temporal Video Structuring.  . 387-394. 2011
  • Sill Image Object Categorization Using 2D Objects Models.  . 419-423. 2011
  • Sill image object categorization using 2D models.  . 347-351. 2011
  • Direct Spherical Parameterization Based on Surface Curvature.  . 266-269. 2011
  • Online interactive video content retrieval.  2023 IEEE International Conference on Consumer Electronics (ICCE). 215-216. 2011
  • The INVENIO platform for 2D/3D content re-use.  2023 IEEE International Conference on Consumer Electronics (ICCE). 83-84. 2011
  • A scale-space filtering-based shot detection algorithm.  . 000919-000923. 2010
  • An experimental evaluation of view-based 2D/3D indexing methods.  . 000924-000928. 2010
  • Inter and Intra-Video Navigation and Retrieval with Mobile Devices.  . 2010
  • Mobile video browsing and retrieval with the OVIDIUS platform.  Proceedings of the 30th ACM International Conference on Multimedia. 1659-1662. 2010
  • Mobile video navigation and retrieval services with the OVIDIUS platform.  . 2010
  • An overview of view-based 2D/3D indexing methods.  Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 2010
  • OVIDIUS: an on-line video indexing universal system.  Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 77990C-77990C. 2010
  • INVENIO: An MPEG-7 image indexing platform for content re-use within audio-visual production chains.  . 1-6. 2010
  • OVIDIUS: An on-line video retrieval platform for multi-terminal access.  . 1-6. 2010
  • SC3DMC integration into IM1.  . 2010
  • A Triangle-Fan-based approach for low complexity 3D mesh compression.  . 3513-3516. 2009
  • Les normes MPEG-7 et 21 pour la description des contenus multimédias : indexation et réutilisation en postproduction cinématographique.  HAL (Le Centre pour la Communication Scientifique Directe). 2009
  • Normes MPEG-4 de compression pour les maillages 3D statiques et animés.  . 2009
  • Une évaluation des descripteurs visuels MPEG-7 pour la recherche d'images par le contenu.  . 2009
  • The New MPEG-4/FAMC Standard for Animated 3D Mesh Compression.  3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video. 97-100. 2008
  • FaceTOON: a unified platform for feature-based cartoon expression generation.  Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE. 68050S-68050S. 2008
  • Reconstruction volumétrique multirésolution d'objets 3D.  . 2008
  • Interactive TV on parliament session.  . 2007
  • FAMC : La nouvelle technologie MPEG-4 pour la compression d'animations 3D.  . 2007
  • Modèle de skinning pour la compression de maillages dynamiques 3D.  . 2006
  • Temporal-DCT-based compression of 3D dynamic meshes.  . 2006
  • Compression progressive de maillages 3D par approximation B-spline.  . 2005
  • A multiple B-Spline representation for progressive 3D mesh compression.  71. 2005
  • The TOON platform: an integrated system for automating the 2D cartoon production.  . 57-58. 2005
  • 2D/3D Virtual character registration from a single view: a semi automatic approach for cartoon creation.  HAL (Le Centre pour la Communication Scientifique Directe). 2004
  • 3D Mesh coding techniques applied to CAD data: a comparative evaluation.  HAL (Le Centre pour la Communication Scientifique Directe). 2004
  • Accurate Data Modelling for Watermarking Applications.  HAL (Le Centre pour la Communication Scientifique Directe). 2004
  • Extended study of similarity measures for parametric motion-based retrieval.  HAL (Le Centre pour la Communication Scientifique Directe). 2003
  • Shape-based retrieval of 3D mesh models.  . 437-440. 2003
  • Indexation de maillages 3D par descripteurs de forme.  . 2002
  • Modèles paramétriques de mouvement pour la description des contenus vidéos dans le cadre du futur standard MPEG-7.  . 2002
  • Parametric motion models for video content description within the MPEG-7 framework.  . 2001
  • 3D body animation and coding within a MPEG-4 compliant frameworkP.  . 1999
  • Sign Language Indexation within the MPEG-7 Framework.  . 1999

• document

  • FAMC: bitstream description for the layer-based scalable extension.  . 2007
  • FAMC with progressive transmission and scalable rendering functionalities.  . 2007
  • Results of Core Experiment CE1 on mesh animation compression: skinning-based dynamic mesh compression.  . 2007
  • A new categorization for the MPEG-7 3D model database,.  HAL (Le Centre pour la Communication Scientifique Directe). 2003

• proceedings

  • The 27th International Conference on 3D Web Technology.  . 2022

• report

  • [PCC] TMC2 CE2.8 crosscheck result on absoluteD1 coding method.  HAL (Le Centre pour la Communication Scientifique Directe). 2018