Publications - Visual scene understanding français
Research
Videos

2017

  • F. Chabot ,M. Chaouch ,J. Rabarisoa ,C. Teulière ,T. Chateau, Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular image, to appear in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017.
  • F. Chabot ,M. Chaouch ,J. Rabarisoa ,C. Teulière ,T. Chateau, Deep Edge-color invariant features for 2D/3D car fine-grained classification, to appear in IEEE Intelligent Vehicle Symposium (IV) , 2017.
  • G. Vaquette, A. Orcesi, L. Lucat, C. Achard, The DAily Home LIfe Activity Dataset: A High Semantic Activity Dataset for Online Recognition, to appear in IEEE Automatic Face and Gesture Recognition (FG), 2017.

2016

  • H. Fradi, B. Luvison, Q.C. Pham, Crowd behavior analysis using local mid-level visual descriptors, to appear in IEEE Transactions Transactions on Circuits and Systems for Video Technology (TCSVT), special issue on "Group and Crowd Behavior Analysis for Intelligent Multi-camera Video Surveillance", 2016.
  • L. Fagot-Bouquet, R. Audigier, R. Dhome, F. Lerasle, Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object Tracking, in European Conference on Computer Vision (ECCV), 2016.
  • G. Vaquette, C. Achard and L. Lucat, Robust information fusion in the DOHT paradigm for real time action detection, to appear in Journal of Real-Time Image Processing, 2016.
  • S. Chan Lang, Q.C. Pham, C. Achard, Bidirectional sparse representations for multi-shot person re-identification, in IEEE Advanced Video and Signal-based Surveillance (AVSS), 2016.
  • F. Chabot, M. Chaouch, J. Rabarisoa, T. Chateau and C. Teulière, Accurate 3D car pose estimation, in IEEE International Conference on Image Processing (ICIP), 2016.
  • F. Chabot, M. Chaouch, J. Rabarisoa, C. Teulière et T. Chateau. Descripteurs profonds communs aux couleurs et aux contours pour la reconnaissance fine 2D/3D de véhicules, in Reconnaissance des Formes et l'Intelligence Artificielle (RFIA), 2016.
  • G. Vaquette, C. Achard, L. Lucat, Information fusion for action recognition with deeply optimised Hough transform paradigm, in International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP (4: VISAPP), 2016.
  • P.C. Ribeiro, R. Audigier and Q.C. Pham, RIMOC, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance, in Computer Vision and Image Understanding, Pages 1 - 23, 2016, doi:10.1016/j.cviu.2015.11.001

2015

  • L. Fagot-Bouquet, R. Audigier, Y. Dhome and F. Lerasle, Online multi-person tracking based on global sparse collaborative representations, In ICIP , 2015.
  • L. Fagot-Bouquet, R. Audigier, Y. Dhome and F. Lerasle, Suivi multi-personnes à base de représentations parcimonieuses collaboratives globales, in ORASIS , 2015.
  • F. Chabot ,M. Chaouch, J. Rabarisoa, T. Chateau and C. Teulière, Détection de pose de véhicule pour la reconnaissance de marque et modèle, in ORASIS , 2015.
  • P. Paillet, R. Audigier, F. Lerasle and Q.C. Pham, Collaborative Tracking and Distributed Control for an IP-PTZ Camera Network, in International Conference on Pattern Recognition Applications and Methods (ICPRAM), 2015.
  • L. Fagot-Bouquet, R. Audigier, Y. Dhome and F. Lerasle, Collaboration and spatialization for an efficient multi-person tracking via sparse representations , In AVSS , 2015.
  • E. Elghoul, A. Verroust-Blondet and M. Chaouch, A Segmentation Transfer Approach for Rigid Models, in Journal of Information Science and Engineering, Volume 31 (3), pp.993-1009, 2015.

2014

  • L. Fagot-Bouquet, J. Rabarisoa, Q.C. Pham, Fast and accurate video annotation using dense motion hypotheses, In IEEE International Conference on Image Processing, pp.3122,3126, 27-30 Oct, 2014.
  • A. Chan-Hon-Tong, C. Achard and L. Lucat, Simultaneous segmentation and classification of human actions in video streams using deeply optimized Hough transform, in Pattern Recognition, Volume 47, Issue 12, December 2014, Pages 3807-3818, ISSN 0031-3203, http://dx.doi.org/10.1016/j.patcog.2014.05.010.
  • H. Odabai Fard, M. Chaouch, Q.C. Pham, A. Vacavant and T. Chateau, Joint Hierarchical Learning for Efficient Multi-class Object Detection, in IEEE WACV, 2014. 
  • H. Odabai Fard, M. Chaouch, Q.C. Pham, A. Vacavant and T. Chateau, Joint Learning for Multi-class Object Detection, in  VISAPP, International Conference on Vision Theory and Applications, 2014.
  • P. Paillet, R. Audigier, F. Lerasle and Q.C. Pham, Perception-prediction-control Architecture for IP Pan-Tilt-Zoom Camera through Interacting Multiple Models, in VISAPP, International Conference on Vision Theory and Applications, 2014.
  • C. Gabard and C. Achard, Hierarchical scene model for Spatial-color Mixture Of Gaussians, Chapter 15 of “Handbook on Background Modeling and Foreground Detection for Video Surveillance”, Ed. T. Bouwmans, Fatih Porikli, Benjamin Höferlin, and A. Vacavant, Chapman and Hall/CRC, Pages 15-1–15-22, Print ISBN: 978-1-4822-0537-4, 2014.

2013

  • P. Paillet, R. Audigier, F. Lerasle and Q.C. Pham, IMM-based Tracking and Latency Control with off-the-shelf IP PTZ Camera, In Advanced Concepts for Intelligent Vision Systems, ACIVS, 2013.
  • P. Paillet, R. Audigier, F. Lerasle and Q.C. Pham, Contrôle de caméra Pan-Tilt-Zoom réseau pour la poursuite d'une cible mobile, In ORASIS, 14ème journées francophones des jeunes chercheurs en vision par ordinateur, 2013. 
  • A. Chan-Hon-Tong,N. Ballas, C. Achard, B. Delezoide, L. Lucat, P. Sayd and F. Prêteux, Skeleton Point Trajectories for Human Daily Activity Recognition,In International Conference on Computer Vision Theory and Application (VISAPP) , pp. 520-529, 2013
  • A. Chan-Hon-Tong, C. Achard and L. Lucat, Deeply Optimized Hough Transform: Application to Action Segmentation, In International Conference on Image Analysis and Processing (ICIAP), pp. 51-60, 2013. 
  • A. Chan-Hon-Tong, C. Achard and L. Lucat, Transformée de Hough sans a priori pour la segmentation, In GRETSI , 2013. 
  • H. Odabai Fard, Q.C. Pham, M. Chaouch, A. Vacavant and T. Chateau, Détection hiérarchique multi-classes d’objets dans les images, In ORASIS, 2013.
  • E. Elghoul, A. Verroust-Blondet and M. Chaouch, Segmentation par l’exemple de modèles 3D rigides, In CORESA, 2013.
  • T. Chesnais, T. Chateau, Nicolas Allezard, Y. Dhome, Boris Meden, M. Tamaazousti, A. Chan-Hon-Tong, A Region Driven and Contextualized Pedestrian Detector, in VISAPP 2013, pp796-799, 2013

2012

  • Y. Dhome, B. Luvison, T. Chesnais, R. Belaroussi, L. Lucat, M. Chaouch and P. Sayd, Detection of Objects of Interest, In J-Y Dufour editor, Intelligent Video Surveillance Systems, Pages 103-122, Wiley, ISBN 978-1-84821-433-0, 2012.
  • S. Maggio, J.-E. Haugeard, B. Meden, B. Luvison, R. Audigier, B. Burger and Q.C. Pham, Tracking of Objects of Interest in a Sequence of Images, In J-Y Dufour editor, Intelligent Video Surveillance Systems, Pages 123-142, Wiley, ISBN 978-1-84821-433-0. 2012.
  • C.Gabard, L.Lucat, C.Achard, P.Sayd, Hierarchical and spatial-colorimetric model to detect moving targets. In VISAPP 2012, February 2012.
  • B. Meden, F. Lerasle, P. Sayd, Tracking by reidentification in a non-overlapping fields of view cameras network. In VISAPP 2012, February 2012.
  • T. Chesnais, N. Allezard, Y. Dhome, T. Château, Automatic process to build a contextualized detector. In VISAPP 2012, February 2012.
  • L. Jourdheuil, N. Allezard, T. Château, Heterogeneous Adaboost with real-time constraints. In VISAPP 2012,February 2012.
  • L. Jourdheuil, N. Allezard, T. Château, Adaboost discret hétérogène à contrainte temps réel : application à la détection de piétons par stéréovision. In RFIA 2012, Janvier 2012.
  • C. Guillot, Q.-C. Pham, P. Sayd, C. Tilmant, J.-M. Lavest. Détection et localisation d’objets stationnaires par une paire de caméras PTZ. In RFIA 2012, Janvier 2012.
  • B. Meden, F. Lerasle, P. Sayd, Suivi par ré-identification dans un réseau de caméras à champs disjoints. RFIA 2012, Janvier 2012
  • T. Chesnais, N. Allezard, Y. Dhome, T. Château, Création automatique d’un détecteur adapté à la scène. In RFIA 2012, Janvier 2012.

2011

  • B. Meden, F. Lerasle, P. Sayd, Mixed-State Particle Filtering for Simultaneous Tracking and Re-Identification in Non-Overlapping Camera Networks. In Proceedings of the Scandinavian Conference on Image Analysis, Vol. LNCS 6688:124--133, Springer, 2011.
  • B. Meden, F. Lerasle, P. Sayd, Mixed-State CONDENSATION pour suivi et ré-identification simultanés dans des réseaux de caméras à champs de vue disjoints. In ORASIS 2011.
  • C.Gabard, L.Lucat, C.Achard, P.Sayd, Amélioration de la soustraction de fond par analyse des modèles statistiques. In ORASIS, 2011

2010

  • C.Gabard, L.Lucat, C.Achard, P.Sayd, Error decreasing of background subtraction process by modeling the foreground. In ACCV workshop on Visual Surveillance. 2010
  • C.Guillot, M.Taron, P.Sayd, Q.-C.Pham, C.Tilmant, J.M.Lavest. Background subtraction for PTZ cameras performing a guard tour and application to cameras with very low frame rate. In ACCV workshop on Visual Surveillance. 2010
  • Y.Dhome, C.Gabard et al., A survey and comparison of background subtraction algorithms in monocular vision. In IPTA, 2010.
  • L.Lucat, Y.Dhome, P.Sayd., Elderly people assistance using video monitoring. In Handicap 2010.
  • C.Guillot, M.Taron, P.Sayd, Q.-C.Pham, C.Tilmant, J.M.Lavest. Background subtraction adapted to PTZ cameras by keypoint density estimation. In BMVC, 2010.
  • C.Guillot, M.Taron, P.Sayd, Q.-C.Pham, C.Tilmant, J.M.Lavest. Soustraction de fond adaptée aux caméras PTZ par densité de points d'intérêt, in RFIA atelier Vidéo-surveillance Intelligente : Systèmes et AlGorithmES (VISAGES 2010), 2010.
  • B. Luvison, C. Chateau, P.Sayd, Q.-C.Pham and J.T. Lapresté. Estimation Parcimonieuse de Densité par Fonctions Noyaux : Application à la Détection Temps Réel d'Evènements Rares. In RFIA, 2010.

2009

  • L.Gond, P.Sayd, T.Chateau and M.Dhome. A regression-based approach to recover human pose from voxel data. In ICCV Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS2009), 2009.
  • B. Luvison, C. Chateau, Patrick Sayd, Q.C. Pham and J.T. Lapresté. An Unsupervised Learning Based Approach For Unexpected Event Detection, In VISAPP, 2009.
  • B. Luvison, C. Chateau, Patrick Sayd, Q.C. Pham and J.T. Lapresté. Méthode d'apprentissage non supervisée pour la détection d'évènements inattendus. In CORESA, 2009.

2008

  • J. Bégard, N. N. Allezard, P. Sayd, Real-Time Human Detection in Urban Scenes: Local Descriptors and Classifiers Selection with AdaBoost-like Algorithms, in OTCBVS'08, Anchorage, Alaska, June 2008
  • J. Bégard, N. Allezard, P. Sayd, Détection de piétons temps-réel en milieu urbain, in 16ème Congrès Francophone AFRIF-AFIA de Reconnaissance des Formes et Intelligence Artificielle (RFIA), 2008
  • L. Gond, Q.C. Pham, J. Bégard, N. Allezard, P. Sayd, Analyse temps réel des postures humaines dans une foule avec des images infrarouges, in Workshop Interdisciplinaire sur la Sécurité Globale (WISG), 2008
  • L. Gond, Q.C. Pham, J. Bégard, N. Allezard , P. Sayd, Imagerie infrarouge pour la surveillance de foules, in 16ème Congrès Francophone AFRIF-AFIA de Reconnaissance des Formes et Intelligence Artificielle (RFIA) , 2008
  • L. Gond, P. Sayd, T. Chateau, M. Dhome, A 3D shape descriptor for human pose recovery, in Conference on Articulated Motion and Deformable Objects, Andratx, Mallorca, Spain, 2008.
  • Q.C. Pham, Y.Dhome, L. Gond P. Sayd, Video Monitoring of Vulnerable People in Home Environmentin proc. of the 6th International Conference On Smart homes and health Telematics, Ames, IOWA, June 2008
  • J. Badri, C. Tilmant, J.-M. Lavest, Q.-C. Pham et P. Sayd. Automatic calibration of hybrid dynamic vision system for high resolution object tracking, Book chapter in Pattern Recognition : Techniques, Technology and Applications, I-Tech Education and Publishing, Vienna, Austria, 2008.

2007

  • J. Badri, C. Tilmant, J.M. Lavest, Q.C. Pham, P. Sayd, Camera-to-Camera Mapping for Hybrid Pan-Tilt-Zoom Sensors calibration, in SCIA - Scandinavian Conference on Image Analysis, 2007
  • J. Badri, C. Tilmant, J.M. Lavest, Q.C. Pham, P. Sayd, Hybrid Dynamic Sensors Calibration From Camera-to-Camera Mapping : an Automatic Approach, in VISAPP Second International Conference on Computer Vision Theory and Applications, 2007
  • J. Badri, C. Tilmant, J.M. Lavest, Q.C. Pham, P. Sayd, Hybrid sensors calibration : Application to pattern recognition and tracking, in WISP 2007 - IEEE International Symposium on Intelligent Signal Processing, 2007.
  • J. Badri, C. Tilmant, J.M. Lavest, Q.C. Pham, P. Sayd, Mise en relation caméra à caméra pour le calibrage de capteurs hétérogènes avec une caméra Pan-Tilt-Zoom, in ORASIS 2007 - congrès francophone des jeunes chercheurs en vision par ordinateur, 2007
  • J. Bégard, N. Allezard, P. Sayd, Real-Time Humans Detection in Urban Scenes, in BMVC, 2007.
  • Q.C. Pham, L. Gond, J. Bégard, N. Allezard, P. Sayd, Real-Time Posture Analysis in a Crowd using Thermal Imaging, in CVPR Workshop on Visual Surveillance, 2007.