
Christian Wolf
Présentation
Christian WOLF a obtenu un "Diplom Ingenieur der Informatik" de l'Université de Technologie de Vienne en 2000, puis un doctorat en informatique de l'INSA de Lyon en 2003, et l'habilitation à diriger des recherches en 2012, également de l'INSA de Lyon . De septembre 2004 à août 2005, il était Mâitre de Conférences à l'Université Louis Pasteur, Strasbourg et membre du Laboratoire des Sciences de l'Images, de l'Informatique et de la Télédétection (LSIIT). Depuis 2005 il est Maître de Conférences à l'INSA de Lyon et membre du Laboratoire d'Informatique en Images et Systèmes d'Information (LIRIS). Ses activités de recherche portent sur la vision par ordinateur et sur l'apprentissage automatique, particulièrement sur les modèles graphiques, le deep learning, l'interprétation de scènes complexes, la reconnaissance de gestes et d'activités humaines, et sur la vision par ordinateur pour la robotique.
Publications
Publications
|
Space and time continuous physics simulation from partial observationsInternational Conference on Learning Representation, May 2024, Vienna, Austria
Communication dans un congrès
hal-04464153
v1
|
|
Learning whom to trust in navigation: dynamically switching between classical and neural planningInternational Conference on Intelligent Robots and Systems (IROS), Oct 2023, Detroit, United States
Communication dans un congrès
hal-04237170
v1
|
|
Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel SpaceInternational Conference on Learning Representations, Apr 2022, Virtuel, United States
Communication dans un congrès
hal-03630595
v1
|
|
Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?Computer Vision and Pattern Recognition (CVPR), IEEE, Jun 2021, Virtual, France
Communication dans un congrès
hal-02860823
v3
|
Théo GuesserWorkshop on Visualization for AI explainability (VISxAI), Oct 2020, Salt-lake city, United States
Communication dans un congrès
hal-03347249
v1
|
|
|
COPHY: Counterfactual Learning of Physical DynamicsInternational Conference on Learning Representations, Apr 2020, Addis-Abeba, Ethiopia
Communication dans un congrès
hal-02428585
v1
|
|
Learning to plan with uncertain topological mapsECCV 2020 - 16th European Conference on Computer Vision, Aug 2020, Glasgow, United Kingdom. pp.1-24, ⟨10.1007/978-3-030-58580-8_28⟩
Communication dans un congrès
hal-02933641
v1
|
|
Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a SupercomputerICPR 2020 - 25th International Conference on Pattern Recognition, Dec 2020, Milan, Italy. pp.1-16, ⟨10.1109/ICPR48806.2021.9412212⟩
Communication dans un congrès
hal-02934130
v1
|
|
EgoMap: Projective mapping and structured egocentric memory for Deep RLECML-PKDD 2020 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2020, ghent, Belgium. pp.1-12, ⟨10.1007/978-3-030-67661-2_31⟩
Communication dans un congrès
hal-02864146
v1
|
|
RLMViz: Interpreting Deep Reinforcement Learning MemoryJournée Visu 2019, May 2019, Paris, France
Communication dans un congrès
hal-02140902
v1
|
|
Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement LearningECML PKDD 2019 - European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2019, Würzburg, Germany. pp.1-16, ⟨10.1007/978-3-030-46133-1_3⟩
Communication dans un congrès
hal-02302554
v1
|
|
Attentional PointNet for 3D-Object Detection in Point CloudsCVPR 2019 - Workshop on Autonomous driving, Jun 2019, Long Beach, California, United States. pp.1-10, ⟨10.1109/CVPRW.2019.00169⟩
Communication dans un congrès
hal-02156555
v1
|
What if we Reduce the Memory of an Artificial Doom Player?Workshop on Visualization for AI explainability (VISxAI), Oct 2019, Vancouver, Canada
Communication dans un congrès
hal-03347241
v1
|
|
|
Glimpse Clouds: Human Activity Recognition from Unstructured Feature PointsCVPR 2018 - Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, United States. pp.1-10
Communication dans un congrès
hal-01713109
v1
|
|
Human Activity Recognition with Pose-driven Attention to RGBBMVC 2018 - 29th British Machine Vision Conference, Sep 2018, Newcastle, United Kingdom. pp.1-14
Communication dans un congrès
hal-01828083
v1
|
|
Context Aware Robot Architecture, Application to the RoboCup@Home ChallengeRoboCup symposium, Jun 2018, Montreal, Canada. pp.1-12, ⟨10.1007/978-3-030-27544-0_17⟩
Communication dans un congrès
hal-01832613
v1
|
|
Semantic Grid Estimation with a Hybrid Bayesian and Deep Neural Network ApproachIROS 2018 - IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2018, Madrid, Spain. pp.1-8
Communication dans un congrès
hal-01881377
v1
|
|
Learning to Recognize Touch Gestures: Recurrent vs. Convolutional Features and Dynamic SamplingFG'2018 - 13th IEEE International Conference on Automatic Face and Gesture Recognition, May 2018, Xi'An, China. pp.114-121, ⟨10.1109/FG.2018.00026⟩
Communication dans un congrès
hal-02302545
v1
|
|
Object Level Visual Reasoning in VideosECCV 2018 - European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.1-17
Communication dans un congrès
hal-01828872
v1
|
|
Full-Page Text Recognition: Learning Where to Start and When to Stop14th IAPR International Conference on Document Analysis and Recognition, Nov 2017, Kyoto, France. pp.871-876, ⟨10.1109/ICDAR.2017.147⟩
Communication dans un congrès
hal-02343274
v1
|
|
Semantic Grid Estimation with Occupancy Grids and Semantic Segmentation NetworksICARCV 2018 - 15th International Conference on Control, Automation, Robotics and Vision, Nov 2018, Singapore, Singapore. pp.1-6
Communication dans un congrès
hal-01933939
v1
|
Modout: Learning to Fuse Face and Gesture Modalities with Stochastic RegularizationInternational Conference on Automatic Face and Gesture Recognition, May 2017, Washington D.C., United States
Communication dans un congrès
hal-01444614
v1
|
|
Full-Page Text Recognition: Learning Where to Start and When to StopInternational Conference on Document Analysis and Recognition, Nov 2017, Kyoto, Japan
Communication dans un congrès
hal-01563124
v1
|
|
Human Action Recognition: Pose-based Attention draws focus to HandsICCV Workshop on Hands in Action, Oct 2017, Venice, Italy
Communication dans un congrès
hal-01575390
v1
|
|
|
Residual Conv-Deconv Grid Network for Semantic SegmentationBMVC 2017, Sep 2017, Londre, United Kingdom
Communication dans un congrès
hal-01567725
v1
|
|
Semantic Segmentation via Multi-task, Multi-domain LearningS+SSPR 2016 The joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2016) and Statistical Techniques in Pattern Recognition (SPR 2016) , Nov 2016, Merida, Mexico
Communication dans un congrès
hal-01376998
v1
|
Learning text-line localization with shared and local regression neural networksInternational Conference on Frontiers in Handwriting Recognition, Oct 2016, Shenzhen, China
Communication dans un congrès
hal-01345713
v1
|
|
Avancées méthodologiques pour mobiliser les technologies d'eye-tracking dans le cadre de recherches sur les perceptions environnementalesEye-tracking day 2016, Jun 2016, Tours, France
Communication dans un congrès
halshs-01316282
v1
|
|
|
Mixed Pooling Neural Networks for Color ConstancyIEEE International Conference on Image Processing, Sep 2016, Phoenix, United States
Communication dans un congrès
hal-01314066
v1
|
Activity Recognition with Volume Motion Templates and Histograms of 3D GradientsInternational Conference on Image Processing, Sep 2015, Quebec City, Canada
Communication dans un congrès
hal-01147957
v1
|
|
Paragraph text segmentation into lines with Recurrent Neural NetworksInternational Conference on Document Analysis and Recognition, Aug 2015, Tunisia, Tunisia
Communication dans un congrès
hal-01151760
v1
|
|
Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documentsICDAR 2015 Workshop on Historical Document Imaging and Processing, Aug 2015, Nancy, France
Communication dans un congrès
hal-01178342
v1
|
|
|
Learning joint multimodal behaviors for face-to-face interaction: performance & properties of statistical modelsHuman-Robot Interaction. Workshop on Behavior Coordination between Animals, Humans, and Robots, Mar 2015, Portland, United States
Communication dans un congrès
hal-01110290
v1
|
Hand segmentation with structured convolutional learningACCV, Jan 2014, Singapour, Singapore
Communication dans un congrès
hal-01419789
v1
|
|
Autonomous object modeling based on affordances for spatial organization of behaviorInternational joint conference on development and learning and on epigenetic robotics, Oct 2014, Gênes, Italy. pp.94-99
Communication dans un congrès
hal-01301081
v1
|
|
Modeling sensory-motor behaviors for social robotsWACAI 2014 - Workshop Affect, Compagnon Artificiel, Interaction, Jun 2014, Rouen, France
Communication dans un congrès
hal-01527421
v1
|
|
|
Modeling Perception-Action Loops: Comparing Sequential Models with Frame-Based ClassifiersHAI 2014 - 2nd International Conference on Human-Agent Interaction, Oct 2014, Tsukuba, Japan. pp.309-314
Communication dans un congrès
hal-01061454
v1
|
Multi-scale deep learning for gesture detection and localizationECCV Workshop on Looking at People, Oct 2014, Zürich, Switzerland
Communication dans un congrès
hal-01419792
v1
|
|
|
An Enactive Approach to Autonomous Agent and Robot LearningJoint International Conference on Development and Learning and on Epigenetic Robotics, Aug 2013, Osaka, Japan. pp.1-6, ⟨10.1109/DevLrn.2013.6652527⟩
Communication dans un congrès
hal-01339220
v1
|
Integrating spatial layout of object parts into classification without pairwise terms: application to fast body parts estimation from depth imagesVISAPP, Feb 2013, Barcelona, Spain. pp.626-631
Communication dans un congrès
hal-01339138
v1
|
|
A multi-scale approach to gesture detection and recognitionICCV Workshop on Understanding Human Activities: Context and Interactions (HACI 2013), Dec 2013, Sydney, Australia. pp.484-491, ⟨10.1109/ICCVW.2013.69⟩
Communication dans un congrès
hal-01339262
v1
|
|
Graph-Based Analysis of Physical Exercise ActionsACM Multimedia Workshop on Multimedia Indexing and Information Retrieval for Healthcare, Oct 2013, Barcelona, Spain. pp.23-32
Communication dans un congrès
hal-01339245
v1
|
|
Appariement de points spatio-temporels par hyper-graphes et optimisation discrète exacteCOmpression et REprésentation des Signaux Audiovisuels (CORESA), May 2012, Lille, France. pp.56-61
Communication dans un congrès
hal-01352973
v1
|
|
Supervised learning and codebook optimization with neural networkCOmpression et REprésentation des Signaux Audiovisuels (CORESA 2012), May 2012, Lille, France. pp.50-55
Communication dans un congrès
hal-01352975
v1
|
|
|
Action recognition in videosInternational Conference on Image Processing Theory, Tools and Applications (IPTA), Oct 2012, Istanbul, Turkey. ⟨10.1109/IPTA.2012.6469480⟩
Communication dans un congrès
hal-01497896
v1
|
Sparse Shift-Invariant Representation of Local 2D Patterns and Sequence Learning for Human Action Recognition21st International Conference on Pattern Recognition (ICPR), Nov 2012, Tsukuba Science City, Japan. pp.3823-3826
Communication dans un congrès
hal-01353014
v1
|
|
|
Spatio-Temporal Convolutional Sparse Auto-Encoder for Sequence ClassificationBritish Machine Vision Conference (BMVC), Sep 2012, Guildford, United Kingdom. pp.124.1-124.12, ⟨10.5244/C.26.124⟩
Communication dans un congrès
hal-01353046
v1
|
Real-Time Exact Graph Matching with Application in Human Action RecognitionInternational Workshop on Human Behavior Understanding, Oct 2012, Vilamoura, Portugal. pp.17-28, ⟨10.1007/978-3-642-34014-7_2⟩
Communication dans un congrès
hal-01353052
v1
|
|
Robust feature line extraction on CAD triangular meshesInternational Conference on Computer Graphics Theory and Applications, Mar 2011, Algarve, Portugal
Communication dans un congrès
hal-01158033
v1
|
|
|
Sequential Deep Learning for Human Action Recognition2nd International Workshop on Human Behavior Understanding (HBU), Nov 2011, Amsterdam, Netherlands. pp.29-39, ⟨10.1007/978-3-642-25446-8_4⟩
Communication dans un congrès
hal-01354493
v1
|
Maintien des personnes âgées à domicile - enjeux scientifiques et technologiques liés à la vision par ordinateurEcole d'été "Intelligence ambiante", Lille; Session Enjeux sociétaux, scientifiques et technologiques du maintien des personnes âgées à domicile. , Jul 2011, Lille, France. pp.1-60
Communication dans un congrès
hal-01354567
v1
|
|
Une approche neuronale pour la classification d’actions de sport par la prise en compte du contenu visuel et du mouvement dominantCOmpression et REprésentation des Signaux Audiovisuels (CORESA), Oct 2010, Lyon, France. pp.25-30
Communication dans un congrès
hal-01381510
v1
|
|
|
Interactive Content-Aware ZoomingGraphics Interface 2010 Conference, May 2010, Ottawa, Ontario, Canada. pp.79--87
Communication dans un congrès
inria-00606829
v1
|
|
Integrating a discrete motion model into GMM based background subtractionInternational Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. pp.9-12, ⟨10.1109/ICPR.2010.11⟩
Communication dans un congrès
hal-01381470
v1
|
|
Recognizing and localizing individual activities through graph matchingInternational Conference on Advanced Video and Signal-Based Surveillance (BEST PAPER), Aug 2010, Boston, United States. pp.196-203, ⟨10.1109/AVSS.2010.81⟩
Communication dans un congrès
hal-01381516
v1
|
|
Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks20th International Conference on Artificial Neural Networks (ICANN), Sep 2010, Thessaloniki, Greece. pp.154-159, ⟨10.1007/978-3-642-15822-3_20⟩
Communication dans un congrès
hal-01381827
v1
|
|
Pairwise features for human action recognitionInternational Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. pp.3224-3227, ⟨10.1109/ICPR.2010.788⟩
Communication dans un congrès
hal-01381471
v1
|
|
3D Object detection and viewpoint selection in sketch images using local patch-based Zernike moments7th International conference on Content-Based Multimedia Indexing (CBMI), Jun 2009, Chania, Crete, Greece. pp.189-194, ⟨10.1109/CBMI.2009.29⟩
Communication dans un congrès
hal-01437638
v1
|
|
Classification of images based on Hidden Markov ModelsIEEE Workshop on Content Based Multimedia Indexing, Jun 2009, Chania, Crète, Greece. pp.169-174, ⟨10.1109/CBMI.2009.22⟩
Communication dans un congrès
hal-01437635
v1
|
Families of Markov models for document image segmentationMachine Learning for Signal Processing Workshop, Sep 2009, Grenoble, France. pp.6, ⟨10.1109/MLSP.2009.5306241⟩
Communication dans un congrès
hal-01437733
v1
|
|
Séparation recto/verso d'un document par modélisation markovienne à double coucheCORESA'09 : COdage et REprésentation des Signaux Audiovisuels, Mar 2009, Toulouse, France. pp.6
Communication dans un congrès
hal-01437622
v1
|
|
Markov Random Fields for Improving 3D Mesh Analysis and SegmentationEurographics 2008 Workshop on 3D Object Retrieval, Apr 2008, Crete, Greece. pp.1-8
Communication dans un congrès
hal-01500680
v1
|
|
Improving recto document side restoration with an estimation of the verso side from a singled scanned pageInternational Conference on Pattern Recognition, Dec 2008, Tampa, United States. pp.1-4
Communication dans un congrès
hal-01501272
v1
|
|
|
Inference and parameter estimation on belief networks for image segmentationJournées Francophone sur les Réseaux Bayésiens, May 2008, Lyon, France
Communication dans un congrès
hal-00280517
v1
|
Quality, quantity and generality in the evaluation of object detection algorithmsImage Eval 2007, Jun 2007, Amsterdam, NL, Netherlands
Communication dans un congrès
hal-01527426
v1
|
|
Reinforcement Learnig For Parameter Control of Text Detection in Images and Video SequencesInternational Conference on Information and Communication Technologies : From Theory to Applications, Apr 2004, Damascus, Syria. ⟨10.1109/ICTTA.2004.1307859⟩
Communication dans un congrès
hal-01593442
v1
|
|
Utilisation de connaissances a priori pour le paramétrage d'un algorithme de détection de textes dans les documents audiovisuels : application à un corpus de journaux télévisésRFIA, Jan 2004, Toulouse, France. pp.0
Communication dans un congrès
hal-01583299
v1
|
|
Détection de textes de scenes dans des images issues d'un flux vidéoJournée de COmpression et REprésentation des Signaux Audiovisuels (CORESA), Jan 2003, Lyon, France. pp.63-66
Communication dans un congrès
hal-01583289
v1
|
|
Attentional PointNet for 3D-Object Detection in Point CloudsCVPR 2019 - Workshop on Autonomous Driving, Jun 2019, Long Beach, California, United States. pp.1
Poster de conférence
hal-02160868
v1
|
Mesh Segmentation and Global 3D Model ExtractionSymposium on Geometry Processing, Jul 2012, Tallinn, Estonia. 2012
Poster de conférence
hal-01353042
v1
|
|
Global triangular mesh regularization using conditional Markov random fieldsSymposium on Geometry Processing, Jul 2009, Berlin, Germany. EUROGRAPHICS, 2009
Poster de conférence
hal-01364624
v1
|
Artificial Intelligence. What is it, exactly?Sébastien Konieczny; Henri Prade. College Publication, 2021, 9781848903388
Ouvrages
hal-04270168
v1
|
|
L’intelligence Artificielle: De quoi s’agit-il vraiment ?Sébastien Konieczny; Henri Prade. Cepadues, 2020, 9782364938502
Ouvrages
hal-04270163
v1
|
|
Gaze and face-to-face interactionGeert Brône & Bert Oben. Eye-tracking in Interaction. Studies on the role of eye gaze in dialogue, Benjamins, pp.139 - 168, 2018, ⟨10.1075/ais.10.07bai⟩
Chapitre d'ouvrage
hal-01939223
v1
|
Extraction d'informations textuelles contenues dans les images et les séquences audio-visuelles par une approche de type machine à vecteurs supportsFrance, Patent n° : FR 03 11918,. 1201. 2003
Brevet
hal-01527420
v1
|
|
SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation2021
Autre publication scientifique
hal-03430140
v1
|
|
Learning to detect and localize many objects from few examples[Research Report] INSA-Lyon; LIRIS; A2IA. 2016
Rapport
(rapport de recherche)
hal-01399159
v1
|
|
Activity recognition from videos with parallel hypergraph matching on GPUs[Research Report] INSA Lyon. 2015
Rapport
(rapport de recherche)
hal-01234661
v1
|
|
Hand Pose Estimation through Weakly-Supervised Learning of a Rich Intermediate Representation[Research Report] INSA Lyon. 2015
Rapport
(rapport de recherche)
hal-01281943
v1
|
Rivière : Renaturer la VillE : facteur de RisquE ou de bien-être social aux yeux des habitants et des usagers ? L’apport d’une médiation paysagère[Rapport de recherche] labex IMU. 2015
Rapport
(rapport de recherche)
halshs-01250481
v1
|
|
|
Mechanical Mesh Segmentation and Global 3D Shape Extraction[Research Report] 6936, Université Lyon 1 - Claude Bernard; INSA Lyon. 2014
Rapport
(rapport de recherche)
hal-01467963
v1
|