Ioan Marius Bilasco
99
Documents
Publications
Publications
SnatchML: Hijacking ML Models Without Training Access2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), Apr 2025, Copenhagen, Denmark. pp.92-109, ⟨10.1109/SaTML64287.2025.00013⟩
Communication dans un congrès
hal-05148276
v1
|
|
Neuronal Competition Groups with Supervised STDP for Spike-Based ClassificationNeurIPS Neural Information Processing Systems, Dec 2024, Vancouver, Canada
Communication dans un congrès
hal-04721171
v1
|
|
|
|
Motion Consistency Map for Facial Expression SpottingInternational Conference on Content-based Multimedia Indexing, Sep 2024, Reykjavík, Iceland
Communication dans un congrès
hal-04654155
v1
|
S3TC: Spiking Separated Spatial and Temporal Convolutions with Unsupervised STDP-based Learning for Action RecognitionInternational Conference on Pattern Recognition, Dec 2024, Kolkata, France
Communication dans un congrès
hal-04720991
v1
|
|
AdvART: Adversarial Art for Camouflaged Object Detection Attacks2024 IEEE International Conference on Image Processing (ICIP), Oct 2024, Abu Dhabi, United Arab Emirates. pp.666-672, ⟨10.1109/ICIP51287.2024.10648014⟩
Communication dans un congrès
hal-04964950
v1
|
|
2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action RecognitionCORESA, Jun 2023, Villeneuve d'Ascq, France
Communication dans un congrès
hal-04126185
v1
|
|
|
|
2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action RecognitionInternational Joint Conference on Neural Networks (IJCNN) 2022, Jul 2022, Padova, Italy
Communication dans un congrès
hal-03679597
v1
|
|
|
BAREM: A multimodal dataset of individuals interacting with an e-service platformCBMI 2021 - Content-based Multimedia Indexing, Jun 2021, Lille / Virtual, France
Communication dans un congrès
hal-03263944
v1
|
|
|
A Study On the Effects of Pre-processing On Spatio-temporal Action Recognition Using Spiking Neural Networks Trained with STDPContent-based Multimedia Indexing, Jun 2021, Lille (en ligne), France
Communication dans un congrès
hal-03263914
v1
|
Improving STDP-based Visual Feature Learning with WhiteningIJCNN 2020 - International Joint Conference on Neural Networks, Jul 2020, Glasgow, United Kingdom
Communication dans un congrès
hal-02532943
v1
|
|
|
|
Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDPInternational Joint Conference on Neural Networks (IJCNN), Jul 2019, Budapest, Hungary
Communication dans un congrès
hal-02146289
v1
|
Video-based Face Alignment with Local Motion ModelingIEEE Winter Conf. on Applications of Computer Vision, 2019, Hawaii, United States
Communication dans un congrès
hal-02042559
v1
|
|
Mastering Occlusions by Using Intelligent Facial Frameworks Based on the Propagation of MovementInternational Conference on Content-Based Multimedia Indexing (CBMI), Sep 2018, La Rochelle, France
Communication dans un congrès
hal-01845363
v1
|
|
Mastering the Output Frequency in Spiking Neural NetworksInternational Joint Conference on Neural Networks (IJCNN), Jul 2018, Rio de Janeiro, Brazil
Communication dans un congrès
hal-01741500
v1
|
|
|
|
Dynamic index finger gesture video dataset for mobile interactionInternational Conference on Content-Based Multimedia Indexing (CBMI), Sep 2018, La Rochelle, France
Communication dans un congrès
hal-01845367
v1
|
|
|
Etude de l’apport de la reconstruction des régions occultées du visage pour la reconnaissance des expressionsCORESA, Nov 2018, Poitiers, France
Communication dans un congrès
hal-01993650
v1
|
|
|
Towards Spatio-Temporal Face Alignment in Unconstrained ConditionsVISAPP, Jan 2018, Funchal, Portugal
Communication dans un congrès
hal-01644813
v1
|
|
|
Consistent Optical Flow Maps for full and micro facial expression recognitionVISAPP, Feb 2017, Porto, Portugal. pp.235-242, ⟨10.5220/0006127402350242⟩
Communication dans un congrès
hal-01503522
v1
|
|
|
Vers un alignement spatio-temporel du visage en conditions non contrôléesCORESA, Nov 2017, Caen, France
Communication dans un congrès
hal-01644791
v1
|
|
|
Etude de la dynamique du visage en situation d'interaction naturelleCOmpression et REprésentation des Signaux Audiovisuels (CORESA) 2016, May 2016, Nancy, France
Communication dans un congrès
hal-01306045
v1
|
EmoGame: Towards a Self-Rewarding Methodology for Capturing Children Faces in an Engaging Context7th International Workshop, HBU 2016 at ACMMM 2016 , Oct 2016, Amsterdam, Netherlands. ⟨10.1007/978-3-319-46843-3_1⟩
Communication dans un congrès
hal-01380611
v1
|
|
|
|
Fast head turns detection in low quality videos using optical flowReconnaissance des Formes et l'Intelligence Artificielle (RFIA), Jun 2016, Clermont-Ferrand, France
Communication dans un congrès
hal-01542994
v1
|
|
|
Introducing FoxFaces: a 3-in-1 head datasetInternational Conference on Computer Vision Theory and Applications (VISAPP), Feb 2016, Porto, Portugal
Communication dans un congrès
hal-01306023
v1
|
Head Yaw Estimation using Frontal Face DetectorInternational Conference on Computer Vision Theory and Applications (VISAPP), Feb 2016, Porto, Portugal
Communication dans un congrès
hal-01306038
v1
|
|
|
|
Faces and Thoughts: An Empathic DairyIEEE International Conference on Automatic Face and Gesture Recognition, IEEE, May 2015, Ljubljana, Slovenia
Communication dans un congrès
hal-01150212
v1
|
Pruning near-duplicate images for mobile landmark identification: a graph theoretical approachInternational Workshop on Content-Based Multimedia Indexing, Jun 2015, Prague, Czech Republic. ⟨10.1109/CBMI.2015.7153635⟩
Communication dans un congrès
hal-01532834
v1
|
|
Affect Recognition Using Magnitude Models of MotionMultiMedia Modelling 2014, Jan 2014, Dublin, Ireland. pp.339-344, ⟨10.1007/978-3-319-04117-9_33⟩
Communication dans un congrès
hal-00973499
v1
|
|
Data analysis of TV Shows viewersEmpaTex - ACM TVX Workshop, Jun 2014, Newcastle upon Tyne, United Kingdom
Communication dans un congrès
hal-01075103
v1
|
|
Analysing user visual implicit feedback in enhanced TV scenariosSpontaneous Facial Behavior Analysis - ECCV Workshop, Sep 2014, Zurich, Switzerland
Communication dans un congrès
hal-01075087
v1
|
|
|
|
Cross-database evaluation of normalized raw pixels for gender recognition under unconstrained settings22nd International Conference on Pattern Recognition (ICPR 2014), Aug 2014, Stockholm, Sweden. pp.3144-3149, ⟨10.1109/ICPR.2014.542⟩
Communication dans un congrès
hal-00973505
v1
|
|
|
A Local Approach for Negative Emotion DetectionInternational Conference on Pattern Recognition, Aug 2014, Stockholm, Sweden. pp.417-420
Communication dans un congrès
hal-00973503
v1
|
|
|
Positive/Negative Emotion Detection from RGB-D upper Body ImagesInternational Workshop on FFER (Face and Facial Expression Recognition from Real World Videos)-ICPR 2014, Aug 2014, Stockholm, Sweden
Communication dans un congrès
hal-01074990
v1
|
Events detection using a video-surveillance Ontology and a rule-based approachECCV 2014 : Workshops on Computer Vision, Sep 2014, Zurich, Switzerland. pp 299-308, ⟨10.1007/978-3-319-16181-5_21⟩
Communication dans un congrès
hal-01075090
v1
|
|
Vers une reconnaissance d'état affectif à base de mouvements du haut du corps et du visageColloque National Compression et Représentation des Signaux Audiovisuels (CORESA), Nov 2014, Reims, France
Communication dans un congrès
hal-01150213
v1
|
|
Caractérisation locale des changements de texture pour la reconnaissance d’expressions faciales spontanéesColloque National Compression et Représentation des Signaux Audiovisuels (CORESA), Nov 2014, Reims, France
Communication dans un congrès
hal-01150214
v1
|
|
An ontology based approach for inferring multiple object events in surveillance domainSAI 2014 : Science and Information Conference, Aug 2014, London, United Kingdom. pp.404 - 409, ⟨10.1109/SAI.2014.6918219⟩
Communication dans un congrès
hal-01075056
v1
|
|
|
|
Construction de masques faciaux pour améliorer la reconnaissance d'expressionsCOmpression et REpresentation des Signaux Audiovisuels, May 2012, Lille, France. pp.17
Communication dans un congrès
hal-00812319
v1
|
|
|
Learning symmetrical model for head pose estimationICPR - 21st International Conference on Pattern Recognition, Nov 2012, Tsukuba, Japan. pp.3614-3617
Communication dans un congrès
hal-00804181
v1
|
Estimation discrète de l'angle Pan de la têteCompression et Représentation des Signaux Audiovisuels (CORESA), May 2012, Lille, France. pp.N° 24
Communication dans un congrès
hal-00812186
v1
|
|
MuMIe : a new system for multimedia metadata interoperability1st ACM International Conference on Multimedia Retrieval (ICMR) 2011, Apr 2011, Trento, Italy. pp.1, ⟨10.1145/1991996.1991997⟩
Communication dans un congrès
hal-00812292
v1
|
|
|
|
MuMIE : Une approche automatique pour l'interopérabilité des métadonnéesExtraction et Gestion des Connaissances (EGC) 2011, Jan 2011, Brest, France. pp.347-352
Communication dans un congrès
hal-00812290
v1
|
Extracting Human Behaviour from Video StreamsEU-Australia Workshop on Bilateral Cooperation in e-Health, May 2011, Budapest, Hungary
Communication dans un congrès
hal-01565780
v1
|
|
|
|
Vers une Interopérabilité Multi-Niveaux des MétadonnéesINFORSID 2011, May 2011, Lille, France
Communication dans un congrès
hal-00812330
v1
|
Extracting Human Behaviour from Video StreamsMultitel Spring Workshop on Video Analysis, Jun 2010, Mons, Belgium
Communication dans un congrès
hal-00812331
v1
|
|
Schema matching for integrating multimedia metadataInternational Conference on Machine and Web Intelligence (ICMWI), 2010, Oct 2010, Algiers, Algeria. pp.234-239, ⟨10.1109/ICMWI.2010.5647884⟩
Communication dans un congrès
hal-00812318
v1
|
|
Prédiction de séries temporelles et applications à l'analyse de séquences vidéosExtraction et gestion des connaissances (EGC'2010), Jan 2010, Hammamet, Tunisie. pp.713-714
Communication dans un congrès
hal-00730601
v1
|
|
Multimedia metadata mapping : towards helping developers in their integration task8th International Conference on Advances in Mobile Computing and Multimedia (MoMM) 2010, Nov 2010, Paris, France. pp.205-212, ⟨10.1145/1971519.197155⟩
Communication dans un congrès
hal-00812304
v1
|
|
Semi-Automatic Multimedia Metadata IntegrationEKAW 2010 Poster and Demo Track, Oct 2010, Lisboa, Portugal. pp.art 10
Communication dans un congrès
hal-00812317
v1
|
|
Détection des mouvements anormaux dans des vidéos10 ème Conférence Internationale Francophone sur l'Extraction et la Gestion des Connaissances (EGC), 2010, Hammamet, Tunisia. pp.699-700
Communication dans un congrès
hal-00730568
v1
|
|
|
|
IPTV 2.0 from Triple Play to social TVIEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) 2010, Mar 2010, Shanghai, China. pp.1-5, ⟨10.1109/ISBMSB.2010.5463095⟩
Communication dans un congrès
hal-00812316
v1
|
|
|
Automatic Facial Feature Detection for Facial Expression RecognitionFifth International Conference on Computer Vision Theory and Applications (VISAPP) 2010, May 2010, Angers, France. pp.407-412
Communication dans un congrès
hal-00812308
v1
|
Semantics for intelligent delivery of multimedia contentProceedings of the International Symposium On Applied Computing, Mar 2010, Sierre, Switzerland
Communication dans un congrès
hal-00730593
v1
|
|
Motion similarity measure between video sequences using multivariate time series modelingInternational Conference on Machine and Web Intelligence (ICMWI), 2010, Oct 2010, Algiers, Algeria. pp.292-296, ⟨10.1109/ICMWI.2010.5647919⟩
Communication dans un congrès
hal-00812128
v1
|
|
|
|
Drowsy Driver Detection System Using Eye Blink PatternsInternational Conference on Machine and Web Intelligence (ICMWI 2010), Oct 2010, Alger, Algeria. pp.230-233, ⟨10.1109/ICMWI.2010.5648121⟩
Communication dans un congrès
hal-00812315
v1
|
Metadata roles within CAM4HOMEITEA2-CELTIC Joint Workshop, Jun 2009, Paris, France
Communication dans un congrès
hal-00730594
v1
|
|
In-situ Quantification of 3D Scene ComplexityProceedings of The International Conference on Advanced Geographic Information Systems and Web Services, Feb 2009, Cancun, Mexico. pp.34-39, ⟨10.1109/GEOWS.2009.37⟩
Communication dans un congrès
hal-00730595
v1
|
|
A Semantic Approach to Metadata Management in Sensor SystemsCognitive systems with interactive sensors (COGIS), Nov 2009, Paris, France
Communication dans un congrès
hal-00730597
v1
|
|
Semantic-based rules for 3D scene adaptationWeb3D Symposium, Apr 2007, Perugia, Italy. pp.97-100
Communication dans un congrès
hal-01221818
v1
|
|
User localization using a typology of 3D queriesFirst International Workshop on Mobile Geospatial Augmented Reality, May 2006, Banff (Alberta), Canada
Communication dans un congrès
hal-01221847
v1
|
|
An MPEG-7 framework enhancing the reuse of 3D modelsWeb3D Symposium, Apr 2006, Columbia (MA), United States. pp.65-74
Communication dans un congrès
hal-01221820
v1
|
|
Annotating 3D contents with MPEG-7 for reuse purposesInternational Conference on Multimedia Content Analysis, Management, and Retrieval 2006 (SPIE 2006), Jan 2006, San José (CA), United States
Communication dans un congrès
hal-01221843
v1
|
|
On indexing of 3D scenes using MPEG-7ACM Multimedia, Nov 2005, Singapore, Singapore
Communication dans un congrès
hal-01221823
v1
|
|
STAMP: Adaptable Templates for Synchronized Multimedia PresentationsWeb Intelligence (WI 2005), Sep 2005, Compiègne, France. pp.645-648
Communication dans un congrès
hal-01221832
v1
|
|
DSEAM: a model for annotating 3D scenes using MPEG-7Seventh IEEE International Symposium on Multimedia (ISM 2005), Dec 2005, Irvine (CA), United States. pp.310-319
Communication dans un congrès
hal-01221826
v1
|
|
Générer des présentations multimédia adaptées avec STAMP20èmes Journées Bases de Données Avancées, BDA '04, Oct 2004, Montpellier, France
Communication dans un congrès
hal-01221836
v1
|
Unsupervised Learning of Sparse Facial Movements using Convolutional Spiking Neural NetworksNeuromorphic Computing for Development and Learning Workshop, Sep 2025, Prague, Czech Republic. Zenodo, 2025, ⟨10.5281/zenodo.17194640⟩
Poster de conférence
hal-05281706
v1
|
|
Improving Human Action Recognition with Neuronal Competition in Spiking Neural NetworksNeuromorphic Computing for Development and Learning Workshop, Sep 2025, Prague (Czech Republic), Czech Republic. 2025, ⟨10.5281/zenodo.15873154⟩
Poster de conférence
hal-05330402
v1
|
|
Impact of frame-based representations for event-based data in the field of gesture recognitionNeuromorphic Computing for Development and Learning Workshop, Sep 2025, Prague (CZ), Czech Republic. Zenodo, 2025, ⟨10.5281/zenodo.15882836⟩
Poster de conférence
hal-05330405
v1
|
Towards a Unified Multimedia Metadata Management SolutionMa, Zongmin. Intelligent Multimedia Databases and Information Retrieval: Advancing Applications and Technologies, IGI Global, pp.170-194, 2012, ⟨10.4018/978-1-61350-126-9.ch011⟩
Chapitre d'ouvrage
hal-00730575
v1
|
|
Designing intelligent content delivery frameworks using MPEG-21Agius, Harry and Angelides, Marios. The Handbook of MPEG Applications: Standards in Practice, John Wiley and Sons Ltd, pp.ch. 19, 2010, ⟨10.1002/9780470974582.ch19⟩
Chapitre d'ouvrage
hal-00730598
v1
|
|
Indexing Three Dimensional Scenes.Encyclopedia of Multimedia, Springer, pp.346-352, 2008
Chapitre d'ouvrage
hal-01221808
v1
|
Spiking Neural Networks Trained withUnsupervised STDP for Video Analysis2021
Autre publication scientifique
hal-03450937
v1
|
|
Empathic Products - D2.3: Guidelines for the Design of Empathic Products2015
Autre publication scientifique
hal-01306085
v1
|
|
Empathic Products - D2.1 Measuring User eXperience2013
Autre publication scientifique
hal-01306066
v1
|
|
Empathic Products - D3.1 : Affective Technology - State of the Art2013
Autre publication scientifique
hal-01306753
v1
|
|
CAM4HOME Metadata Framework2009
Autre publication scientifique
hal-01565800
v1
|
|
|
Une approche sémantique pour la réutilisation et l'adaptation de donnée 3DAutre [cs.OH]. Université Joseph-Fourier - Grenoble I, 2007. Français. ⟨NNT : ⟩
Thèse
tel-00206220
v3
|
|
|
Analyse faciale dans les flux vidéoVision par ordinateur et reconnaissance de formes [cs.CV]. Université de Lille, 2019
HDR
tel-02407177
v1
|
Chargement...
Chargement...