Accueil | Recherche | Publications | Enseignement English

Publications

Certains des documents présentés ici sont rendus disponibles par les auteurs qui y ont contribué en vue d'assurer la diffusion à temps de travaux sur une base non-commerciale. Les droits de copie et autres droits sont gardés par les auteurs et par les détenteurs du copyright, en dépit du fait qu'ils présentent ici leurs travaux sous forme électronique. Les personnes copiant ces informations doivent adhérer aux termes et contraintes couverts par le copyright de chaque auteur. Ces travaux ne peuvent pas être rendus disponibles ailleurs sans la permission explicite du détenteur du copyright.

Revues internationales avec comité de rédaction

[DACB22]  Doubinsky, P., Audebert, N., Crucianu, M., Le Borgne, H. (2022) Multi-Attribute Balanced Sampling for Disentangled GAN Controls. Pattern Recognition Letters, 162: 56-62, 2022. [HAL]
[BBCF20]  Besedin, A., Blanchart, P., Crucianu, M., Ferecatu, M. (2020) Deep Online Classification Using Pseudo-Generative Models. Computer Vision and Image Understanding, [accès restreint].
[SFBC15b]  Stoian, A., Ferecatu, M., Benois-Pineau, J., Crucianu, M. (2016) Fast action localization in large scale video archives. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), Volume: 26, Issue: 10, Oct. 2016, pp. 1917-1930, DOI: 10.1109/TCSVT.2015.2475835 [accès restreint]
[PBC09]  Poullot, S., Buisson, O., Crucianu, M. (2010) Scaling Content-Based Video Copy Detection to Very Large Databases, Multimedia Tools and Applications (CORE B), Vol. 47 (2): 279-306. [accès restreint]
[CEOT08]  Crucianu, M., Estevez, D., Oria, V., Tarel, J.-Ph. (2008) Speeding Up Active Relevance Feedback with Approximate kNN Retrieval for Hyperplane Queries, International Journal of Imaging Systems and Technology, Special issue on Multimedia Information Retrieval, Vol. 18 (2-3): 150-159. [accès restreint][preprint (pdf)]
[CTF08]  Crucianu, M., Tarel, J.-Ph., Ferecatu, M. (2008) An Exploration of Diversified User Strategies for Image Retrieval with Relevance Feedback, Journal of Visual Languages and Computing (CORE A), Vol. 19 (2008), pp. 629-636. [accès restreint][HAL preprint (pdf)]
[GCB08]  Grira, N., Crucianu, M., Boujemaa, N. (2008) Active Semi-Supervised Fuzzy Clustering, Pattern Recognition, Vol. 41, No 5 (mai 2008), pp. 1851-1861. [accès restreint]
[FBC08a]  Ferecatu, M., Boujemaa, N., Crucianu, M. (2008) Semantic interactive image retrieval combining visual and conceptual content description, ACM Multimedia Systems Journal, Vol. 13, No 5-6 (février 2008), pp. 309-322. [accès restreint][preprint (pdf)][bibtex]
[GCB06]  Grira, N., Crucianu, M., Boujemaa, N. (2006) Fuzzy Clustering with Pairwise Constraints for Knowledge-Driven Image Categorization, IEE Proceedings on Vision, Image and Signal Processing, Volume 153, Issue 3, pp. 299-304. [pdf][obtenir bibtex]

Chapitres d'ouvrages

[CBC21] Le Cacheux, Y., Le Borgne, H. and Crucianu, M. (2021) Zero-shot Learning with Deep Neural Networks for Object Recognition. Dans : Benois-Pineau, J., Zemmari, A. (eds) Multi-faceted Deep Learning: Models and Data, Springer, 2021, ISBN 978-3-030-74477-9. [présentation ouvrage]
[Cru12]  Crucianu, M. (2012) Scalability issues in visual information retrieval. Dans : J. Benois-Pineau, F. Precioso, M. Cord (eds) Visual indexing and retrieval. Springer Verlag, 2012, pp. 65-81, ISBN 978-1-4614-3587-7. [présentation ouvrage]
[Cru09]  Crucianu, M. (2009) Image retrieval with relevance feedback. Dans : L. Liu, T. Özsu (eds) Encyclopedia of Databases: Multimedia Databases. Springer Verlag, 2009. [présentation ouvrage][accès restreint]
[FBC08b]  Ferecatu, M., Boujemaa, N., Crucianu, M. (2008) Interactive image retrieval using a hybrid visual and conceptual content representation. Dans : P. Maragos, A. Potamianos, P. Gros (eds) Multimodal Processing and Interaction: Audio, Video, Text. Springer Verlag, Series: Multimedia Systems and Applications, Vol. 33, pp. 1-20. [accès restreint][présentation ouvrage]

Conférences internationales avec comité de sélection

[DAC24]  Doubinsky, P.; Audebert, N.; Crucianu, M. and Le Borgne, H. (2024) Semantic Generative Augmentations for Few-Shot Counting. WACV, 2023. [HAL]
[DAC23]  Doubinsky, P.; Audebert, N.; Crucianu, M. and Le Borgne, H. (2023) Wasserstein Loss for Semantic Editing in the Latent Space of GANs. 20th International Conference on Content-based Multimedia Indexing (CBMI), Orléans, France, 2023. [HAL]
[AFC23b]  Aissa, W.; Ferecatu, M. and Crucianu, M. (2023) Multimodal Representations for Teacher-Guided Compositional Visual Reasoning. Advanced Concepts for Intelligent Vision Systems, 21st International Conference (ACIVS 2023), Kumamoto, Japan, 2023. [HAL]
[AFC23]  W. Aissa, M. Ferecatu, M. Crucianu (2023) Curriculum Learning for Compositional Visual Reasoning, VISAPP 2023, February 19-21, Lisbon, Portugal. [HAL]
[ZBCF22]  S. Zhou, P. Blanchart, M. Crucianu, M. Ferecatu (2022) Why is the prediction wrong? Towards underfitting case explanation via meta-classification, DSAA 2022 (9th IEEE International Conference on Data Science and Advanced Analytics), October 13-16, Shenzhen, China (online). [HAL]
[CBC20a]  Yannick Le Cacheux, Hervé Le Borgne, M. Crucianu (2020) Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning, ECCV 2020 workshop Transferring and adapting source knowledge in computer vision (TASK-CV), 23 août 2020, Glasgow, Scotland. [arXiv]
[CBC19b]  Yannick Le Cacheux, Hervé Le Borgne, M. Crucianu (2019) Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning, International Conference on Computer Vision, 27 octobre - 2 novembre 2019, Séoul, Corée du Sud. [thecvf]
[CBC19]  Yannick Le Cacheux, Hervé Le Borgne, M. Crucianu (2019) From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process, 23rd International Conference on Multimedia Modeling, 8-11 janvier 2019, Thessaloniki, Greece. [arXiv]
[BBC18]  A. Besedin, P. Blanchart, M. Crucianu, M. Ferecatu (2018) Deep Online Storage-free Learning on Unordered Image Streams, ECML/PKDD 2018 Workshop on Large-scale Learning from Data Streams in Evolving Environments (IOTSTREAMING-2018), September 2018, Dublin, Ireland.
[YRFC17]  L. Yang, H. Rodriguez, M. Ferecatu, M. Crucianu (2017) Fully convolutional network with superpixel parsing for fashion Web image segmentation, 23rd International Conference on Multimedia Modeling, Reykjavik, Iceland, 4-6 janvier 2017.
[BBC17]  A. Besedin, P. Blanchart, M. Crucianu, M. Ferecatu (2017) Evolutive deep models for online learning on data streams with no storage, ECML/PKDD 2017 Workshop on Large-scale Learning from Data Streams in Evolving Environments (IOTSTREAMING-2017), September 2018, Dublin, Ireland.
[TBC16b]  Tran, N., Le Borgne, H., Crucianu, M. (2016) Cross-Modal Classification by Completing Unimodal Representations, Workshop Vision and Language Integration Meets Multimedia Fusion, avec ACM Multimedia, Amsterdam, NL, 15-19 octobre, 2016. [pdf]
[YRFC16b]  L. Yang, H. Rodriguez, M. Ferecatu, M. Crucianu (2016) A Global-Local approach to extracting deformable fashion items from Web images, Pacific-Rim Conference on Multimedia (PCM), Xi'an, Chine, 15-16 septembre 2016. [pdf]
[TBC16]  Tran, N., Le Borgne, H., Crucianu, M. (2016) Aggregating Image and Text Quantized Correlated Components, Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, Etats Unis, 26 juin - 1er juillet, pp. 2046-2054, 2016. [accès ouvert]
[YRFC16]  L. Yang, H. Rodriguez, M. Ferecatu, M. Crucianu (2016) Classification-Driven Active Contour for Dress Segmentation, 11th Intl. Joint Conf. on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), Rome, Italie, 27-29 février 2016. [pdf]
[RLF16]  H. Randrianarivo, B. Le Saux, M. Ferecatu, M. Crucianu (2016) Contextual discriminatively trained model mixture for object detection in aerial images, Intl. Conf. on Big Data from Space (BiDS'16), March 2016, Spain.
[SFBC15a]  Stoian, A., Ferecatu, M., Benois-Pineau, J., Crucianu, M. (2015) Scalable action localization with kernel-space hashing, IEEE International Conference on Image Processing (ICIP), Québec, Canada, 27-30 septembre 2015. [pdf]
[TBC15]  Tran, N., Le Borgne, H., Crucianu, M. (2015) Combining generic and specific information for cross-modal retrieval, ACM International Conference on Multimedia Retrieval (ICMR), Shanghai, Chine, 23-26 juin 2015. [pdf]
[FACG13]  C. A. F. Filho, A. de Albuquerque Araújo, M. Crucianu, V. Gouet-Brunet (2013) Sketch-Finder: Efficient and Effective Sketch-Based Retrieval for Large Image Collections. SIBGRAPI 2013, pp. 234-241.
[YCOD10]  Yu, Y., Crucianu, M., Oria, V., Damiani, E. (2010) Combining Multi-Probe Histogram and Order-Statistics Based LSH for Scalable Audio Content Retrieval, ACM Multimedia 2010 (CORE A+, taux d'acceptation 16%), Florence, Italie, 25-29 octobre 2010, pp. 381-390. [pdf]
[OBC10]  Wajih Ouertani, Pierre Bonnet, Michel Crucianu, Nozha Boujemaa, Daniel Barthélémy. (2010) Iterative Search with Local Visual Features for Computer Assisted Plant Identification. BioIdentify 2010. Paris, 20-22 septembre 2010, pp. 237-242. [pdf]
[OCB10]  Ouertani, W., Crucianu, M., Boujemaa, N. (2010) Interactive Learning of Heterogeneous Visual Concepts with Local Features, ACM Multimedia 2010, papier court, Florence, Italie, 25-29 octobre 2010, pp. 995-998. [pdf]
[PC10]  Pröscholdt, T., Crucianu, M. (2010) On Finding Complementary Clusterings, European Symposium on Artificial Neural Networks (ESANN 2010), Bruges, Belgique, 28-30 avril 2010, pp. 487-492. [pdf]
[YCOC09]  Yu, Y., Crucianu, M., Oria, V., Chen, L. (2009) Local Summarization and Multi-Level LSH for Retrieving Multi-Variant Audio Tracks, ACM Multimedia 2009 (CORE A+, taux d'acceptation 16%), Beijing, China, 19-24 octobre 2009, pp. 341-350. [pdf]
[PCS09]  Poullot, S., Crucianu, M., Satoh, S. (2009) Indexing Local Configurations of Features for Scalable Content-Based Video Copy Detection, 1st Workshop on Large-Scale Multimedia Retrieval and Mining (LS-MMRM) in conjunction with ACM Multimedia 2009, Beijing, China, 23 octobre 2009, pp. 43-50. [pdf]
[PCB08c]  Poullot, S., Crucianu, M., Buisson, O. (2008) Fast Content-Based Mining of Web2.0 Videos, Pacific-Rim Conference on Multimedia, Taiwan, décembre 2008. Springer Verlag, LNCS Vol. 5353, pp. 99-108. [pdf]
[PCB08a]  Poullot, S., Crucianu, M., Buisson, O. (2008) Scalable Mining of Large Video Databases Using Copy Detection, Dans Proceedings of ACM Multimedia 2008 (CORE A+, taux d'acceptation 18%, EIC 0,97), Vancouver, Canada, 27-30 octobre 2008, pp. 61-70. [pdf]
[PBC07]  Poullot, S., Buisson, O., Crucianu, M. (2007) Z-grid-based Probabilistic Retrieval for Scaling Up Content-Based Copy Detection, ACM International Conference on Image and Video Retrieval (taux d'acceptation 37%), Amsterdam, July 9-11, 2007, pp. 348-355. [pdf]
[FBC05a]  Ferecatu, M., Boujemaa, N., Crucianu, M. (2005) Hybrid Visual and Conceptual Image Representation in an Active Relevance Feedback Context, Proceedings of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (taux d'acceptation 44,68%), Singapour, 6-12 novembre 2005, pp. 209-216. [pdf]
[GCB05a]  Grira, N., Crucianu, M., Boujemaa, N. (2005) Active Semi-Supervised Fuzzy Clustering for Image Database Categorization, Proceedings of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (taux d'acceptation 44,68%), Singapour, 6-12 novembre 2005, pp. 9-16.
[GCB05b]  Grira, N., Crucianu, M., Boujemaa, N. (2005) Active semi-supervised clustering for image database categorization, Content-Based Multimedia Indexing (CBMI'05), Riga, Latvia, juin 2005. [pdf]
[GCB05c]  Grira, N., Crucianu, M., Boujemaa, N. (2005) Semi-supervised image database categorization using pairwise constraints, International Conference on Image Processing (ICIP'05, CORE A, taux d'acceptation 42,5%, EIC 0,71), Genova, Italie, septembre 2005, pp. 1228-1231. [bibtex]
[FBC05c]  Ferecatu, M., Crucianu, M., Boujemaa, N. (2005) Improving performance of interactive categorization of images using relevance feedback, International Conference on Image Processing (ICIP'05, CORE A, taux d'acceptation 42,5%, EIC 0,71), Genova, Italie, septembre 2005, pp. 1197-1200. [bibtex]
[GCB05d]  Grira, N., Crucianu, Boujemaa, N. (2005) Semi-supervised fuzzy clustering with pairwise-constrained competitive agglomeration, Proceedings of the IEEE International Conference on Fuzzy Systems (Fuzz'IEEE 2005), Reno, Etats-Unis, 22-25 mai 2005, pp. 80-86. [pdf][bibtex]
[FBC04a]  Ferecatu, M., Crucianu, M., Boujemaa, N. (2004) Sample selection strategies for relevance feedback in region-based image retrieval, dans K. Aizawa, Y. Nakamura, and S. Satoh (Eds.): Pacific-Rim Conference on Multimedia 2004 (taux d'acceptation 24,4%), Lecture Notes in Computer Science 3332, pp. 497-504, Springer-Verlag. [pdf][bibtex]
[FBC04b]  Ferecatu, M., Crucianu, M., Boujemaa, N. (2004) Retrieval of Difficult Image Classes Using SVM-Based Relevance Feedback, Proceedings of the 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (taux d'acceptation 39,25%), 15-16 octobre 2004, New York, pp. 23-30. [pdf]
[RCVF03]  Ramel, J.-Y., Crucianu, M., Vincent, N., Faure, C. (2003) Detection, extraction and representation of tables, International Conference on Document Analysis and Recognition (ICDAR’03), 3-6 août 2003, Edinburgh, UK.

Conférences nationales avec comité de sélection

[PCB08b]  Poullot, S., Crucianu, M., Buisson, O. (2008) Passage à l'échelle de la fouille vidéo basée sur la détection de copies, Bases de Données Avancées, Valence, octobre 2008. [pdf]
[CEOT07]  Crucianu, M., Estevez, D., Oria, V., Tarel, J.-Ph. (2007) Recherche approximative des kppv pour des requêtes hyperplans, avec application au contrôle de pertinence actif, Bases de Données Avancées (BDA 2007), Marseille, 23-26 octobre 2007.
[FC03]  Fernandez, Y., Crucianu, M. (2003) Dimensions perceptives pour un espace musical, Compression et Représentation de Signaux Audiovisuels (CORESA’03), 16-17 janvier 2003, Lyon, France, pp. 45-48. [pdf]

Divers

[CRU14]  Crucianu, M. (2014) Multimedia Information Retrieval: Beyond Ranking. Keynote talk, 2014 International Workshop on Computational Intelligence for Multimedia Understanding, 1-2 novembre 2014, Paris, France. [transparents en pdf]
[CRU10]  Crucianu, M. (2010) Kernel Approximation by Locality Sensitive Hashing with Application to Active Learning. Rapport de recherche CEDRIC No 1898, 10 pages, mars 2010.
[LPC09]  D.-D. Le, S. Poullot, M. Crucianu, X. Wu, M. Nett, M. E. Houle, S. Satoh (2009) National Institute of Informatics at TRECVID 2009, TRECVID 2009 Workshop. [pdf]
[BCV08]  Boisson, F., Crucianu, M., Vodislav, D. (2008) Publication Framework for Content-Based Search in Heterogeneous Distributed Multimedia Databases, Research Report CEDRIC 1585, 10 septembre 2008, 18 pages. Présenté au CHORUS P2P Workshop 1P2P4mm (avec InfoScale 2008), Vico Equense, Italy, 6 juin 2008. [pdf]
[FBC05b]  Ferecatu, M., Crucianu, M., Boujemaa, N. (2005) Retour de pertinence actif avec une représentation hybride, visuelle et conceptuelle, des images, Rapport de recherche INRIA RR-5558, 20 avril 2005.
[CTF05]  Crucianu, M., Tarel, J.-Ph., Ferecatu, M. (2005) A Comparison of User Strategies in Image Retrieval with Relevance Feedback, 7th International Workshop on Audio-Visual Content and Information Visualization in Digital Libraries (AVIVDiLib'05), pp. 121-130, Cortona, Italie, 4-6 mai 2005.
[GCB04]  Grira, N., Crucianu, M., Boujemaa, N. (2004) Unsupervised and semi-supervised clustering: a brief survey, juillet 2004, 11 p., dans A Review of Machine Learning Techniques for Processing Multimedia Content, rapport du Réseau d'Excellence MUSCLE (6ePCRD). [pdf]
[CFB04]  Crucianu, M., Ferecatu, M., Boujemaa, N. (2004) Relevance feedback for image retrieval: a short survey, juin 2004, 20 p., dans State of the Art in Audiovisual Content-Based Retrieval, Information Universal Access and Interaction, Including Datamodels and Languages, rapport du Réseau d'Excellence DELOS2 (6ePCRD). [pdf]
[FBC04c]  Ferecatu, M., Crucianu, M., Boujemaa, N. (2004) Reducing the Redundancy in the Selection of Samples for SVM-based Relevance Feedback, Rapport de Recherche INRIA 5258, 5 mai 2004, 20 p. [html]
[Cru01]  Crucianu, M. (2001) L'hyperespace musical : définition, navigation, exploitation, Rapport interne n° 245, juin 2001, Laboratoire Informatique, Université de Tours, 8 p. [pdf]
[CMV01]  Crucianu, M., Martin, E., Verley, G. (2001) Adaptive structuring of information: a web-based approach, 7th International Conference on Re-engineering Technologies for Information Systems (ReTIS 2001), Lyon, 5-6 juillet 2001, Oesterreichische Computer Gesellschaft, pp. 207-212.
[CMV00]  Crucianu, M., Martin, E., Verley, G. (2000) A web-based approach to adaptive information structuring, Rapport Interne n° 236, Laboratoire d'Informatique, Université de Tours, octobre 2000. [pdf]

Vertigo | CEDRIC | CNAM © Michel Crucianu | A propos de ce site | 17 novembre 2023