Efficient dynamic texture classification with probabilistic motifs

Autor: Luong Phat Nguyen, Julien Mille, Dominique H. Li, Donatello Conte, Nicolas Ragot

We propose to tackle dynamic texture video classification as a pattern mining problem. In a nutshell, videos are represented by frequent sequences of representative patches. Firstly, we use a Gaussian Mixture Model to make the clustering of patches f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ff980259bc1e8e85c5b6631cb16c5cca
https://hal.science/hal-03700841

Euclidean Distance-Based Skeletons: A Few Notes on Average Outward Flux and Ridgeness

Autor: Aurélie Leborgne, Julien Mille, Laure Tougne

Publikováno v: International Journal of Mathematical Imaging and Vision
International Journal of Mathematical Imaging and Vision, 2019, 61 (3), pp.310-330. ⟨10.1007/s10851-018-0836-7⟩
International Journal of Mathematical Imaging and Vision, Springer Verlag, 2019, 61 (3), pp.310-330. ⟨10.1007/s10851-018-0836-7⟩

International audience; Among the various existing and mathematically equivalent definitions of the skeleton, we consider the set of critical points of the Euclidean distance transform of the shape. The problem of detecting these points and using the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0e94e427f8331c6b165b913448651f87
https://hal.science/hal-01866288

Human Action Recognition: Pose-based Attention draws focus to Hands

Autor: Julien Mille, Fabien Baradel, Christian Wolf

Publikováno v: ICCV Workshop on Hands in Action
ICCV Workshop on Hands in Action, Oct 2017, Venice, Italy
ICCV Workshops

We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect the most discriminative moments in an action. Attention is handled in a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a962516f922a9a3d95324bab429a20c6
https://hal.archives-ouvertes.fr/hal-01575390

Adding a rigid motion model to foreground detection: application to moving object detection in rivers

Autor: Imtiaz Ali, Laure Tougne, Julien Mille

Publikováno v: Pattern Analysis and Applications
Pattern Analysis and Applications, Springer Verlag, 2014, 3, 17, pp.567-585. ⟨10.1007/s10044-013-0346-6⟩

International audience; Object detection in a dynamic backgroundis a challenging task in many computer vision applica-tions. In some situations, the motion of objects can bepredicted thanks to its regularity (e.g. vehicle motion,pedestrian motion). I

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c47f83522be468a87a9a434d63ffd6bb
https://doi.org/10.1007/s10044-013-0346-6

Evaluation framework for carotid bifurcation lumen segmentation and stenosis grading

Autor: Leo Joskowicz, Moti Freiman, Karl Krissian, Jacob Sosna, Coert Metz, Noy Cohen, Ingrid Sanchez, Julien Mille, T. van Walsum, Wiro J. Niessen, Maciej Orkisz, Wilbur C.K. Wong, M. P M Q van Gils, K. Hameeteman, M. Hernández Hoyos, Gabriel P. Krestin, L. Florez Valencia, L. van den Borne, Olivier Cuisenaire, Michiel Schaap, Mehmet Akif Gulsun, P. Berman, A. van der Lugt, Philippe Douek, Maria A. Zuluaga, Huseyin Tek, M. Aissat, Fethallah Benmansour, S. Rozie, Albert C. S. Chung

Publikováno v: Medical Image Analysis
Medical Image Analysis, Elsevier, 2011, 15 (4), pp.477-488. ⟨10.1016/j.media.2011.02.004⟩
Medical Image Analysis, 15(4), 477-488. Elsevier

International audience; This paper describes an evaluation framework that allows a standardized and objective quantitative comparison of carotid artery lumen segmentation and stenosis grading algorithms. We describe the data repository comprising 56

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::27332a824966de70a664d31b04ad79e6
https://doi.org/10.1016/j.media.2011.02.004