Quand: le 21 septembre 2016 \u00e0 14 heures –
\nO\u00f9: Tour 55 – couloir 55\/65 – 2\u00e8me \u00e9tage – Salle 211
\nUniversit\u00e9 Pierre et Marie Curie
\n4 place Jussieu – 75005 Paris<\/p>\n
Directeur de th\u00e8se :<\/strong> Titus ZAHARIA – Professeur<\/p>\n Rapporteurs :<\/strong><\/p>\n Malik MALLEM – Professeur – Universit\u00e9 d’Evry Val d’Essonne<\/p>\n Antoine MANZANERA – Professeur – ENSTA-ParisTech<\/p>\n Examinateurs :<\/strong><\/p>\n Catherine ACHARD – Ma\u00eetre de conf\u00e9rences HDR – Universit\u00e9 Paris 6 – France<\/p>\n Anne BLONDET-VERROUST – Charg\u00e9e de recherche – INRIA<\/p>\n Bertrand DELEZOIDE – Head of multimedia research team – Docteur – CEA Tech – LIST – France<\/p>\n R\u00e9sum\u00e9 :<\/em><\/p>\n Aujourd\u2019hui, les recherches portant sur le geste manquent de mod\u00e8les g\u00e9n\u00e9riques. Les sp\u00e9cialistes du geste doivent osciller entre une formalisation excessivement conceptuelle et une description purement visuelle du mouvement.<\/p>\n Nous reprenons les concepts d\u00e9velopp\u00e9s par le chor\u00e9graphe Rudolf Laban pour l\u2019analyse de la danse classique contemporaine, et proposons leur extension afin d\u2019\u00e9laborer un mod\u00e8le g\u00e9n\u00e9rique du geste bas\u00e9 sur ses \u00e9l\u00e9ments expressifs.<\/p>\n Nous pr\u00e9sentons \u00e9galement deux corpus de gestes 3D que nous avons constitu\u00e9s. Le premier, ORCHESTRE-3D, se compose de gestes pr\u00e9-segment\u00e9s de chefs d\u2019orchestre enregistr\u00e9s en r\u00e9p\u00e9tition. Son annotation \u00e0 l\u2019aide d\u2019\u00e9motions musicales est destin\u00e9e \u00e0 l\u2019\u00e9tude du contenu \u00e9motionnel de la direction musicale. Le deuxi\u00e8me corpus, HTI 2014-2015, propose des s\u00e9quences d\u2019actions vari\u00e9es de la vie quotidienne.<\/p>\n Dans une premi\u00e8re approche de reconnaissance dite \u00ab globale \u00bb, nous d\u00e9finissons un descripteur qui se rapporte \u00e0 l\u2019enti\u00e8ret\u00e9 du geste. Ce type de caract\u00e9risation nous permet de discriminer diverses actions, ainsi que de reconna\u00eetre les diff\u00e9rentes \u00e9motions musicales que portent les gestes des chefs d\u2019orchestre de notre base ORCHESTRE-3D. Abstract:<\/em><\/p>\n Nowadays, researches dealing with gesture analysis suffer from a lack of unified mathematical models. On the one hand, gesture formalizations by human sciences remain purely theoretical and are not inclined to any quantification. On the other hand, the commonly used motion descriptors are generally purely intuitive, and limited to the visual aspects of the gesture.<\/p>\n In the present work, we retain Laban Movement Analysis (LMA \u2013 originally designed for the study of dance movements) as a framework for building our own gesture descriptors, based on expressivity.<\/p>\n Two datasets are introduced: the first one is called ORCHESTRE-3D, and is composed of pre-segmented orchestra conductors\u2019 gestures, which have been annotated with the help of lexicon of musical emotions. The second one, HTI 2014-2015, comprises sequences of multiple daily actions.<\/p>\n In a first experiment, we define a global feature vector based upon the expressive indices of our model and dedicated to the characterization of the whole gesture. This descriptor is used for action recognition purpose and to discriminate the different emotions of our orchestra conductors\u2019 dataset. Quand: le 21 septembre 2016 \u00e0 14 heures – O\u00f9: Tour 55 – couloir 55\/65 – 2\u00e8me \u00e9tage – Salle 211 Universit\u00e9 Pierre et Marie Curie 4 place Jussieu – 75005 Paris Directeur de th\u00e8se : Titus ZAHARIA – Professeur Rapporteurs : Malik MALLEM – Professeur – Universit\u00e9 d’Evry Val d’Essonne Antoine MANZANERA – Professeur […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[350],"tags":[],"class_list":["post-770","post","type-post","status-publish","format-standard","hentry","category-theses-2016-fr","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/770","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=770"}],"version-history":[{"count":1,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/770\/revisions"}],"predecessor-version":[{"id":1664,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/770\/revisions\/1664"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=770"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=770"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=770"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\nDans une seconde approche dite \u00ab dynamique \u00bb, nous d\u00e9finissons un descripteur de trame gestuelle (e.g. d\u00e9fini pour tout instant du geste). Les descripteurs de trame sont utilis\u00e9s des poses-cl\u00e9s du mouvement, de sorte \u00e0 en obtenir \u00e0 tout instant une repr\u00e9sentation simplifi\u00e9e et utilisable pour reconna\u00eetre des actions \u00e0 la vol\u00e9e. Nous testons notre approche sur plusieurs bases de geste, dont notre propre corpus HTI 2014-2015.<\/p>\n
\nIn a second approach, the different elements of our expressive model are used as a frame descriptor (e.g., describing the gesture at a given time). The feature space provided by such local characteristics is used to extract key poses of the motion. With the help of such poses, we obtain a per-frame sub-representation of body motions which is available for real-time action recognition purpose.<\/p>\n","protected":false},"excerpt":{"rendered":"