{"id":13642,"date":"2024-07-31T09:28:08","date_gmt":"2024-07-31T09:28:08","guid":{"rendered":"https:\/\/dailyai.com\/?p=13642"},"modified":"2024-07-31T17:50:03","modified_gmt":"2024-07-31T17:50:03","slug":"metas-sam-2-model-enables-accurate-video-segmentation-in-seconds","status":"publish","type":"post","link":"https:\/\/dailyai.com\/fr\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/","title":{"rendered":"Le mod\u00e8le SAM 2 de Meta permet une segmentation vid\u00e9o pr\u00e9cise en quelques secondes"},"content":{"rendered":"

La division recherche de Meta a pr\u00e9sent\u00e9 SAM 2 (Segment Anything Model 2), un syst\u00e8me d'intelligence artificielle qui marque une avanc\u00e9e consid\u00e9rable dans l'analyse vid\u00e9o.<\/b><\/p>\n

Ce nouveau mod\u00e8le d\u00e9veloppe les comp\u00e9tences de son pr\u00e9d\u00e9cesseur SAM en mati\u00e8re de segmentation d'images, en s'aventurant dans le domaine plus complexe de la vid\u00e9o.<\/span><\/p>\n

La segmentation vid\u00e9o - la capacit\u00e9 d'identifier et de suivre des objets sp\u00e9cifiques dans une sc\u00e8ne en mouvement - est depuis longtemps un d\u00e9fi pour l'IA.\u00a0<\/span><\/p>\n

Alors que les humains peuvent suivre sans effort une voiture dans la circulation ou une personne marchant dans une foule, les syst\u00e8mes d'IA ont tendance \u00e0 \u00e9prouver des difficult\u00e9s.\u00a0<\/span>Il s'agit d'un probl\u00e8me majeur pour voitures sans conducteur<\/a> et d'autres v\u00e9hicules autonomes (AV), qui doivent suivre des objets 3D en mouvement dans leur environnement.<\/p>\n

SAM 2<\/span><\/a> vise \u00e0 combler ce foss\u00e9, en rapprochant la compr\u00e9hension de la vid\u00e9o par l'IA de la perception humaine.<\/span><\/p>\n

Le syst\u00e8me peut identifier et suivre pratiquement n'importe quel objet dans une vid\u00e9o avec un minimum d'intervention de la part de l'utilisateur - parfois un simple clic. <\/span>Cela ouvre un monde de possibilit\u00e9s dans des domaines allant du montage de films \u00e0 la recherche scientifique.<\/span><\/p>\n

Voici comment Meta a cr\u00e9\u00e9 et test\u00e9 SAM 2 :<\/span><\/p>\n

    \n
  1. L'\u00e9quipe a cr\u00e9\u00e9 une technique appel\u00e9e \"Promptable Visual Segmentation\" (PVS), qui permet aux utilisateurs de guider l'IA \u00e0 l'aide de simples indices sur n'importe quelle image vid\u00e9o. Cela signifie que le syst\u00e8me peut s'adapter \u00e0 un large \u00e9ventail de sc\u00e9narios, qu'il s'agisse de suivre une personne sp\u00e9cifique dans une foule ou de suivre le mouvement de l'aile d'un oiseau en vol.<\/span><\/li>\n
  2. Ils ont construit une architecture de mod\u00e8le qui comprend des composants pour le traitement des images individuelles, le stockage d'informations sur les objets dans le temps et la g\u00e9n\u00e9ration de segmentations pr\u00e9cises. <\/span><\/li>\n
  3. Un \u00e9l\u00e9ment cl\u00e9 est le module de m\u00e9moire, qui permet \u00e0 SAM 2 de maintenir un suivi coh\u00e9rent m\u00eame lorsque des objets disparaissent temporairement de la vue.<\/span><\/li>\n
  4. Un nouvel ensemble de donn\u00e9es massif a \u00e9t\u00e9 cr\u00e9\u00e9, contenant plus de 50 000 vid\u00e9os et 35 millions d'images \u00e9tiquet\u00e9es, ce qui \u00e9clipse les pr\u00e9c\u00e9dents ensembles de donn\u00e9es de segmentation vid\u00e9o. T<\/span><\/li>\n
  5. Cet ensemble de donn\u00e9es, appel\u00e9 SA-V, couvre un large \u00e9ventail de types d'objets, de tailles et de sc\u00e9narios, ce qui renforce la capacit\u00e9 du mod\u00e8le \u00e0 s'adapter \u00e0 de nouvelles situations.<\/span><\/li>\n
  6. Le mod\u00e8le a fait l'objet d'une formation et de tests approfondis sur 17 ensembles de donn\u00e9es vid\u00e9o divers, allant des s\u00e9quences de cam\u00e9ras de surveillance \u00e0 l'imagerie m\u00e9dicale. <\/span><\/li>\n
  7. SAM 2 a surpass\u00e9 les m\u00e9thodes de pointe existantes dans les t\u00e2ches de segmentation d'objets vid\u00e9o semi-supervis\u00e9es, obtenant une am\u00e9lioration moyenne de 7,5% dans les scores J&F (une mesure standard de la qualit\u00e9 de la segmentation).<\/span><\/li>\n<\/ol>\n
    https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/An9rqhh8jLAD81wdPLApEcu-1Z2NzXx4_528PrvelbMmWVgTvtk8DgdwDHRYohgxxotkX_WENwyB-eegqi3EQXlQ.mp4<\/a><\/video><\/div>\n

    Au-dessus<\/strong>: La segmentation d'images pour des clips vid\u00e9o complexes permet de s\u00e9parer diff\u00e9rentes formes en quelques secondes.<\/p>\n

      \n
    • Dans la production cin\u00e9matographique, SAM 2 pourrait rationaliser le travail sur les effets visuels, ce qui permettrait de gagner du temps en post-production.<\/li>\n
    • Les scientifiques pourraient suivre des cellules dans des images microscopiques ou surveiller les changements environnementaux dans l'imagerie satellitaire.<\/li>\n
    • Pour les AV, y compris les voitures sans conducteur, SAM 2 pourrait am\u00e9liorer la d\u00e9tection d'objets dans des sc\u00e9narios de circulation complexes<\/li>\n
    • Les d\u00e9fenseurs de la faune et de la flore pourraient utiliser SAM 2 pour surveiller les populations animales dans de vastes zones.<\/li>\n
    • Dans le domaine de l'AR\/VR, il peut permettre des interactions plus pr\u00e9cises avec des objets virtuels dans une vid\u00e9o en direct.<\/li>\n<\/ul>\n

      Fid\u00e8le \u00e0 l'engagement de Meta en faveur de la recherche ouverte, SAM 2 est publi\u00e9 en tant que logiciel libre.\u00a0<\/span><\/p>\n

      Il s'agit non seulement du mod\u00e8le, mais aussi de l'ensemble de donn\u00e9es utilis\u00e9 pour l'entra\u00eener.\u00a0<\/span><\/p>\n

      Les chercheurs \u00e9tudient d\u00e9j\u00e0 les moyens de traiter des vid\u00e9os plus longues, d'am\u00e9liorer les performances sur les d\u00e9tails fins et de r\u00e9duire la puissance de calcul n\u00e9cessaire pour faire fonctionner le mod\u00e8le.<\/span><\/p>\n

      Au fur et \u00e0 mesure que la technologie de segmentation des images \u00e9volue, elle va certainement transformer la fa\u00e7on dont nous interagissons avec le contenu vid\u00e9o et dont nous l'analysons. <\/span><\/p>\n

      En rendant les t\u00e2ches d'\u00e9dition complexes plus accessibles et en permettant de nouvelles formes d'analyse visuelle, SAM 2 repousse les limites de la manipulation visuelle.\u00a0<\/span><\/p>","protected":false},"excerpt":{"rendered":"

      La division recherche de Meta a pr\u00e9sent\u00e9 SAM 2 (Segment Anything Model 2), un syst\u00e8me d'IA qui marque une avanc\u00e9e consid\u00e9rable dans le domaine de l'analyse vid\u00e9o. Ce nouveau mod\u00e8le d\u00e9veloppe les comp\u00e9tences de son pr\u00e9d\u00e9cesseur SAM en mati\u00e8re de segmentation d'images, en s'aventurant dans le domaine plus complexe de la vid\u00e9o. La segmentation vid\u00e9o - la capacit\u00e9 d'identifier et de suivre des objets sp\u00e9cifiques dans une sc\u00e8ne en mouvement - est depuis longtemps un d\u00e9fi pour l'IA. Alors que les humains peuvent suivre sans effort une voiture qui se d\u00e9place dans la circulation ou une personne qui marche dans une foule, les syst\u00e8mes d'IA ont tendance \u00e0 \u00e9prouver des difficult\u00e9s. Il s'agit d'un probl\u00e8me majeur pour les voitures sans conducteur et les autres v\u00e9hicules autonomes,<\/p>","protected":false},"author":2,"featured_media":13644,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[84],"tags":[105,131],"class_list":["post-13642","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-industry","tag-machine-learning","tag-meta"],"yoast_head":"\nMeta's SAM 2 model enables accurate video segmentation in seconds | DailyAI<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/fr\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Meta's SAM 2 model enables accurate video segmentation in seconds | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Meta’s research division has introduced SAM 2 (Segment Anything Model 2), an AI system that marks a huge advancement in video analysis. This new model expands on its predecessor SAM\u2019s image segmentation skills, venturing into the more complex domain of video. Video segmentation – the ability to identify and track specific objects in a moving scene – has long been a challenge for AI.\u00a0 While humans can effortlessly follow a car as it moves through traffic or a person walking through a crowd, AI systems tend to struggle.\u00a0This is a massive problem for driverless cars and other autonomous vehicles (AVs),\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/fr\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2024-07-31T09:28:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-07-31T17:50:03+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1792\" \/>\n\t<meta property=\"og:image:height\" content=\"1024\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"\u00c9crit par\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Meta’s SAM 2 model enables accurate video segmentation in seconds\",\"datePublished\":\"2024-07-31T09:28:08+00:00\",\"dateModified\":\"2024-07-31T17:50:03+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/\"},\"wordCount\":562,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp\",\"keywords\":[\"machine learning\",\"Meta\"],\"articleSection\":[\"Industry\"],\"inLanguage\":\"fr-FR\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/\",\"name\":\"Meta's SAM 2 model enables accurate video segmentation in seconds | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp\",\"datePublished\":\"2024-07-31T09:28:08+00:00\",\"dateModified\":\"2024-07-31T17:50:03+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2024\\\/07\\\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp\",\"width\":1792,\"height\":1024,\"caption\":\"AI meta\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2024\\\/07\\\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Meta’s SAM 2 model enables accurate video segmentation in seconds\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/fr\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Le mod\u00e8le SAM 2 de Meta permet une segmentation vid\u00e9o pr\u00e9cise en quelques secondes | DailyAI","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/fr\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/","og_locale":"fr_FR","og_type":"article","og_title":"Meta's SAM 2 model enables accurate video segmentation in seconds | DailyAI","og_description":"Meta’s research division has introduced SAM 2 (Segment Anything Model 2), an AI system that marks a huge advancement in video analysis. This new model expands on its predecessor SAM\u2019s image segmentation skills, venturing into the more complex domain of video. Video segmentation – the ability to identify and track specific objects in a moving scene – has long been a challenge for AI.\u00a0 While humans can effortlessly follow a car as it moves through traffic or a person walking through a crowd, AI systems tend to struggle.\u00a0This is a massive problem for driverless cars and other autonomous vehicles (AVs),","og_url":"https:\/\/dailyai.com\/fr\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/","og_site_name":"DailyAI","article_published_time":"2024-07-31T09:28:08+00:00","article_modified_time":"2024-07-31T17:50:03+00:00","og_image":[{"width":1792,"height":1024,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp","type":"image\/webp"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"\u00c9crit par":"Sam Jeans","Dur\u00e9e de lecture estim\u00e9e":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Meta’s SAM 2 model enables accurate video segmentation in seconds","datePublished":"2024-07-31T09:28:08+00:00","dateModified":"2024-07-31T17:50:03+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/"},"wordCount":562,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp","keywords":["machine learning","Meta"],"articleSection":["Industry"],"inLanguage":"fr-FR"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/","url":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/","name":"Le mod\u00e8le SAM 2 de Meta permet une segmentation vid\u00e9o pr\u00e9cise en quelques secondes | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp","datePublished":"2024-07-31T09:28:08+00:00","dateModified":"2024-07-31T17:50:03+00:00","breadcrumb":{"@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/"]}]},{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2024\/07\/DALL\u00b7E-2024-07-31-10.22.07-Create-a-high-quality-landscape-image-showcasing-a-person-with-a-clear-outline-around-them-to-demonstrate-the-concept-of-image-segmentation.-The-back.webp","width":1792,"height":1024,"caption":"AI meta"},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2024\/07\/metas-sam-2-model-enables-accurate-video-segmentation-in-seconds\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Meta’s SAM 2 model enables accurate video segmentation in seconds"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Votre dose quotidienne de nouvelles sur l'IA","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam est un r\u00e9dacteur scientifique et technologique qui a travaill\u00e9 dans diverses start-ups sp\u00e9cialis\u00e9es dans l'IA. Lorsqu'il n'\u00e9crit pas, on peut le trouver en train de lire des revues m\u00e9dicales ou de fouiller dans des bo\u00eetes de disques vinyles.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/fr\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/13642","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/comments?post=13642"}],"version-history":[{"count":3,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/13642\/revisions"}],"predecessor-version":[{"id":13648,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/posts\/13642\/revisions\/13648"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media\/13644"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/media?parent=13642"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/categories?post=13642"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/fr\/wp-json\/wp\/v2\/tags?post=13642"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}