{"id":4299,"date":"2023-10-01T23:35:17","date_gmt":"2023-10-01T22:35:17","guid":{"rendered":"https:\/\/www.ceessnoek.info\/?p=4299"},"modified":"2023-10-01T23:35:19","modified_gmt":"2023-10-01T22:35:19","slug":"iccv-2023-tubelet-contrastive-self-supervision","status":"publish","type":"post","link":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/","title":{"rendered":"ICCV 2023: Tubelet-Contrastive Self-Supervision"},"content":{"rendered":"\n<p>The ICCV 2023 paper Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization by <a href=\"https:\/\/fmthoker.github.io\">Fida Mohammad Thoker<\/a>, Hazel Doughty, Cees G M Snoek is <a href=\"https:\/\/arxiv.org\/abs\/2303.11003\">now available<\/a>. We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical local motion dynamics but an otherwise different appearance. We do so by adding synthetic motion trajectories to videos which we refer to as tubelets. By simulating different tubelet motions and applying transformations, such as scaling and rotation, we introduce motion patterns beyond what is present in the pretraining data. This allows us to learn a video representation that is remarkably data-efficient: our approach maintains performance when using only 25% of the pretraining videos. Experiments on 10 diverse downstream settings demonstrate our competitive performance and generalizability to new domains and fine-grained actions.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\"><img loading=\"lazy\" decoding=\"async\" width=\"930\" height=\"878\" src=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\" alt=\"\" class=\"wp-image-4196\" srcset=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png 930w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast-300x283.png 300w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast-768x725.png 768w\" sizes=\"auto, (max-width: 930px) 100vw, 930px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>The ICCV 2023 paper Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization by Fida Mohammad Thoker, Hazel Doughty, Cees G M Snoek is now available. We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4299","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek<\/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:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek\" \/>\n<meta property=\"og:description\" content=\"The ICCV 2023 paper Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization by Fida Mohammad Thoker, Hazel Doughty, Cees G M Snoek is now available. We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/\" \/>\n<meta property=\"og:site_name\" content=\"Cees Snoek\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-01T22:35:17+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2023-10-01T22:35:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\" \/>\n<meta name=\"author\" content=\"Cees\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Cees\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/\",\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/\",\"name\":\"ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek\",\"isPartOf\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\",\"datePublished\":\"2023-10-01T22:35:17+00:00\",\"dateModified\":\"2023-10-01T22:35:19+00:00\",\"author\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage\",\"url\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\",\"contentUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ceessnoek.info\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"ICCV 2023: Tubelet-Contrastive Self-Supervision\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.ceessnoek.info\/#website\",\"url\":\"https:\/\/www.ceessnoek.info\/\",\"name\":\"Cees Snoek\",\"description\":\"research on video and image ai\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.ceessnoek.info\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\",\"name\":\"Cees\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g\",\"caption\":\"Cees\"},\"sameAs\":[\"http:\/\/www.CeesSnoek.info\"],\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek","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:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/","og_locale":"en_US","og_type":"article","og_title":"ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek","og_description":"The ICCV 2023 paper Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization by Fida Mohammad Thoker, Hazel Doughty, Cees G M Snoek is now available. We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn similarities between videos with identical [&hellip;]","og_url":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/","og_site_name":"Cees Snoek","article_published_time":"2023-10-01T22:35:17+00:00","article_modified_time":"2023-10-01T22:35:19+00:00","og_image":[{"url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png","type":"","width":"","height":""}],"author":"Cees","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Cees","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/","url":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/","name":"ICCV 2023: Tubelet-Contrastive Self-Supervision - Cees Snoek","isPartOf":{"@id":"https:\/\/www.ceessnoek.info\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage"},"image":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png","datePublished":"2023-10-01T22:35:17+00:00","dateModified":"2023-10-01T22:35:19+00:00","author":{"@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1"},"breadcrumb":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#primaryimage","url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png","contentUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2023\/03\/thoker-tubelet-contrast.png"},{"@type":"BreadcrumbList","@id":"https:\/\/www.ceessnoek.info\/index.php\/iccv-2023-tubelet-contrastive-self-supervision\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ceessnoek.info\/"},{"@type":"ListItem","position":2,"name":"ICCV 2023: Tubelet-Contrastive Self-Supervision"}]},{"@type":"WebSite","@id":"https:\/\/www.ceessnoek.info\/#website","url":"https:\/\/www.ceessnoek.info\/","name":"Cees Snoek","description":"research on video and image ai","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.ceessnoek.info\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1","name":"Cees","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/756ccb993852c1e8e3af39a228d11a7305b2a937750f26dc5799d5df019b0f51?s=96&d=mm&r=g","caption":"Cees"},"sameAs":["http:\/\/www.CeesSnoek.info"],"url":"https:\/\/www.ceessnoek.info\/index.php\/author\/admin\/"}]}},"_links":{"self":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4299","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/comments?post=4299"}],"version-history":[{"count":1,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4299\/revisions"}],"predecessor-version":[{"id":4300,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4299\/revisions\/4300"}],"wp:attachment":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/media?parent=4299"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/categories?post=4299"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/tags?post=4299"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}