{"id":4052,"date":"2022-06-13T08:56:05","date_gmt":"2022-06-13T07:56:05","guid":{"rendered":"https:\/\/www.ceessnoek.info\/?p=4052"},"modified":"2022-06-13T08:56:23","modified_gmt":"2022-06-13T07:56:23","slug":"cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers","status":"publish","type":"post","link":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/","title":{"rendered":"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers"},"content":{"rendered":"\n<p>The CVPR 2022 cam-ready for\u00a0<em>BoxeR: Box-Attention for 2D and 3D Transformers<\/em> by Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees G. M. Snoek is <a href=\"https:\/\/arxiv.org\/abs\/2111.13087\">now available<\/a>. In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision tasks. Specifically, we present BoxeR, short for Box Transformer, which attends to a set of boxes by predicting their transformation from a reference window on an input feature map. The BoxeR computes attention weights on these boxes by considering its grid structure. Notably, BoxeR-2D naturally reasons about box information within its attention module, making it suitable for end-to-end instance detection and segmentation tasks. By learning invariance to rotation in the box-attention module, BoxeR-3D is capable of generating discriminative information from a bird\u2019s-eye view plane for 3D end-to-end object detection. Our experiments demonstrate that the proposed BoxeR-2D achieves state-of- the-art results on COCO detection and instance segmentation. Besides, BoxeR-3D improves over the end-to-end 3D object detection baseline and already obtains a compelling performance for the vehicle category of Waymo Open, without any class-specific optimization.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png\"><img loading=\"lazy\" decoding=\"async\" width=\"1030\" height=\"522\" src=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png\" alt=\"\" class=\"wp-image-3939\" srcset=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png 1030w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer-300x152.png 300w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer-1024x519.png 1024w, https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer-768x389.png 768w\" sizes=\"auto, (max-width: 1030px) 100vw, 1030px\" \/><\/a><\/figure>\n\n\n\n<p>Code is available at\u00a0<a href=\"https:\/\/github.com\/kienduynguyen\/BoxeR\">https:\/\/github.com\/kienduynguyen\/BoxeR<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The CVPR 2022 cam-ready for\u00a0BoxeR: Box-Attention for 2D and 3D Transformers by Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees G. M. Snoek is now available. In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[],"class_list":["post-4052","post","type-post","status-publish","format-standard","hentry","category-science"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.3 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - 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\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - Cees Snoek\" \/>\n<meta property=\"og:description\" content=\"The CVPR 2022 cam-ready for\u00a0BoxeR: Box-Attention for 2D and 3D Transformers by Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees G. M. Snoek is now available. In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/\" \/>\n<meta property=\"og:site_name\" content=\"Cees Snoek\" \/>\n<meta property=\"article:published_time\" content=\"2022-06-13T07:56:05+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-06-13T07:56:23+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.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=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/\",\"url\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/\",\"name\":\"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - Cees Snoek\",\"isPartOf\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png\",\"datePublished\":\"2022-06-13T07:56:05+00:00\",\"dateModified\":\"2022-06-13T07:56:23+00:00\",\"author\":{\"@id\":\"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage\",\"url\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png\",\"contentUrl\":\"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png\",\"width\":1030,\"height\":522},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.ceessnoek.info\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers\"}]},{\"@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":"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - 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\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/","og_locale":"en_US","og_type":"article","og_title":"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - Cees Snoek","og_description":"The CVPR 2022 cam-ready for\u00a0BoxeR: Box-Attention for 2D and 3D Transformers by Duy-Kien Nguyen, Jihong Ju, Olaf Booij, Martin R. Oswald, Cees G. M. Snoek is now available. In this paper, we propose a simple attention mechanism, we call Box-Attention. It enables spatial interaction between grid features, as sampled from boxes of interest, and improves [&hellip;]","og_url":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/","og_site_name":"Cees Snoek","article_published_time":"2022-06-13T07:56:05+00:00","article_modified_time":"2022-06-13T07:56:23+00:00","og_image":[{"url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png","type":"","width":"","height":""}],"author":"Cees","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Cees","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/","url":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/","name":"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers - Cees Snoek","isPartOf":{"@id":"https:\/\/www.ceessnoek.info\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage"},"image":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage"},"thumbnailUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png","datePublished":"2022-06-13T07:56:05+00:00","dateModified":"2022-06-13T07:56:23+00:00","author":{"@id":"https:\/\/www.ceessnoek.info\/#\/schema\/person\/4bca975b7c432aeb5dced40bdbc204c1"},"breadcrumb":{"@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#primaryimage","url":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png","contentUrl":"https:\/\/www.ceessnoek.info\/wp-content\/uploads\/2021\/11\/kien-boxer.png","width":1030,"height":522},{"@type":"BreadcrumbList","@id":"https:\/\/www.ceessnoek.info\/index.php\/cvpr-2022-boxer-box-attention-for-2d-and-3d-transformers\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.ceessnoek.info\/"},{"@type":"ListItem","position":2,"name":"CVPR 2022: BoxeR: Box-Attention for 2D and 3D Transformers"}]},{"@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\/4052","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=4052"}],"version-history":[{"count":1,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4052\/revisions"}],"predecessor-version":[{"id":4053,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/posts\/4052\/revisions\/4053"}],"wp:attachment":[{"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/media?parent=4052"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/categories?post=4052"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.ceessnoek.info\/index.php\/wp-json\/wp\/v2\/tags?post=4052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}