{"id":23,"date":"2024-05-12T16:49:54","date_gmt":"2024-05-12T16:49:54","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/?page_id=23"},"modified":"2024-12-08T19:58:34","modified_gmt":"2024-12-08T19:58:34","slug":"methods","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/","title":{"rendered":"METHOD"},"content":{"rendered":"\n<h2 class=\"wp-block-heading\"><strong>VQAScore<\/strong><\/h2>\n\n\n\n<p>Given an image and text, we calculate the probability of a \u201cYes\u201d answer to a simple question like \u201cDoes this figure show \u2018{text}\u2019? Please answer yes or no.\u201d<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter is-resized\"><img decoding=\"async\" src=\"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048\" alt=\"\" style=\"width:264px;height:auto\" \/><\/figure>\n<\/div>\n\n\n<p><strong>VQA Model for Text-to-Visual Evaluation<\/strong><\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter is-resized\"><img decoding=\"async\" src=\"https:\/\/mscvprojectsricmu.files.wordpress.com\/2024\/05\/1715383072617.png?w=1024\" alt=\"\" class=\"wp-image-187\" style=\"width:561px;height:auto\" \/><\/figure>\n<\/div>\n\n\n<p><strong>Evaluate Text-to-Visual Generation with VQAScore<\/strong><\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter is-resized\"><img decoding=\"async\" src=\"https:\/\/mscvprojectsricmu.files.wordpress.com\/2024\/05\/1715383177332.png?w=882\" alt=\"\" class=\"wp-image-189\" style=\"width:595px;height:auto\" \/><\/figure>\n<\/div>\n\n\n<p><strong>Enhance VQAScore on video by considering the spatial and temporal relations:\u00a0<\/strong><\/p>\n\n\n\n<p class=\"has-text-align-center\"><img decoding=\"async\" src=\"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUffQnjUe42Ks-599dxcfyZLrYm6xN5vs4G7tHngMue0AAtlYgx8Mux6ftSqGc0Hjt5xKkptS25Xb2cTiCQOGbt2hyFbduUdHFzqEGI6Alzy9O-K4_EtvpzANWLY99xVVnDjGq2dn6Yf4aGh3f_j-zfCu50tokyn=s2048?key=Nuf53unSDtWR-j63I7HW4g\" style=\"width: 600px\"><\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>GenAI-Benchmark<\/strong><\/h2>\n\n\n\n<p>For robust text-to-visual generation evaluation, we collected 1,600 challenging real-world text prompts sourced from professional designers and a total of 38,400 human alignment ratings.<\/p>\n\n\n<div class=\"wp-block-image\">\n<figure class=\"aligncenter is-resized\"><img decoding=\"async\" src=\"https:\/\/lh7-us.googleusercontent.com\/p-fzVDowLNRZi1PraJs21_HwoeInKaMjblMzmR_VCiqWZW5ymT_3ehat3H3tg3pZMq4t8cGP3XtmY6WWP9FYjwZ47PCtsw2OtSnDVS49eoTivxGM4vqhsDxRc9tgvVcpfSEdEQt-kME6s9SgnDGgiOHp0g=s2048\" alt=\"\" style=\"width:591px;height:auto\" \/><\/figure>\n<\/div>\n\n\n<p><strong>Towards a Better T2V Evaluation Metric with VQAScore and GenAIBench<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Ranking a few candidate images with VQAScore and selecting the highest-scoring one.<\/li>\n\n\n\n<li>Setting a benchmark for ranking by collecting 43,200 human ratings.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Cinematic T2V Benchmark<\/strong><\/h2>\n\n\n\n<p><strong><strong>Improved Alignment with Camera Components in Text-to-Video Models<\/strong><\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>Developing a benchmark to enhance the understanding of camera components.<\/li>\n\n\n\n<li>Incorporating shot composition, camera movements, and lighting effects, enabling generative models to produce visually consistent and realistic videos.<\/li>\n<\/ul>\n\n\n\n<p class=\"has-text-align-center\"><img decoding=\"async\" src=\"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUfMHjmIplyeRU6CFwmzz8yfL-E_pn3KPAvnsZ1cdA3piB9eiN9F7DV6p_QGP4QFlxbeYeHVWEi3Pgn5DpF_wOOQgR77ocicVsNgZLPudxtNnqOT7lPD12miyBNdwz5NNBD_YkJl=s2048?key=UUd7d0nefy4knMpMsXGxOTsp\" style=\"width: 500px\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>VQAScore Given an image and text, we calculate the probability of a \u201cYes\u201d answer to a simple question like \u201cDoes this figure show \u2018{text}\u2019? Please answer yes or no.\u201d VQA Model for Text-to-Visual Evaluation Evaluate Text-to-Visual Generation with VQAScore Enhance VQAScore on video by considering the spatial and temporal relations:\u00a0 GenAI-Benchmark For robust text-to-visual generation &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;METHOD&#8221;<\/span><\/a><\/p>\n","protected":false},"author":205,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-23","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>METHOD - Alignment for Vision-Language Foundation Models<\/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:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"METHOD - Alignment for Vision-Language Foundation Models\" \/>\n<meta property=\"og:description\" content=\"VQAScore Given an image and text, we calculate the probability of a \u201cYes\u201d answer to a simple question like \u201cDoes this figure show \u2018{text}\u2019? Please answer yes or no.\u201d VQA Model for Text-to-Visual Evaluation Evaluate Text-to-Visual Generation with VQAScore Enhance VQAScore on video by considering the spatial and temporal relations:\u00a0 GenAI-Benchmark For robust text-to-visual generation &hellip; Continue reading &quot;METHOD&quot;\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/\" \/>\n<meta property=\"og:site_name\" content=\"Alignment for Vision-Language Foundation Models\" \/>\n<meta property=\"article:modified_time\" content=\"2024-12-08T19:58:34+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/\",\"name\":\"METHOD - Alignment for Vision-Language Foundation Models\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048\",\"datePublished\":\"2024-05-12T16:49:54+00:00\",\"dateModified\":\"2024-12-08T19:58:34+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/#primaryimage\",\"url\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048\",\"contentUrl\":\"https:\\\/\\\/lh7-us.googleusercontent.com\\\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/methods\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"METHOD\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/\",\"name\":\"Alignment for Vision-Language Foundation Models\",\"description\":\"Students: Yixin Fei, Kewen Wu, Pengliang Ji | Advisors: Zhiqiu Lin, Deva Ramanan (Carnegie Mellon University, Robotics Institute)\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2024team8\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"METHOD - Alignment for Vision-Language Foundation Models","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:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/","og_locale":"en_US","og_type":"article","og_title":"METHOD - Alignment for Vision-Language Foundation Models","og_description":"VQAScore Given an image and text, we calculate the probability of a \u201cYes\u201d answer to a simple question like \u201cDoes this figure show \u2018{text}\u2019? Please answer yes or no.\u201d VQA Model for Text-to-Visual Evaluation Evaluate Text-to-Visual Generation with VQAScore Enhance VQAScore on video by considering the spatial and temporal relations:\u00a0 GenAI-Benchmark For robust text-to-visual generation &hellip; Continue reading \"METHOD\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/","og_site_name":"Alignment for Vision-Language Foundation Models","article_modified_time":"2024-12-08T19:58:34+00:00","og_image":[{"url":"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/","name":"METHOD - Alignment for Vision-Language Foundation Models","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/#primaryimage"},"thumbnailUrl":"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048","datePublished":"2024-05-12T16:49:54+00:00","dateModified":"2024-12-08T19:58:34+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/#primaryimage","url":"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048","contentUrl":"https:\/\/lh7-us.googleusercontent.com\/QEXfyCI4lXu1tszjhCZpvI33hk8U8CeChJ8AihPYXLU3F4tmbeypznloFTMBrDxEqXkv1pcbd-a30qXY2Cj63amQqA9YNtpqSdHbbSlyMr0zSWCT7NTozLxtApswNFBx19yAUgn0xbKP0w8US5RtqKuogw=s2048"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/methods\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/"},{"@type":"ListItem","position":2,"name":"METHOD"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/","name":"Alignment for Vision-Language Foundation Models","description":"Students: Yixin Fei, Kewen Wu, Pengliang Ji | Advisors: Zhiqiu Lin, Deva Ramanan (Carnegie Mellon University, Robotics Institute)","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages\/23","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/users\/205"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/comments?post=23"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages\/23\/revisions"}],"predecessor-version":[{"id":97,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/pages\/23\/revisions\/97"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2024team8\/wp-json\/wp\/v2\/media?parent=23"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}