{"id":775438,"date":"2021-07-21T08:58:37","date_gmt":"2021-07-21T15:58:37","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=775438"},"modified":"2021-09-16T09:01:04","modified_gmt":"2021-09-16T16:01:04","slug":"grounded-visual-generation","status":"publish","type":"msr-video","link":"https:\/\/www.microsoft.com\/en-us\/research\/video\/grounded-visual-generation\/","title":{"rendered":"Grounded Visual Generation"},"content":{"rendered":"<p>Multi-modal data provides an exciting opportunity to train grounded generative models that synthesize images consistent with real world phenomena. In this talk, I will share several of our recent efforts towards creating grounded visual generation models: (1) introducing user attention grounding for text-to-image synthesis, (2) improving text-to-image generation results with stronger language grounding, and (3) taking steps towards creating spatially grounded world models for embodied vision-and-language tasks.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Multi-modal data provides an exciting opportunity to train grounded generative models that synthesize images consistent with real world phenomena. In this talk, I will share several of our recent efforts towards creating grounded visual generation models: (1) introducing user attention grounding for text-to-image synthesis, (2) improving text-to-image generation results with stronger language grounding, and (3) [&hellip;]<\/p>\n","protected":false},"featured_media":775441,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-video-type":[259633],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-775438","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-video-type-vision-language-summer-talk-series","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/fLqF4isdWPg","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/775438"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/775438\/revisions"}],"predecessor-version":[{"id":775444,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/775438\/revisions\/775444"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/775441"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=775438"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=775438"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=775438"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=775438"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=775438"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=775438"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=775438"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}