{"id":6033,"date":"2025-01-16T04:27:00","date_gmt":"2025-01-15T19:27:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=6033"},"modified":"2025-01-16T04:27:00","modified_gmt":"2025-01-15T19:27:00","slug":"sa2va-marrying-sam2-with-llava-for-dense-grounded-understanding-of-images-and-videos","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=6033","title":{"rendered":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos\u00a0<\/strong>[110.3]<br>Sa2VA\u306f\u3001\u753b\u50cf\u3068\u30d3\u30c7\u30aa\u306e\u4e21\u65b9\u306e\u57fa\u76e4\u7684\u7406\u89e3\u306e\u305f\u3081\u306e\u7d71\u4e00\u30e2\u30c7\u30eb\u3067\u3042\u308b\u3002 \u30bb\u30b0\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\u3084\u4f1a\u8a71\u306a\u3069\u3001\u5e45\u5e83\u3044\u753b\u50cf\u3084\u30d3\u30c7\u30aa\u306e\u30bf\u30b9\u30af\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308b\u3002 \u672c\u7a3f\u3067\u306f,\u8907\u6570\u306e\u30bf\u30b9\u30af,\u7279\u306b\u30d3\u30c7\u30aa\u30aa\u30d6\u30b8\u30a7\u30af\u30c8\u306e\u30bb\u30b0\u30e1\u30f3\u30c6\u30fc\u30b7\u30e7\u30f3\u306b\u304a\u3044\u3066,Sa2VA\u304c\u6700\u5148\u7aef\u3092\u5b9f\u73fe\u3059\u308b\u3053\u3068\u3092\u793a\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2501.04001v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2501.04001v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 07 Jan 2025 18:58:54 GMT)<\/li>\n\n\n\n<li>\u300cBy leveraging the knowledge from both LLaVA and SAM-2, our model has strong capabilities in both mask and language generation.\u300d\u3068\u306e\u3053\u3068\u3002\u306a\u308b\u307b\u3069\u3001\u3068\u3044\u3046\u611f\u3058\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/lxtgh.github.io\/project\/sa2va\/\">Sa2VA<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[251,484],"class_list":["post-6033","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mllm","tag-484"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6033","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=6033"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/6033\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=6033"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=6033"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=6033"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}