{"id":4090,"date":"2023-11-28T05:35:00","date_gmt":"2023-11-27T20:35:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4090"},"modified":"2023-11-28T05:35:00","modified_gmt":"2023-11-27T20:35:00","slug":"docpedia","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4090","title":{"rendered":"DocPedia"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding&nbsp;<\/strong>[98.4]<br>\u672c\u7814\u7a76\u306f, OCR\u30d5\u30ea\u30fc\u6587\u66f8\u7406\u89e3\u306e\u305f\u3081\u306e\u65b0\u3057\u3044\u5927\u898f\u6a21\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30e2\u30c7\u30eb(LMM)\u3067\u3042\u308bDocPedia\u3092\u63d0\u6848\u3059\u308b\u3002 \u65e2\u5b58\u306e\u4f5c\u696d\u3067\u306f\u9ad8\u89e3\u50cf\u5ea6\u306e\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8\u3067\u82e6\u52b4\u3057\u305f\u308a\u3001\u5927\u304d\u306a\u8a00\u8a9e\u30e2\u30c7\u30eb\u3092\u6368\u3066\u305f\u308a\u3001\u8996\u899a\u3084\u8a00\u8a9e\u80fd\u529b\u306b\u5236\u7d04\u304c\u3042\u3063\u305f\u308a\u3059\u308b\u306e\u306b\u5bfe\u3057\u3066\u3001DocPedia\u3067\u306f\u3001\u30d4\u30af\u30bb\u30eb\u7a7a\u9593\u3067\u306f\u306a\u304f\u3001\u5468\u6ce2\u6570\u9818\u57df\u306e\u8996\u899a\u5165\u529b\u3092\u76f4\u63a5\u51e6\u7406\u3057\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2311.11810v1\">\u8ad6\u6587<\/a>&nbsp;&nbsp;<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2311.11810v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>&nbsp; &nbsp;(Mon, 20 Nov 2023 14:42:25 GMT)<\/li>\n\n\n\n<li>\u300c&nbsp;DocPedia directly processes visual input in the frequency domain rather than the pixel space.\u300d\u3068\u3044\u3046\u306e\u304c\u7279\u5fb4\u7684\u306a\u6587\u7ae0\u7406\u89e3\u30e2\u30c7\u30eb\u3002DCT \u2192 Frequency Adapter\u3000\u2192 \u2026\u3068\u8208\u5473\u6df1\u3044\u30d6\u30ed\u30c3\u30af\u56f3\u306b\u306a\u3063\u3066\u3044\u308b\u3002\u3002\u3002<\/li>\n\n\n\n<li>LLaVAR\u3084mPLUG-Owl\u306b\u6bd4\u3079\u3066\u6027\u80fd\u306f\u9ad8\u3044\u304csupervised\u306aSOTA\u3068\u306f\u8ddd\u96e2\u304c\u3042\u308b\u3002<\/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":[117,223,524],"class_list":["post-4090","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-document-understanding","tag-llm","tag-524"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4090","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=4090"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4090\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4090"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4090"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4090"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}