{"id":4961,"date":"2024-06-10T04:11:00","date_gmt":"2024-06-09T19:11:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=4961"},"modified":"2024-06-10T04:11:00","modified_gmt":"2024-06-09T19:11:00","slug":"video-mme-the-first-ever-comprehensive-evaluation-benchmark-of-multi-modal-llms-in-video-analysis","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=4961","title":{"rendered":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis\u00a0<\/strong>[118.1]<br>Video-MME\u306f\u3001\u30d3\u30c7\u30aa\u89e3\u6790\u306b\u304a\u3051\u308bMLLM\u306e\u5b8c\u5168\u306a\u30de\u30eb\u30c1\u30e2\u30fc\u30c9\u8a55\u4fa1\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3067\u3042\u308b\u3002 \u6211\u3005\u306f,GPT-4\u30b7\u30ea\u30fc\u30ba\u3084Gemini 1.5 Pro,\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u753b\u50cf\u30e2\u30c7\u30eb\u306a\u3069,\u6700\u5148\u7aef\u306eMLLM\u3092\u5e45\u5e83\u304f\u8a55\u4fa1\u3057\u305f\u3002 \u6211\u3005\u306e\u5b9f\u9a13\u306b\u3088\u308b\u3068\u3001Gemini 1.5 Pro\u306f\u6700\u3082\u512a\u308c\u305f\u5546\u7528\u30e2\u30c7\u30eb\u3067\u3042\u308a\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30e2\u30c7\u30eb\u3088\u308a\u3082\u5927\u5e45\u306b\u512a\u308c\u3066\u3044\u307e\u3059\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2405.21075v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2405.21075v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Fri, 31 May 2024 17:59:47 GMT)<\/li>\n\n\n\n<li>\u30d3\u30c7\u30aa\u89e3\u6790\u3092\u5bfe\u8c61\u3068\u3057\u305f\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u3002900\u500b\u3001256\u6642\u9593\u306e\u52d5\u753b\u306b\u5bfe\u3057\u30662.7K\u306eQA\u3092\u4eba\u304c\u306e\u30c6\u30fc\u30b7\u30e7\u30f3\u3057\u3066\u3044\u308b\u3002\u30c9\u30e1\u30a4\u30f3\u3082\u69d8\u3005\uff08<a href=\"https:\/\/github.com\/BradyFU\/Video-MME?tab=readme-ov-file#-video-mme-overview\">GitHub &#8211; BradyFU\/Video-MME: \u2728\u2728Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis<\/a>\uff09\u3002<\/li>\n\n\n\n<li>\u73fe\u6642\u70b9\u306e\u30d9\u30f3\u30c1\u30de\u30fc\u30af\u7d50\u679c\u306fGemini Pro\u304c\u3082\u3063\u3068\u3082\u3088\u304f\u3001Gemini Flash\u3001GPT-4o\u3001GPT-4V\u304c\u7d9a\u3044\u3066\u3044\u308b\u3002API\u306b\u3088\u3063\u3066\u4f7f\u3048\u308b\u30c7\u30fc\u30bf\u7a2e\u985e\u304c\u7570\u306a\u308b\u306a\u3069\u524d\u63d0\u3092\u5408\u308f\u305b\u308b\u306e\u304c\u96e3\u3057\u3044\u70b9\u306b\u6ce8\u610f\u304c\u5fc5\u8981\u3002\u4f8b\u3048\u3070\u300cSince the video interface of GPT-4o has not been released yet, we sample 10 frames and evaluate the model using multiple images as input.\u300d\u3068\u3044\u3046\u6ce8\u91c8\u304c\u3042\u308b\u3002<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/video-mme.github.io\/\">Video-MME: Welcome<\/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":[251,517],"class_list":["post-4961","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-mllm","tag-517"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4961","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=4961"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/4961\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4961"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4961"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4961"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}