
{"id":8973,"date":"2026-06-10T01:06:22","date_gmt":"2026-06-09T17:06:22","guid":{"rendered":"https:\/\/infernews.com\/blog\/evaluation-code-covebench-dual-level-metrics\/"},"modified":"2026-06-10T01:09:45","modified_gmt":"2026-06-09T17:09:45","slug":"evaluation-code-covebench-dual-level-metrics","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/evaluation-code-covebench-dual-level-metrics\/","title":{"rendered":"CoVEBench \u6aa2\u67e5\u5f71\u7247\u7de8\u8f2f\u6a21\u578b\u7684\u771f\u529f\u592b"},"content":{"rendered":"\n<figure class=\"wp-block-image size-full\"><img data-dominant-color=\"c2c5c2\" data-has-transparency=\"false\" style=\"--dominant-color: #c2c5c2;\" loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"558\" src=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/06\/image-2.png\" alt=\"\" class=\"wp-image-8977 not-transparent\" srcset=\"https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/06\/image-2.png 1024w, https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/06\/image-2-300x163.png 300w, https:\/\/infernews.com\/blog\/wp-content\/uploads\/2026\/06\/image-2-768x419.png 768w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8fd1\u5e74\u4e0d\u5c11\u5f71\u7247\u7de8\u8f2f\u6a21\u578b\u5df2\u80fd\u6839\u64da\u6587\u5b57\u6539\u7247\uff0c\u4f46\u4e00\u9047\u5230\u591a\u500b\u8981\u6c42\u540c\u6642\u51fa\u73fe\uff0c\u4f8b\u5982\u4e00\u908a\u6539\u4e3b\u9ad4\u3001\u4e00\u908a\u4fdd\u7559\u80cc\u666f\u8207\u52d5\u4f5c\u9023\u8cab\uff0c\u8868\u73fe\u5c31\u5bb9\u6613\u5931\u6e96\u3002CoVEBench \u662f\u4e00\u500b\u8a3a\u65b7\u578b benchmark\uff0c\u5c08\u9580\u6aa2\u67e5 compositional instruction-guided video editing \u5728\u8907\u96dc\u689d\u4ef6\u4e0b\u662f\u5426\u771f\u7684\u505a\u5f97\u5230\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u9019\u9805\u76ee\u7684\u5224\u65b7\u65b9\u6cd5\u6bd4\u4e00\u822c\u300c\u6574\u9ad4\u770b\u8d77\u4f86\u5dee\u4e0d\u591a\u300d\u66f4\u56b4\u683c\u3002\u5b83\u628a\u8868\u73fe\u5206\u6210\u6307\u4ee4\u5b8c\u6210\u5ea6\u3001\u756b\u8cea\u8207\u4f86\u6e90\u4fdd\u771f\u5ea6\u4e09\u689d\u7dda\u4f86\u770b\uff0c\u4e26\u7528\u7d30\u7dfb checklist \u6aa2\u67e5\u591a\u500b\u7de8\u8f2f\u9ede\u6709\u6c92\u6709\u540c\u6642\u6210\u7acb\uff1b\u5c31\u7b97\u6a21\u578b\u500b\u5225\u8981\u6c42\u505a\u5230\u5e7e\u9805\uff0c\u53ea\u8981\u7121\u6cd5\u901a\u904e union criterion\uff0c\u5206\u6578\u4ecd\u7136\u4e0d\u9ad8\uff0c\u9019\u7a2e\u8a2d\u8a08\u80fd\u66f4\u65e9\u770b\u51fa\u6a21\u578b\u77ed\u677f\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u5982\u679c\u60f3\u4e86\u89e3\u5b83\u7684\u5167\u5bb9\uff0c\u8f03\u5408\u9069\u7684\u505a\u6cd5\u662f\u5148\u770b\u793a\u7bc4\u9801\u8207\u8cc7\u6599\u96c6\u898f\u6a21\uff0c\u518d\u5c0d\u7167\u8a55\u4f30\u6307\u6a19\u3002CoVEBench \u6536\u9304 416 \u6bb5\u4f86\u6e90\u5f71\u7247\u3001626 \u689d\u591a\u91cd\u6307\u4ee4\u30019,990 \u500b\u7d30\u9805\u6aa2\u67e5\u9ede\uff0c\u9810\u8a2d\u6703\u62bd\u53d6 10 \u5f35\u7b49\u8ddd frame \u505a frame-level metrics\uff1bAES\u3001VQR\u3001MSM \u5247\u53ea\u91dd\u5c0d edited videos \u8a08\u7b97\uff0c\u65b9\u4fbf\u628a\u300c\u6539\u5f97\u5920\u4e0d\u5920\u300d\u8207\u300c\u6709\u6c92\u6709\u6539\u58de\u5176\u4ed6\u5730\u65b9\u300d\u5206\u958b\u5206\u6790\u3002<\/p>\n\n\n<div\n    \tclass=\"align wp-block-vpb-video\"    id='vpbpVideoPlayer-1'\n    data-attributes='{&quot;source&quot;:&quot;https:\\\/\\\/nju-link.github.io\\\/CoVEBench\\\/assets\\\/videos\\\/demo.mp4&quot;,&quot;repeat&quot;:true,&quot;autoplay&quot;:true,&quot;muted&quot;:true,&quot;align&quot;:&quot;&quot;,&quot;poster&quot;:&quot;&quot;,&quot;controls&quot;:{&quot;play-large&quot;:true,&quot;restart&quot;:false,&quot;rewind&quot;:true,&quot;play&quot;:true,&quot;fast-forward&quot;:true,&quot;progress&quot;:true,&quot;current-time&quot;:true,&quot;duration&quot;:false,&quot;mute&quot;:true,&quot;volume&quot;:true,&quot;pip&quot;:false,&quot;airplay&quot;:false,&quot;settings&quot;:true,&quot;download&quot;:false,&quot;fullscreen&quot;:true},&quot;width&quot;:&quot;100%&quot;,&quot;radius&quot;:&quot;0px&quot;,&quot;resetOnEnd&quot;:false,&quot;autoHideControl&quot;:true,&quot;isSetup&quot;:false}'\n><\/div>\n\n\n<ul class=\"wp-block-list\">\n<li>\u6838\u5fc3\u7528\u9014\u662f\u8a55\u6e2c video editing models\uff0c\u4e0d\u662f\u76f4\u63a5\u62ff\u4f86\u526a\u7247<\/li>\n\n\n\n<li>\u4e3b\u8981\u6307\u6a19\u5305\u62ec Union Accuracy\uff08UAS\uff09\u3001Instruction Following Score\uff08IFS\uff09\u3001Video Realism Score\uff08VRS\uff09\u3001Semantic Consistency\uff08SEM\uff09<\/li>\n\n\n\n<li>\u8a2d\u8a08\u91cd\u9ede\u5728\u7d30\u7c92\u5ea6 checklist\uff0c\u800c\u975e\u53ea\u770b\u55ae\u4e00\u7e3d\u5206<\/li>\n\n\n\n<li>\u7d50\u679c\u986f\u793a\u5f37\u6a21\u578b\u672a\u5fc5\u517c\u9867\u4fdd\u7559\u539f\u7247\u5167\u5bb9\uff0c\u7de8\u8f2f\u529b\u5ea6\u8207\u4fdd\u771f\u5ea6\u5b58\u5728\u62c9\u626f<\/li>\n\n\n\n<li>\u9805\u76ee\u4ea6\u6bd4\u8f03\u4e86 joint editing \u8207 stepwise decomposition \u7684\u5dee\u7570\uff0c\u524d\u8005\u8868\u73fe\u66f4\u597d<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u5f9e\u516c\u958b\u8cc7\u8a0a\u770b\uff0cCoVEBench \u7684\u50f9\u503c\u5728\u65bc\u5b83\u628a\u5931\u6557\u539f\u56e0\u62c6\u5f97\u5920\u6e05\u695a\uff0c\u9069\u5408\u7814\u7a76\u5718\u968a\u3001\u8a55\u6e2c\u4eba\u54e1\uff0c\u4ee5\u53ca\u60f3\u6bd4\u8f03\u9589\u6e90\u8207\u958b\u6e90\u65b9\u6848\u7684\u4eba\u53c3\u8003\u3002\u76f8\u95dc\u6a21\u578b\u5305\u62ec Wan2.7 \u8207 HappyHorse1.0\uff1b\u5373\u4f7f\u9818\u5148\u7cfb\u7d71\u5728\u8907\u5408\u7de8\u8f2f\u4e0a\u8f03\u5f37\uff0cUAS \u4ecd\u672a\u7b97\u9ad8\uff0c\u53cd\u6620\u9019\u500b\u9818\u57df\u96e2\u7a69\u5b9a\u53ef\u9760\u9084\u6709\u4e00\u6bb5\u8ddd\u96e2\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>GitHub\uff1a<\/strong> <a href=\"https:\/\/github.com\/NJU-LINK\/CoVEBench\" rel=\"noopener noreferrer\">https:\/\/github.com\/NJU-LINK\/CoVEBench<\/a><\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u9805\u76ee\uff1a<\/strong> <a href=\"https:\/\/nju-link.github.io\/CoVEBench\/\" rel=\"noopener noreferrer\">https:\/\/nju-link.github.io\/CoVEBench\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u9019\u662f\u7528\u4f86\u9a57\u8b49\u5f71\u7247\u7de8\u8f2f\u6a21\u578b\u8868\u73fe\u7684\u57fa\u6e96\u9805\u76ee\u3002\u5b83\u7279\u5225\u64c5\u9577\u63ed\u51fa\u8907\u5408\u6307\u4ee4\u4e0b\u5e38\u88ab\u5ffd\u7565\u7684\u5931\u8aa4\u3002<\/p>\n","protected":false},"author":8,"featured_media":8972,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ai_generated_summary":"","footnotes":""},"categories":[133,120,197],"tags":[],"class_list":["post-8973","post","type-post","status-publish","format-standard","hentry","category-133","category-120","category-framework"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/8973","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=8973"}],"version-history":[{"count":2,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/8973\/revisions"}],"predecessor-version":[{"id":8978,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/8973\/revisions\/8978"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media\/8972"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=8973"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=8973"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=8973"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}