{"id":344,"date":"2025-04-03T00:03:07","date_gmt":"2025-04-02T16:03:07","guid":{"rendered":"http:\/\/106.52.84.14\/?p=344"},"modified":"2025-04-03T00:03:07","modified_gmt":"2025-04-02T16:03:07","slug":"%e4%bb%8e%e8%bf%90%e5%8a%a8%e6%b5%81%e4%b8%ad%e6%95%b4%e5%90%88%e6%97%b6%e5%ba%8f%e5%85%88%e9%aa%8c%e8%bf%9b%e8%a1%8c%e5%be%ae%e5%88%9b%e6%89%8b%e6%9c%af%e5%99%a8%e6%a2%b0%e5%88%86%e5%89%b2","status":"publish","type":"post","link":"https:\/\/www.mics-ai.com\/index.php\/2025\/04\/03\/%e4%bb%8e%e8%bf%90%e5%8a%a8%e6%b5%81%e4%b8%ad%e6%95%b4%e5%90%88%e6%97%b6%e5%ba%8f%e5%85%88%e9%aa%8c%e8%bf%9b%e8%a1%8c%e5%be%ae%e5%88%9b%e6%89%8b%e6%9c%af%e5%99%a8%e6%a2%b0%e5%88%86%e5%89%b2\/","title":{"rendered":"\u4ece\u8fd0\u52a8\u6d41\u4e2d\u6574\u5408\u65f6\u5e8f\u5148\u9a8c\u8fdb\u884c\u5fae\u521b\u624b\u672f\u5668\u68b0\u5206\u5272"},"content":{"rendered":"\n

\u5728\u4e16\u754c\u5fae\u521b\u5916\u79d1\u9886\u57df\uff0c\u673a\u5668\u4eba\u624b\u672f\u7cfb\u7edf\u56e0\u624b\u672f\u521b\u53e3\u5c0f\u3001\u64cd\u4f5c\u7cbe\u786e\u5e73\u7a33\u7b49\u4f18\u70b9\uff0c\u5df2\u65e5\u76ca\u666e\u53ca\u3002\u5728\u673a\u5668\u4eba\u8f85\u52a9\u5fae\u521b\u624b\u672f\u4e2d\uff0c\u5206\u5272\u624b\u672f\u5668\u68b0\u5bf9\u4e8e\u5668\u68b0\u59ff\u6001\u4f30\u8ba1\u3001\u8ffd\u8e2a\u548c\u63a7\u5236\u5177\u6709\u91cd\u8981\u4f5c\u7528\u3002\u7136\u800c\uff0c\u5728\u590d\u6742\u7684\u624b\u672f\u73af\u5883\u4e2d\u5206\u5272\u5668\u68b0\u5374\u4e5f\u662f\u4e00\u4e2a\u68d8\u624b\u7684\u96be\u9898\u3002<\/p>\n\n\n\n

\u4eca\u5929\u4e3a\u5927\u5bb6\u4ecb\u7ecd\u7684\u8bba\u6587\u662f\u7531\u9999\u6e2f\u4e2d\u6587\u5927\u5b66\u548c\u5e1d\u56fd\u7406\u5de5\u5927\u5b66\u8054\u5408\u53d1\u8868\u7684Incorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video [1]\uff0c\u53d1\u8868\u4e8eMICCAI 2019\uff0c\u7b2c\u4e00\u4f5c\u8005\u662f Yueming Jin\u3002<\/strong>\u8fd9\u7bc7\u6587\u7ae0\u63d0\u51fa\u4e86\u65b0\u9896\u7684\u56fe\u50cf\u5206\u5272\u6846\u67b6\u3002\u8be5\u6846\u67b6\u5c06\u9884\u6d4b\u5f97\u5230\u7684\u65f6\u5e8f\u5148\u9a8c\u4fe1\u606f\u6574\u5408\u5230\u6ce8\u610f\u529b\u91d1\u5b57\u5854\u7f51\u7edc\u4e2d\uff0c\u5145\u5206\u5229\u7528\u5668\u68b0\u7684\u8fd0\u52a8\u4fe1\u606f\uff0c\u63d0\u9ad8\u4e86\u56fe\u50cf\u5206\u5272\u7cbe\u5ea6\uff1b\u540c\u65f6\uff0c\u8be5\u6846\u67b6\u6240\u4f7f\u7528\u7684\u65f6\u5e8f\u5148\u9a8c\u4fe1\u606f\uff08temporal prior\uff09\u4e5f\u53ef\u4ee5\u7528\u4e8e\u534a\u76d1\u7763\u5b66\u4e60\u3002\u8be5\u65b9\u6cd5\u57282017 MICCAI EndoVis Robotic Instrument Segmentation Challenge\u6240\u6709\u4efb\u52a1\u4e0a\u7684\u6027\u80fd\u5747\u660e\u663e\u8d85\u8fc7\u4e86\u76ee\u524d\u6700\u597d\u7684\u7ed3\u679c\u3002<\/p>\n\n\n\n

\u4e0b\u9762\u662f\u8fd9\u7bc7\u5de5\u4f5c\u7684\u8be6\u7ec6\u4ecb\u7ecd\uff1a<\/strong><\/p>\n\n\n\n

\u5728\u590d\u6742\u7684\u624b\u672f\u73af\u5883\u4e2d\u51c6\u786e\u5730\u8bc6\u522b\u51fa\u5668\u68b0\u9700\u8981\u66f4\u591a\u7684\u7ec6\u8282\uff0c\u89c6\u9891\u56fe\u50cf\u4e2d\u7684\u65f6\u5e8f\u4fe1\u606f\u80fd\u4e3a\u8bc6\u522b\u4efb\u52a1\u63d0\u4f9b\u6307\u5f15\u3002\u4e3a\u6b64\uff0c\u4f5c\u8005\u63d0\u51fa\u7684\u65b9\u6cd5\u662f\uff1a\u4ece\u89c6\u9891\u56fe\u50cf\u7684\u8fd0\u52a8\u6d41\uff08motion flow\uff09\u4e2d\u5f97\u5230\u5148\u9a8c\u4fe1\u606f\uff0c\u518d\u5c06\u5148\u9a8c\u4fe1\u606f\u6574\u5408\u5230\u6ce8\u610f\u529b\u91d1\u5b57\u5854\u7f51\u7edc\u4e2d\uff08\u79f0\u4e3aMF-TAPNet\uff09\u3002\u5177\u4f53\u6765\u8bf4\uff0c\u9996\u5148\u4f7f\u7528Unflow [2]\u65b9\u6cd5\u8ba1\u7b97\u76f8\u90bb\u7684\u4e24\u5e27\u4e4b\u95f4\u7684\u5149\u6d41\uff08optical flow\uff09\uff0c\u80fd\u8868\u793a\u6bcf\u4e2a\u50cf\u7d20\u79fb\u52a8\u7684\u5e45\u5ea6\u548c\u65b9\u5411\u3002\u4f5c\u8005\u8ba4\u4e3a\uff0c\u5bf9\u5e94\u7684mask\u4e5f\u4f1a\u53d1\u751f\u76f8\u540c\u7684\u4f4d\u79fb\u3002\u57fa\u4e8e\u8fd9\u4e2a\u5047\u8bbe\uff0c\u7ed3\u5408\u5149\u6d41\u548c\u7f51\u7edc\u8f93\u51fa\u7684\u4e0a\u4e00\u5e27\u5206\u5272\u56fe\uff0c\u53bb\u9884\u6d4b\u5f53\u524d\u5e27\u4e2d\u5668\u68b0\u7684\u4f4d\u7f6e\u548c\u5f62\u72b6\u3002\u8fd9\u4e00\u6b65\u9aa4\u79f0\u4e3atime turner\uff0c\u5f97\u5230\u7684\u5f53\u524d\u5e27\u7684\u9884\u6d4b\u56fe\u4e3a\u63a5\u4e0b\u6765\u7684\u5206\u5272\u7f51\u7edc\u63d0\u4f9b\u4e86\u53ef\u9760\u7684\u5148\u9a8c\u4fe1\u606f\uff08temporal prior\uff09\u3002\u7136\u540e\uff0c\u5c06\u5f97\u5230\u7684prior\u52a0\u5165\u5206\u5272\u7f51\u7edc\uff0c\u5373\u65f6\u5e8f\u91d1\u5b57\u5854\u7f51\u7edc\uff08TAPNet\uff09\u7684\u74f6\u9888\u5c42\uff08bottleneck layer\uff09\u4f5c\u4e3a\u521d\u59cb\u7684\u6ce8\u610f\u529b\u56fe\uff08attention map\uff09\u3002\u6b64\u5206\u5272\u7f51\u7edc\u7531\u591a\u5c3a\u5ea6\u7684\u6ce8\u610f\u529b\u6a21\u5757\uff08multi-stage attention guided modules\uff0c\u7f29\u5199\u4e3aAG\uff09\u7ec4\u6210\u3002\u5728\u8fd9\u79cd\u91d1\u5b57\u5854\u7ed3\u6784\u4e2d\u53ef\u4ee5\u9010\u6e10\u5b8c\u5584\u6ce8\u610f\u529b\u56fe\uff0c\u63d0\u5347\u7ec6\u5316\u7279\u5f81\uff0c\u6700\u7ec8\u5f97\u5230\u51c6\u786e\u7684\u5206\u5272\u7ed3\u679c\u3002\u4ee5AG5\u6765\u89e3\u91ca\u6ce8\u610f\u529b\u6a21\u5757\u7684\u5177\u4f53\u64cd\u4f5c\uff08\u56fe1\uff08c\uff09\uff09\uff1a\u9996\u5148\u4f7f\u7528\u8df3\u8dc3\u8fde\u63a5\u6765\u62fc\u63a5\u9ad8\u7ef4\u548c\u4f4e\u7ef4\u7279\u5f81\uff0c\u518d\u75281\u00d71\u5377\u79ef\u6765\u964d\u4f4e\u62fc\u63a5\u7ed3\u679cft<\/sub>5<\/sup>\u7684\u901a\u9053\u6570\u3002pt<\/sub>\u7ecf\u8fc7\u4e0b\u91c7\u6837\u548c1\u00d71\u5377\u79ef\u4e4b\u540e\uff0c\u4e0eft<\/sub>5<\/sup>\u5177\u6709\u540c\u6837\u7684\u7ef4\u5ea6\uff0c\u7136\u540e\u4e8c\u8005\u8fdb\u884celement-wise multiplication\uff0c\u63d0\u53d6prior\u8bc6\u522b\u51fa\u7684\u7279\u5f81\u3002\u8be5\u7ed3\u679c\u518d\u6b21\u4e0eft<\/sub>5<\/sup>\u76f8\u52a0\uff0c\u5e76\u8fdb\u884c3\u00d73\u5377\u79ef\u548csigmoid\u6fc0\u6d3b\uff0c\u4ea7\u751f\u4e0b\u4e00\u4e2aAG\u6a21\u5757\u7684attention map\u3002<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n\n

\u56fe1. (a)MF-TAPNet\u7ed3\u6784\u56fe. (b)\u65f6\u5e8f\u6ce8\u610f\u529b\u91d1\u5b57\u5854\u7f51\u7edc\u7ed3\u6784\u56fe. (c)\u6ce8\u610f\u529b\u6a21\u5757\u7ed3\u6784\u56fe<\/p>\n\n\n\n

\u53e6\u5916\uff0c\u8be5\u6846\u67b6\u8fd8\u53ef\u4ee5\u7528\u4e8e\u8fdb\u884c\u534a\u76d1\u7763\u5b66\u4e60\uff0c\u5904\u7406\u95f4\u9694\u6027\u6807\u6ce8\u7684\u89c6\u9891\u3002\u4f7f\u7528time turner\u53ef\u4ee5\u4f7f\u7b97\u6cd5\u5728\u6807\u6ce8\u8f83\u5c11\u7684\u60c5\u51b5\u4e0b\u8fdb\u884c\u534a\u76d1\u7763\u5b66\u4e60\u3002\u5229\u7528\u5e8f\u5217\u4e00\u81f4\u6027\uff0c\u5c06\u5bf9\u672a\u6807\u6ce8\u5e27\u7684\u9884\u6d4b\u8f6c\u6362\u4e3a\u76f8\u90bb\u7684\u5df2\u6807\u6ce8\u5e27\u7684\u9884\u6d4b\uff0c\u8fd9\u6837\u5c31\u53ef\u4ee5\u8ba1\u7b97\u8be5\u9884\u6d4b\u4e0e\u5df2\u6807\u6ce8\u5e27\u7684mask\u4e4b\u95f4\u7684loss\u3002\u5f53\u524d\u4e00\u5e27\u5177\u6709\u6807\u6ce8\u800c\u5f53\u524d\u5e27\u6ca1\u6709\u65f6\uff0c\u7b80\u5355\u5730\u6cbf\u65f6\u5e8f\u7684\u53cd\u65b9\u5411\u6267\u884ctime turner\u5373\u53ef\u5b9e\u73b0\u534a\u76d1\u7763\u5b66\u4e60\u3002<\/p>\n\n\n\n

\u88681\u7ed9\u51fa\u4e86\u5728\u4e09\u4e2a\u4efb\u52a1\u4e0a\u4e0d\u540c\u6846\u67b6\u8fdb\u884c\u56db\u6298\u4ea4\u53c9\u9a8c\u8bc1\u7684\u5206\u5272\u7ed3\u679c\uff0c\u53ef\u4ee5\u770b\u5230\uff0cTAPNet\u7684\u6027\u80fd\u6bd4\u8d77\u4e4b\u524d\u7684\u5de5\u4f5c\u5df2\u7ecf\u6709\u6240\u63d0\u5347\uff0c\u800c\u7ed3\u5408TAPNet\u548cmotion flow\u4e4b\u540e\u7ed3\u679c\u4ecd\u7136\u80fd\u591f\u7ee7\u7eed\u63d0\u5347\u3002\u5bf9\u4e8e\u591a\u7c7b\u5206\u5272\u4efb\u52a1\uff0c\u91c7\u7528\u52a0\u6743\u7684\u4ea4\u53c9\u71b5loss\u3002\u8bc4\u4ef7\u6307\u6807\u4e3a\u4e24\u5f20mask\u4e4b\u95f4\u7684\u4ea4\u5e76\u6bd4\u548cdice\u7cfb\u6570\u3002\u56fe2\u4e3a\u4e09\u79cd\u5206\u5272\u7f51\u7edc\u7684\u7ed3\u679c\u5bf9\u6bd4\u3002\u4ece\u4e0a\u5230\u4e0b\uff0c\u5bf9\u6bcf\u4e2a\u4efb\u52a1\u90fd\u9009\u4e86\u8fde\u7eed\u7684\u4e24\u5e27\u4ee5\u53ca\u5b83\u4eec\u5bf9\u5e94\u7684mask\uff0c\u56fe\u4e2d\u7b2c\u4e8c\u884c\u662f\u56fe\u7247\u5bf9\u5e94\u7684ground truth\uff0c\u7b2c\u4e09\u884c\u81f3\u7b2c\u4e94\u884c\u5206\u522b\u662fPlainUNet\u3001TAPNet\u548cMF-TAPNet\u7684\u5206\u5272\u7ed3\u679c\u3002\u5176\u4e2d\uff0cMF-TAPNet\u5bf9\u50cf\u7d20\u7c7b\u522b\u7684\u5224\u65ad\u6700\u4e3a\u51c6\u786e\u3002<\/p>\n\n\n\n

\u88681. \u5206\u5272\u7ed3\u679c\u5bf9\u6bd4\uff08mean\u00b1std\uff09<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n
\n
\"\"<\/figure>\n<\/div>\n\n\n

\u56fe2. \u5178\u578b\u5206\u5272\u7ed3\u679c(a)\u4e8c\u503c\u5206\u5272(\u5206\u5272\u5668\u68b0\u548c\u80cc\u666f\u7ec4\u7ec7).(b)\u5668\u68b0\u7ed3\u6784\u5206\u5272(\u6746\u3001\u8155\u90e8\u3001\u94b3\u53e3).(c)\u7c7b\u578b\u5206\u5272(\u5916\u89c2\u76f8\u4f3c\u7684\u4e0d\u540c\u4eea\u5668)<\/p>\n\n\n\n

\u5bf9\u8fd9\u7bc7\u8bba\u6587\u7684\u603b\u7ed3:<\/strong><\/p>\n\n\n\n

\u5728\u624b\u672f\u5668\u68b0\u5206\u5272\u4efb\u52a1\u4e2d\uff0c\u5373\u4f7f\u62e5\u6709\u89c6\u9891\u6570\u636e\uff0c\u5f88\u591a\u7684\u5de5\u4f5c\u4e5f\u8fd8\u662f\u53ea\u505c\u7559\u5728\u4e8c\u7ef4\u56fe\u50cf\u7684\u5904\u7406\u4e0a\u3002\u800c\u624b\u672f\u573a\u666f\u6bd4\u8f83\u590d\u6742\uff0c\u53c8\u4e3a\u624b\u672f\u5668\u68b0\u7684\u5206\u5272\u589e\u52a0\u96be\u5ea6\uff1b\u6b64\u5916\uff0c\u83b7\u5f97\u4eba\u5de5\u6807\u6ce8\u4e5f\u662f\u4e00\u4ef6\u8d39\u65f6\u8d39\u529b\u7684\u4e8b\u60c5\u3002\u5982\u4f55\u540c\u65f6\u5173\u6ce8\u5230\u6807\u6ce8\u7684\u5229\u7528\u6548\u7387\u548c\u5206\u5272\u7cbe\u5ea6\u5e94\u8be5\u662f\u672a\u6765\u5de5\u4f5c\u4e2d\u7684\u4e00\u4e2a\u5173\u6ce8\u70b9\u3002\u8fd9\u7bc7\u6587\u7ae0\u5728\u91d1\u5b57\u5854\u7ed3\u6784\u7684\u57fa\u7840\u4e0a\u6574\u5408\u4e86\u65f6\u5e8f\u4fe1\u606f\uff0c\u6240\u4f7f\u7528\u7684\u65f6\u5e8f\u5148\u9a8c\u5728\u534a\u76d1\u7763\u5b66\u4e60\u4e2d\u53ea\u9700\u8981\u8fdb\u884c\u53cd\u5411\u64cd\u4f5c\u3002\u5b9e\u9a8c\u7ed3\u679c\u8868\u660e\uff0c\u8be5\u65b9\u6cd5\u4e0d\u4ec5\u5728\u5206\u5272\u7ed3\u679c\u4e0a\u6765\u5e26\u4e86\u660e\u663e\u63d0\u5347\uff0c\u5728\u4e34\u5e8a\u7814\u7a76\u4e2d\u63d0\u5347\u6807\u6ce8\u7684\u4f7f\u7528\u6548\u7387\u4e0a\u4e5f\u5177\u6709\u5f88\u5927\u6f5c\u529b\u3002<\/p>\n\n\n\n

\u4ee5\u4e0a\u5c31\u662f\u672c\u6b21\u4e0e\u5927\u5bb6\u5206\u4eab\u7684\u7ed3\u5408\u65f6\u5e8f\u4fe1\u606f\u8fdb\u884c\u6df1\u5ea6\u5b66\u4e60\u56fe\u50cf\u5206\u5272\u7684\u6587\u7ae0\uff0c\u7b14\u8005\u6c34\u5e73\u6709\u9650\uff0c\u6587\u4e2d\u4e0d\u5f53\u4e4b\u5904\u6b22\u8fce\u6307\u6b63\uff0c\u518d\u4f1a\uff01<\/p>\n\n\n\n

\u53c2\u8003\u6587\u732e<\/p>\n\n\n\n

[1] Y. Jin, K. Cheng, Q. Dou, P. Heng, \u201cIncorporating Temporal Prior from Motion Flow for Instrument Segmentation in Minimally Invasive Surgery Video,\u201d 2019.<\/p>\n\n\n\n

[2] S. Meister, J. Hur, S. Roth, \u201cUnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss,\u201d 2018.<\/p>\n\n\n\n

\u672c\u6587\u4f5c\u8005\uff1a\u5f20\u5b87\u5a55   <\/p>\n\n\n\n

\u6307\u5bfc\u8001\u5e08\uff1a\u738b\u8fde\u751f   <\/p>\n\n\n\n

\u5355      \u4f4d\uff1a\u53a6\u95e8\u5927\u5b66<\/p>\n\n\n\n

\n\n\n\n

\u533b\u5b66\u56fe\u50cf\u8ba1\u7b97\u9752\u5e74\u7814\u8ba8\u4f1a\uff08Medical Imaging Computing Seminar\uff0cMICS\uff09\u521b\u7acb\u4e8e2014\u5e74\uff0c\u5176\u5b97\u65e8\u662f\u4e3a\u533b\u5b66\u56fe\u50cf\u9886\u57df\u7684\u534e\u4eba\u9752\u5e74\u5b66\u8005\u63d0\u4f9b\u5b66\u672f\u4ea4\u6d41\u5e73\u53f0\uff0c\u589e\u8fdb\u76f8\u4e92\u4e4b\u95f4\u7684\u4e86\u89e3\u548c\u53cb\u8c0a\uff0c\u5e2e\u52a9\u9752\u5e74\u5b66\u8005\u878d\u5165\u5b66\u672f\u7814\u7a76\u5927\u5bb6\u5ead\u3002MICS\u805a\u7126\u4e8e\u8fd1\u4e24\u5e74\u5185\u7684\u533b\u5b66\u56fe\u50cf\u8ba1\u7b97\u9886\u57df\u539f\u521b\u7814\u7a76\uff0c\u6b22\u8fce\u533b\u5b66\u56fe\u50cf\u5904\u7406\u3001\u8ba1\u7b97\u673a\u89c6\u89c9\u3001\u4eba\u5de5\u667a\u80fd\u7b49\u65b0\u7406\u8bba\u3001\u65b0\u65b9\u6cd5\u3001\u65b0\u5e94\u7528\u7684\u5c55\u793a\uff0c\u4ee5\u53ca\u5f71\u50cf\u4e0e\u4e34\u5e8a\u533b\u5b66\u3001\u57fa\u7840\u533b\u5b66\u6df1\u5ea6\u4ea4\u53c9\u7684\u7a81\u7834\u6027\u8fdb\u5c55\u62a5\u544a\u3002\u9996\u5c4aMICS\u5728\u533b\u5b66\u56fe\u50cf\u9886\u57df\u8457\u540d\u5b66\u8005\u3001\u5317\u5361\u7f57\u6765\u7eb3\u5927\u5b66\u6559\u5802\u5c71\u5206\u6821\u6c88\u5b9a\u521a\u6559\u6388\u7684\u5021\u8bae\u4e0b\uff0c\u4e8e2014\u5e7412\u6708\u5728\u6df1\u5733\u5927\u5b66\u4e3e\u884c\u3002\u7ecf\u8fc72015\uff08\u6d4e\u5357\uff09\u30012016\uff08\u5e7f\u5dde\uff09\u30012017\uff08\u4e0a\u6d77\uff09\u30012018\uff08\u5357\u4eac\uff09\u30012019\uff08\u82cf\u5dde\uff09\u7684\u84ec\u52c3\u53d1\u5c55\uff0cMICS\u4ece\u53c2\u4f1a\u4eba\u6570\u4e0d\u8db3\u767e\u4eba\u5230\u5438\u5f15\u4e0a\u5343\u540d\u4e13\u5bb6\u5b66\u8005\u53c2\u4e0e\uff0c\u5df2\u8fc5\u901f\u6210\u4e3a\u5168\u56fd\u533b\u5b66\u56fe\u50cf\u8ba1\u7b97\u9886\u57df\u6700\u5177\u5f71\u54cd\u529b\u7684\u6d3b\u52a8\u4e4b\u4e00\u30022020\u5e74\u7684MICS\u4f1a\u8bae\u5c06\u4e8e7\u670818~19\u65e5\u5728\u5927\u8fde\u4e3e\u529e\uff0c\u6b22\u8fce\u5168\u7403\u540c\u9053\u4e13\u5bb6\u548c\u540c\u5b66\u5171\u805a\u5b66\u672f\u76db\u5bb4\uff01<\/p>\n\n\n

\n
\"\"<\/figure>\n<\/div>\n\n\n

\u201c\u533b\u5b66\u56fe\u50cf\u8ba1\u7b97\u9752\u5e74\u7814\u8ba8\u4f1a\u201d\u5fae\u4fe1\u516c\u4f17\u53f7<\/p>\n","protected":false},"excerpt":{"rendered":"

\u5728\u4e16\u754c\u5fae\u521b\u5916\u79d1\u9886\u57df\uff0c\u673a\u5668\u4eba\u624b\u672f\u7cfb\u7edf\u56e0\u624b\u672f…<\/p>\n","protected":false},"author":1,"featured_media":345,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-344","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-7"],"_links":{"self":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts\/344","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/comments?post=344"}],"version-history":[{"count":0,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/posts\/344\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/media\/345"}],"wp:attachment":[{"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/media?parent=344"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/categories?post=344"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.mics-ai.com\/index.php\/wp-json\/wp\/v2\/tags?post=344"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}