{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,2]],"date-time":"2022-04-02T17:43:39Z","timestamp":1648921419788},"reference-count":0,"publisher":"IOS Press","license":[{"start":{"date-parts":[[2021,12,22]],"date-time":"2021-12-22T00:00:00Z","timestamp":1640131200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,22]]},"abstract":"<jats:p>Recently developed methods such as DETR [1] apply Transformer [2] structure to target detection. The performance of using Transformers for target detection (DETR) is similar to that of two-stage target detector. First of all, this paper attempts to apply Transformer to computer room personnel detection. The contributions of the improved DETR include: 1) in order to improve the poor performance of small target detection. Embed Depthwise Convolution in the encoder. When the coding feature is reconstructed, the channel information is retained. 2) in order to solve the problem of slow convergence in DETR training. This paper improves the cross-attention in DECODE and adds the spatial query module. It can accelerate the convergence of DETR. The convergence speed of the improved method is six times faster than that of the original DETR, and the mAP0.5 is improved by 3.1%.<\/jats:p>","DOI":"10.3233\/faia210461","type":"book-chapter","created":{"date-parts":[[2021,12,29]],"date-time":"2021-12-29T10:43:33Z","timestamp":1640774613000},"source":"Crossref","is-referenced-by-count":0,"title":["Detection Method of Computer Room Personnel Based on Improved DERT"],"prefix":"10.3233","author":[{"given":"Dan","family":"Su","sequence":"first","affiliation":[{"name":"State Grid Jibei Information and Telecommunication Company, Beijing 100053, China"}]},{"given":"Qiong-lan","family":"Na","sequence":"additional","affiliation":[{"name":"State Grid Jibei Information and Telecommunication Company, Beijing 100053, China"}]},{"given":"Hui-min","family":"He","sequence":"additional","affiliation":[{"name":"State Grid Jibei Information and Telecommunication Company, Beijing 100053, China"}]},{"given":"Yi-xi","family":"Yang","sequence":"additional","affiliation":[{"name":"State Grid Information and Telecommunication Branch, Beijing 100761, China"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Proceedings of CECNet 2021"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA210461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,29]],"date-time":"2021-12-29T10:43:34Z","timestamp":1640774614000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA210461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,22]]},"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia210461","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,22]]}}}