{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T22:56:29Z","timestamp":1774911389304,"version":"3.50.1"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,8]]},"abstract":"<jats:p>Pedestrian attribute recognition has received\nincreasing attention due to its important role\nin video surveillance applications. However,\nmost existing methods are designed for a fixed\nset of attributes. They are unable to handle\nthe incremental few-shot learning scenario, i.e.\nadapting a well-trained model to newly added\nattributes with scarce data, which commonly\nexists in the real world. In this work, we\npresent a meta learning based method to address\nthis issue. The core of our framework\nis a meta architecture capable of disentangling\nmultiple attribute information and generalizing\nrapidly to new coming attributes. By conducting\nextensive experiments on the benchmark\ndataset PETA and RAP under the incremental\nfew-shot setting, we show that our method is\nable to perform the task with competitive performances\nand low resource requirements.<\/jats:p>","DOI":"10.24963\/ijcai.2019\/543","type":"proceedings-article","created":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:46:05Z","timestamp":1564299965000},"page":"3912-3918","source":"Crossref","is-referenced-by-count":20,"title":["Incremental Few-Shot Learning for Pedestrian Attribute Recognition"],"prefix":"10.24963","author":[{"given":"Liuyu","family":"Xiang","sequence":"first","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Jin","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[{"name":"WMG Data Science, University of Warwick, CV4 7AL Coventry, United"},{"name":"Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leida","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Xidian University, Xi'an 710071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"name":"Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}","theme":"Artificial Intelligence","location":"Macao, China","acronym":"IJCAI-2019","number":"28","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2019,8,10]]},"end":{"date-parts":[[2019,8,16]]}},"container-title":["Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2019,7,28]],"date-time":"2019-07-28T07:50:01Z","timestamp":1564300201000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2019\/543"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2019\/543","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}