{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:27:12Z","timestamp":1772908032688,"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":[[2021,8]]},"abstract":"<jats:p>Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussian kernel sizes. In this paper, we propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. First, crowd counting is formulated as a measure matching problem. Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching. Third, we propose a self-supervised mechanism by devising a Sinkhorn scale consistency loss to resist scale changes. Finally, an efficient optimization method is provided to minimize the overall loss function. Extensive experiments on four challenging crowd counting datasets namely ShanghaiTech, UCF-QNRF, JHU++ and NWPU have validated the proposed method.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/116","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"837-844","source":"Crossref","is-referenced-by-count":39,"title":["Direct Measure Matching for Crowd Counting"],"prefix":"10.24963","author":[{"given":"Hui","family":"Lin","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Xi'an Jiaotong University"}]},{"given":"Xiaopeng","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Xi'an Jiaotong University\uff1b"},{"name":"Pengcheng Laboratory, Shenzhen"}]},{"given":"Zhiheng","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Xi'an Jiaotong University"}]},{"given":"Xing","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University"}]},{"given":"Yunfeng","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Pengcheng Laboratory, Shenzhen"}]},{"given":"Yihong","family":"Gong","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University"}]}],"member":"10584","event":{"name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","theme":"Artificial Intelligence","location":"Montreal, Canada","acronym":"IJCAI-2021","number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"start":{"date-parts":[[2021,8,19]]},"end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:01:27Z","timestamp":1628679687000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/116"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/116","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}