{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T13:54:28Z","timestamp":1762091668871,"version":"build-2065373602"},"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":[[2023,8]]},"abstract":"<jats:p>Recent advances in interactive segmentation (IS)\n\nallow speeding up and simplifying image editing\n\nand labeling greatly. The majority of modern IS\n\napproaches accept user input in the form of clicks.\n\nHowever, using clicks may require too many user\n\ninteractions, especially when selecting small ob-\n\njects, minor parts of an object, or a group of ob-\n\njects of the same type. In this paper, we consider\n\nsuch a natural form of user interaction as a loose\n\ncontour, and introduce a contour-based IS method.\n\nWe evaluate the proposed method on the standard\n\nsegmentation benchmarks, our novel UserContours\n\ndataset, and its subset UserContours-G containing\n\ndifficult segmentation cases. Through experiments,\n\nwe demonstrate that a single contour provides the\n\nsame accuracy as multiple clicks, thus reducing the\n\nrequired amount of user interactions.<\/jats:p>","DOI":"10.24963\/ijcai.2023\/147","type":"proceedings-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:31:30Z","timestamp":1691742690000},"page":"1322-1330","source":"Crossref","is-referenced-by-count":3,"title":["Contour-based Interactive Segmentation"],"prefix":"10.24963","author":[{"given":"Polina","family":"Popenova","sequence":"first","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danil","family":"Galeev","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Vorontsova","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anton","family":"Konushin","sequence":"additional","affiliation":[{"name":"Samsung Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"32","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2023","name":"Thirty-Second International Joint Conference on Artificial Intelligence {IJCAI-23}","start":{"date-parts":[[2023,8,19]]},"theme":"Artificial Intelligence","location":"Macau, SAR China","end":{"date-parts":[[2023,8,25]]}},"container-title":["Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T08:37:41Z","timestamp":1691743061000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2023\/147"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2023\/147","relation":{},"subject":[],"published":{"date-parts":[[2023,8]]}}}