{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:12:26Z","timestamp":1762341146550},"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":[[2018,7]]},"abstract":"<jats:p>In natural images, the scales (thickness) of object skeletons may\n\ndramatically vary among objects and object parts.\n\nThus, robust skeleton detection requires powerful multi-scale feature integration ability.\n\nTo address this issue, we present a new convolutional neural network (CNN) architecture\n\nby introducing a novel hierarchical feature integration mechanism,\n\nnamed Hi-Fi, to address the object skeleton detection problem.\n\nThe proposed CNN-based approach intrinsically captures high-level semantics from deeper layers,\n\nas well as low-level details from shallower layers.\n\nBy hierarchically integrating different CNN feature levels with bidirectional guidance,\n\nour approach (1) enables mutual refinement across features of different levels,\n\nand (2) possesses the strong ability to capture both rich object context\n\nand high-resolution details.\n\nExperimental results show that our method\n\nsignificantly outperforms the state-of-the-art methods\n\nin terms of effectively fusing features from very different scales,\n\nas evidenced by a considerable performance improvement on several benchmarks.<\/jats:p>","DOI":"10.24963\/ijcai.2018\/166","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"1191-1197","source":"Crossref","is-referenced-by-count":40,"title":["Hi-Fi: Hierarchical Feature Integration for Skeleton Detection"],"prefix":"10.24963","author":[{"given":"Kai","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer and Control Engineering, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shanghua","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dandan","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Specialty Fiber Optics and Optical Access Networks, Shanghai University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Computer and Control Engineering, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2018","name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","start":{"date-parts":[[2018,7,13]]},"theme":"Artificial Intelligence","location":"Stockholm, Sweden","end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:50:29Z","timestamp":1530755429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/166"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/166","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}