{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:34:29Z","timestamp":1730266469563,"version":"3.28.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650534","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["FASN: Feature Aggregate Side-Network for Open-Vocabulary Semantic Segmentation"],"prefix":"10.1109","author":[{"given":"Daixi","family":"Jia","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Software, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lipeng","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Software, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingzhe","family":"Su","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Software, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengge","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Software, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsuo","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences,Institute of Software, Chinese Academy of Sciences,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","year":"2021","author":"Jia","key":"ref5"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"CLIP brings better features to visual aesthetics learners","year":"2023","author":"Xu","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00936"},{"key":"ref13","first-page":"8291","article-title":"Vision gnn: An image is worth graph of nodes","volume":"35","author":"Han","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8076-5_32"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref16"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"ref22","article-title":"Zero-shot semantic segmentation","volume":"32","author":"Bucher","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"article-title":"Clip surgery for better explainability with enhancement in open-vocabulary tasks","year":"2023","author":"Li","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1883"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"issue":"1-45","key":"ref30","first-page":"5","article-title":"The pascal visual object classes challenge 2012 (voc2012) development kit","volume":"2007","author":"Everingham","year":"2012","journal-title":"Pattern Anal. Stat. Model. Comput. Learn., Tech. Rep"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_16"},{"key":"ref35","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume":"34","author":"Cheng","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"article-title":"Open-vocabulary object detection via vision and language knowledge distillation","year":"2021","author":"Gu","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25925"},{"article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","year":"2021","author":"Zhang","key":"ref40"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref41"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650534.pdf?arnumber=10650534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:27:08Z","timestamp":1725946028000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650534","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}