乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:34:49Z","timestamp":1730237689531,"version":"3.28.0"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.00071","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"699-710","source":"Crossref","is-referenced-by-count":3,"title":["Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only"],"prefix":"10.1109","author":[{"given":"Jun","family":"Chen","sequence":"first","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}]},{"given":"Deyao","family":"Zhu","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}]},{"given":"Guocheng","family":"Qian","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}]},{"given":"Bernard","family":"Ghanem","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}]},{"given":"Zhicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meta AI Research"}]},{"given":"Chenchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"Meta AI Research"}]},{"given":"Fanyi","family":"Xiao","sequence":"additional","affiliation":[{"name":"Meta AI Research"}]},{"given":"Sean Chang","family":"Culatana","sequence":"additional","affiliation":[{"name":"Meta AI Research"}]},{"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[{"name":"King Abdullah University of Science and Technology (KAUST)"}]}],"member":"263","reference":[{"article-title":"Flamingo: a visual language model for few-shot learning","volume-title":"Advances in Neural Information Processing Systems","author":"Alayrac","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00940"},{"article-title":"BEit: BERT pre-training of image transformers","volume-title":"International Conference on Learning Representations","author":"Bao","key":"ref3"},{"article-title":"On the opportunities and risks of foundation models","year":"2021","author":"Bommasani","key":"ref4"},{"key":"ref5","article-title":"Zero-shot semantic segmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Bucher"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"article-title":"Efficient self-supervised vision pretraining with local masked reconstruction","year":"2022","author":"Chen","key":"ref9"},{"article-title":"Rethinking atrous convolution for semantic image segmentation","year":"2017","author":"Chen","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref12","first-page":"17864","article-title":"Perpixel classification is not all you need for semantic segmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Cheng"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Few-shot semantic segmentation with prototype learning","volume-title":"BMVC","volume":"3","author":"Dong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01058"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref23","first-page":"21713","article-title":"Uncertainty-aware learning for zero-shot semantic segmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Hu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","year":"2023","author":"Li","key":"ref26"},{"key":"ref27","first-page":"10317","article-title":"Consistent structural relation learning for zero-shot segmentation","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Li"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00688"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00862"},{"article-title":"Segclip: Patch aggregation with learnable centers for open-vocabulary semantic segmentation","year":"2022","author":"Luo","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00071"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298780"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"ref43","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref44","article-title":"Attention is all you need","volume-title":"Advances in neural information processing systems","volume":"30","author":"Vaswani"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00845"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_42"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00860"},{"article-title":"Florence: A new foundation model for computer vision","year":"2021","author":"Yuan","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.221"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_40"},{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref58"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","start":{"date-parts":[[2023,10,1]]},"location":"Paris, France","end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378186.pdf?arnumber=10378186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:59:41Z","timestamp":1705543181000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.00071","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}