{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:17:14Z","timestamp":1761808634690,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985487"},{"type":"electronic","value":"9789819985494"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8549-4_27","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"323-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CLIP for\u00a0Lightweight Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Ke","family":"Jin","sequence":"first","affiliation":[]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"27_CR1","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Rao, Y., et al.: DenseCLIP: language-guided dense prediction with context-aware prompting. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18061\u201318070 (2021)","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"27_CR3","unstructured":"Li, B., et al.: Language-driven semantic segmentation. ArXiv arxiv:2201.03546 (2022)"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9992\u201310002 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Sandler, M., et al.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"27_CR6","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2016","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vision 127, 302\u2013321 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging MobileNet and transformer. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5260\u20135269 (2021)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., et al.: CCNet: criss-cross attention for semantic segmentation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 603\u2013612 (2018)","DOI":"10.1109\/ICCV.2019.00069"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Xiao, T., et al.: Unified perceptual parsing for scene understanding. ArXiv arxiv:1807.10221 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"27_CR10","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"key":"27_CR11","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800\u20131807 (2016)","DOI":"10.1109\/CVPR.2017.195"},{"key":"27_CR14","unstructured":"Li, Y., et al.: Rethinking vision transformers for MobileNet size and speed. ArXiv arxiv:2212.08059 (2022)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: ShuffleNet: an extremely efficient convolutional neural network for mobile devices. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6848\u20136856 (2017)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Chen, C.-F., et al.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 347\u2013356 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"27_CR17","first-page":"14541","volume":"35","author":"Z Pan","year":"2022","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with hilo attention. Adv. Neural. Inf. Process. Syst. 35, 14541\u201314554 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR18","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. ArXiv arxiv:2110.02178 (2021)"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CAMP: cross-modal adaptive message passing for text-image retrieval. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5763\u20135772 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"27_CR20","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning (2015)"},{"key":"27_CR21","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2015","unstructured":"Agrawal, A., et al.: VQA: visual question answering. Int. J. Comput. Vision 123, 4\u201331 (2015)","journal-title":"Int. J. Comput. Vision"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8549-4_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T20:07:31Z","timestamp":1730923651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8549-4_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985487","9789819985494"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8549-4_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}