{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:08:18Z","timestamp":1759334898519,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032027245"},{"type":"electronic","value":"9783032027252"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02725-2_33","type":"book-chapter","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:33:24Z","timestamp":1759278804000},"page":"423-434","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deploying Vision Foundation AI Models on\u00a0the\u00a0Edge. The SAM2 Experience"],"prefix":"10.1007","author":[{"given":"Zheshuo","family":"Lin","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1409-5843","authenticated-orcid":false,"given":"Ruben","family":"Tous","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9194-559X","authenticated-orcid":false,"given":"Beatriz","family":"Otero","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"33_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S., Bisht, P., Mula, R., Dhavala, S.S.: A deep learning framework for interoperable machine learning. In: Proceedings of the First International Conference on AI-ML Systems. AIMLSystems \u201921, ACM, New York, NY, USA (2021). https:\/\/doi.org\/10.1145\/3486001.3486243","DOI":"10.1145\/3486001.3486243"},{"key":"33_CR2","doi-asserted-by":"publisher","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9630\u20139640 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00951","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"33_CR3","unstructured":"developers, O.R.: Onnx runtime. https:\/\/onnxruntime.ai\/ (2021)"},{"key":"33_CR4","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2020)"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Mvitv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"33_CR7","unstructured":"Lin, T., et\u00a0al.: Microsoft COCO: common objects in context. CoRR abs\/1405.0312 (2014), http:\/\/arxiv.org\/abs\/1405.0312"},{"key":"33_CR8","doi-asserted-by":"publisher","unstructured":"Liu, H., Zhang, E., Wu, J., Hong, M., Jin, Y.: Surgical SAM 2: real-time segment anything in surgical video by efficient frame pruning. CoRR abs\/2408.07931 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2408.07931","DOI":"10.48550\/ARXIV.2408.07931"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: Efficientvit: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14420\u201314430 (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"33_CR11","doi-asserted-by":"publisher","unstructured":"Papa, L., Russo, P., Amerini, I., Zhou, L.: A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking. IEEE Trans. Pattern Anal. Mach. Intell. 46(12) (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3392941","DOI":"10.1109\/TPAMI.2024.3392941"},{"key":"33_CR12","unstructured":"Qin, D., et\u00a0al.: Mobilenetv4-universal models for the mobile ecosystem. arXiv preprint arXiv:2404.10518 (2024)"},{"key":"33_CR13","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18\u201324 July 2021, Virtual Event. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"33_CR14","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"33_CR15","unstructured":"Ryali, C., et\u00a0al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. In: International Conference on Machine Learning, pp. 29441\u201329454 (2023)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"33_CR17","unstructured":"Xiong, Y., et\u00a0al.: Efficient track anything. preprint arXiv:2411.18933 (2024)"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et\u00a0al.: Efficientsam: leveraged masked image pretraining for efficient segment anything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16111\u201316121 (2024)","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Nystr\u00f6mformer: a nystr\u00f6m-based algorithm for approximating self-attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 14138\u201314148 (2021)","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"You, H., et\u00a0al.: Castling-vit: compressing self-attention via switching towards linear-angular attention at vision transformer inference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14431\u201314442 (2023)","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"33_CR21","unstructured":"Zhang, C., et al.: Faster segment anything: towards lightweight sam for mobile applications. arXiv preprint arXiv:2306.14289 (2023)"},{"key":"33_CR22","unstructured":"Zhao, X., et\u00a0al.: Fast segment anything. arXiv preprint arXiv:2306.12156 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advances in Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02725-2_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:33:35Z","timestamp":1759278815000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02725-2_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783032027245","9783032027252"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02725-2_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IWANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Work-Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"A Coru\u00f1a","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iwann.uma.es\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}