{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:40:03Z","timestamp":1755877203529,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Key R&D Program of China","award":["No. 2021YFC3320301."],"award-info":[{"award-number":["No. 2021YFC3320301."]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,1,19]]},"DOI":"10.1145\/3653804.3656278","type":"proceedings-article","created":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T12:22:26Z","timestamp":1717244546000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["LAtt-Yolov8-seg: Video Real-time Instance Segmentation for Urban Street Scenes Based on Focused Linear Attention Mechanism"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0469-1277","authenticated-orcid":false,"given":"Xinqi","family":"Zhang","sequence":"first","affiliation":[{"name":"HDU-ITMO Joint Institute, Hangzhou Dianzi University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1201-6355","authenticated-orcid":false,"given":"Tuo","family":"Dong","sequence":"additional","affiliation":[{"name":"Comprehensive Command and Support Center of Grassroots Governance, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7077-4947","authenticated-orcid":false,"given":"Liqi","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5087-2763","authenticated-orcid":false,"given":"Zhenglei","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0979-6514","authenticated-orcid":false,"given":"Jianhui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hangzhou Dianzi University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"99","volume-title":"Advances in neural information processing systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91\u201399, 2015."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3202574"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_4_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, 40(4):834\u2013848, 2017."},{"key":"e_1_3_2_1_5_1","volume-title":"NeurIPS","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In NeurIPS, 2017. 1, 2"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"e_1_3_2_1_8_1","first-page":"5961","volume":"2023","author":"Han","unstructured":"Han D, Pan X, Han Y, Flatten transformer: Vision transformer using focused linear attention[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023: 5961-5971.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_10_1","volume-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv","author":"M.","year":"2022","unstructured":"Wang, C.Y.; Bochkovskiy, A.; Liao, H.Y.M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv 2022, arXiv:2207.02696."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"e_1_3_2_1_12_1","first-page":"2125","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"S.","year":"2017","unstructured":"Lin, T.Y.; Doll\u00e1r, P.; Girshick, R.; He, K.; Hariharan, B.; Belongie, S. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 21\u201326 July 2017; pp. 2117\u20132125."},{"key":"e_1_3_2_1_13_1","first-page":"8768","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J.","year":"2018","unstructured":"Liu, S.; Qi, L.; Qin, H.; Shi, J.; Jia, J. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18\u201323 June 2018; pp. 8759\u20138768."},{"key":"e_1_3_2_1_14_1","first-page":"5165","volume-title":"International Conference on Machine Learning","author":"Katharopoulos Angelos","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Franc \u0327ois Fleuret. Transformers are rnns: Fast autoregressive transformers with linear attention. In International Conference on Machine Learning, pages 5156\u20135165. PMLR, 2020. 2, 3"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Learning Representations","author":"Qin Zhen","year":"2022","unstructured":"Zhen Qin, Weixuan Sun, Hui Deng, Dongxu Li, Yunshen Wei, Baohong Lv, Junjie Yan, Lingpeng Kong, and Yiran Zhong. cosformer: Rethinking softmax in attention. In International Conference on Learning Representations, 2022. 3"},{"key":"e_1_3_2_1_16_1","first-page":"10357","volume-title":"International Conference on Machine Learning","author":"Touvron Hugo","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv \u0301e J \u0301egou. Training data-efficient image transformers & distillation through attention. In International Conference on Machine Learning, pages 10347\u201310357. PMLR, 2021. 1, 4, 5, 6"},{"key":"e_1_3_2_1_17_1","first-page":"1","author":"He Kaiming","year":"2017","unstructured":"Kaiming He, Georgia Gkioxari, Piotr Doll \u0301ar, and Ross Girshick. Mask R-CNN. In ICCV, 2017. 1, 2","journal-title":"Ross Girshick. Mask R-CNN. In"},{"key":"e_1_3_2_1_18_1","volume-title":"Saunier N","author":"Perreault","year":"2021","unstructured":"Perreault H, Bilodeau G A, Saunier N, Centerpoly: Real-time instance segmentation using bounding polygons[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 2982-2991."},{"key":"e_1_3_2_1_19_1","first-page":"6070","volume":"2023","author":"Qi","unstructured":"Qi Y, He Y, Qi X, Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023: 6070-6079.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision."},{"key":"e_1_3_2_1_20_1","first-page":"23663","volume":"2023","author":"He","unstructured":"He J, Li P, Geng Y, FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation[C]\/\/Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2023: 23663-23672.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."}],"event":{"name":"CVDL 2024: The International Conference on Computer Vision and Deep Learning","acronym":"CVDL 2024","location":"Changsha China"},"container-title":["Proceedings of the International Conference on Computer Vision and Deep Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653804.3656278","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3653804.3656278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:27:19Z","timestamp":1755876439000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3653804.3656278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":20,"alternative-id":["10.1145\/3653804.3656278","10.1145\/3653804"],"URL":"https:\/\/doi.org\/10.1145\/3653804.3656278","relation":{},"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"2024-06-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}