{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:46:25Z","timestamp":1742967985208,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819723027"},{"type":"electronic","value":"9789819723034"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-97-2303-4_15","type":"book-chapter","created":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T08:02:03Z","timestamp":1716883323000},"page":"222-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Empirical Study of\u00a0Attention Networks for\u00a0Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Hao","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbiao","family":"Si","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guilin","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanyi","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xulong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,29]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-58520-4_4","volume-title":"European Conference on Computer Vision","author":"W Chen","year":"2020","unstructured":"Chen, W., et al.: Tensor low-rank reconstruction for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 202, vol. 12362, pp. 52\u201369. Springer, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_4"},{"key":"15_CR2","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Fu, J., et al.: Dual attention network for scene segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"15_CR5","unstructured":"Guo, M.H., et al.: Attention mechanisms in computer vision: a survey. In: Computational Visual Media, pp. 1\u201338 (2022)"},{"issue":"4","key":"15_CR6","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.tics.2005.02.009","volume":"9","author":"M Hayhoe","year":"2005","unstructured":"Hayhoe, M., Ballard, D.: Eye movements in natural behavior. Trends Cogn. Sci. 9(4), 188\u2013194 (2005)","journal-title":"Trends Cogn. Sci."},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Hu, X., Yang, K., Fei, L., Wang, K.: ACNET: attention based network to exploit complementary features for rgbd semantic segmentation. In: 2019 IEEE International Conference on Image Processing (ICIP), pp. 1440\u20131444. IEEE (2019)","DOI":"10.1109\/ICIP.2019.8803025"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y., Liu, W.: Ccnet: criss-cross attention for semantic segmentation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 603\u2013612 (2019)","DOI":"10.1109\/ICCV.2019.00069"},{"issue":"11","key":"15_CR10","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254\u20131259 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Li, L., Zhou, T., Wang, W., Li, J., Yang, Y.: Deep hierarchical semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1246\u20131257 (2022)","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Zhong, Z., Wu, J., Yang, Y., Lin, Z., Liu, H.: Expectation-maximization attention networks for semantic segmentation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9167\u20139176 (2019)","DOI":"10.1109\/ICCV.2019.00926"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Zhao, H., Han, L., Tong, Y., Tan, S., Yang, K.: Gated fully fusion for semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11418\u201311425 (2020)","DOI":"10.1609\/aaai.v34i07.6805"},{"key":"15_CR14","unstructured":"Molchanov, P., Tyree, S., Karras, T., Aila, T., Kautz, J.: Pruning convolutional neural networks for resource efficient inference. arXiv preprint arXiv:1611.06440 (2016)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Ravanbakhsh, M., et al.: Human-machine collaboration for medical image segmentation. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1040\u20131044. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053555"},{"key":"15_CR16","unstructured":"Song, Q., Li, J., Li, C., Guo, H., Huang, R.: Fully attentional network for semantic segmentation. arXiv preprint arXiv:2112.04108 (2021)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"15_CR18","doi-asserted-by":"publisher","unstructured":"Sun, A., Zhang, X., Ling, T., Wang, J., Cheng, N., Xiao, J.: Pre-avatar: an automatic presentation generation framework leveraging talking avatar. In: 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1002\u20131006 (2022). https:\/\/doi.org\/10.1109\/ICTAI56018.2022.00153","DOI":"10.1109\/ICTAI56018.2022.00153"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Valenzuela, A., Arellano, C., Tapia, J.: An efficient dense network for semantic segmentation of eyes images captured with virtual reality lens. In: 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), pp. 28\u201334. IEEE (2019)","DOI":"10.1109\/SITIS.2019.00017"},{"key":"15_CR20","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008 (2017)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Wang, P., et al.: Understanding convolution for semantic segmentation. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451\u20131460. IEEE (2018)","DOI":"10.1109\/WACV.2018.00163"},{"key":"15_CR22","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR23","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057. PMLR (2015)"},{"key":"15_CR24","first-page":"191","volume-title":"European Conference on Computer Vision","author":"M Yin","year":"2020","unstructured":"Yin, M., et al.: Disentangled non-local neural networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 191\u2013207. Springer, Heidelberg (2020)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Yuan, J., Deng, Z., Wang, S., Luo, Z.: Multi receptive field network for semantic segmentation. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1883\u20131892. IEEE (2020)","DOI":"10.1109\/WACV45572.2020.9093264"},{"key":"15_CR26","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/978-3-030-58539-6_11","volume-title":"European Conference on Computer Vision","author":"Y Yuan","year":"2020","unstructured":"Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 173\u2013190. Springer, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_11"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Psanet: point-wise spatial attention network for scene parsing. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 267\u2013283 (2018)","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, S., et\u00a0al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6881\u20136890 (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., Torralba, A.: Scene parsing through ade20k dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 633\u2013641 (2017)","DOI":"10.1109\/CVPR.2017.544"}],"container-title":["Lecture Notes in Computer Science","Web and Big Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-2303-4_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T08:05:03Z","timestamp":1716883503000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-2303-4_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819723027","9789819723034"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-2303-4_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 May 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"APWeb-WAIM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint International Conference on Web and Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","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":"6 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"apwebwaim2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apweb-waim2023.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}