{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:39:27Z","timestamp":1743115167680,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031189098"},{"type":"electronic","value":"9783031189104"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-18910-4_50","type":"book-chapter","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:03:53Z","timestamp":1666825433000},"page":"626-638","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Semantic Center Guided Windows Attention Fusion Framework for\u00a0Food Recognition"],"prefix":"10.1007","author":[{"given":"Yongxin","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jiale","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xiong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wenxiong","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Zeng","family":"Ming","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,27]]},"reference":[{"issue":"12","key":"50_CR1","doi-asserted-by":"publisher","first-page":"3266","DOI":"10.1109\/TMM.2018.2831627","volume":"20","author":"E Aguilar","year":"2018","unstructured":"Aguilar, E., Remeseiro, B., Bola\u00f1os, M., Radeva, P.: Grab, pay, and eat: semantic food detection for smart restaurants. IEEE Trans. Multim. 20(12), 3266\u20133275 (2018)","journal-title":"IEEE Trans. Multim."},{"key":"50_CR2","doi-asserted-by":"publisher","unstructured":"Bossard, L., Guillaumin, M., Van Gool, L.: Food-101 \u2013 mining discriminative components with random forests. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 446\u2013461. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_29","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Chen, J., Ngo, C.W.: Deep-based ingredient recognition for cooking recipe retrieval. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 32\u201341 (2016)","DOI":"10.1145\/2964284.2964315"},{"key":"50_CR4","unstructured":"Chen, X., Zhu, Y., Zhou, H., Diao, L., Wang, D.: Chinesefoodnet: A large-scale image dataset for Chinese food recognition. arXiv preprint arXiv:1705.02743 (2017)"},{"key":"50_CR5","doi-asserted-by":"crossref","unstructured":"Cui, Y., Che, W., Liu, T., Qin, B., Wang, S., Hu, G.: Revisiting pre-trained models for chinese natural language processing. arXiv preprint arXiv:2004.13922 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"50_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL (2019)"},{"key":"50_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2021)"},{"key":"50_CR8","doi-asserted-by":"crossref","unstructured":"Fu, J., Zheng, H., Mei, T.: Look closer to see better: recurrent attention convolutional neural network for fine-grained image recognition. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4476\u20134484 (2017)","DOI":"10.1109\/CVPR.2017.476"},{"key":"50_CR9","doi-asserted-by":"crossref","unstructured":"Hassannejad, H., Matrella, G., Ciampolini, P., De Munari, I., Mordonini, M., Cagnoni, S.: Food image recognition using very deep convolutional networks. In: Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management, pp. 41\u201349 (2016)","DOI":"10.1145\/2986035.2986042"},{"key":"50_CR10","unstructured":"He, J., et al.: Transfg: a transformer architecture for fine-grained recognition. arXiv preprint arXiv:2103.07976 (2021)"},{"key":"50_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"50_CR12","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vsion and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"50_CR13","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Rams-trans: recurrent attention multi-scale transformer for fine-grained image recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 4239\u20134248 (2021)","DOI":"10.1145\/3474085.3475561"},{"key":"50_CR14","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"50_CR15","unstructured":"Huang, Y., et al.: Gpipe: efficient training of giant neural networks using pipeline parallelism. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"50_CR16","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1109\/TIP.2019.2929447","volume":"29","author":"S Jiang","year":"2019","unstructured":"Jiang, S., Min, W., Liu, L., Luo, Z.: Multi-scale multi-view deep feature aggregation for food recognition. IEEE Trans. Image Process. 29, 265\u2013276 (2019)","journal-title":"IEEE Trans. Image Process."},{"key":"50_CR17","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Commun. ACM 60, 84\u201390 (2012)","journal-title":"Commun. ACM"},{"key":"50_CR18","doi-asserted-by":"publisher","unstructured":"Liu, C., Cao, Y., Luo, Y., Chen, G., Vokkarane, V., Ma, Y.: DeepFood: deep learning-based food image recognition for computer-aided dietary assessment. In: Chang, C.K., Chiari, L., Cao, Y., Jin, H., Mokhtari, M., Aloulou, H. (eds.) ICOST 2016. LNCS, vol. 9677, pp. 37\u201348. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-39601-9_4","DOI":"10.1007\/978-3-319-39601-9_4"},{"key":"50_CR19","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":"50_CR20","doi-asserted-by":"crossref","unstructured":"Martinel, N., Foresti, G.L., Micheloni, C.: Wide-slice residual networks for food recognition. In: 2018 IEEE Winter Conference on applications of computer vision (WACV), pp. 567\u2013576. IEEE (2018)","DOI":"10.1109\/WACV.2018.00068"},{"key":"50_CR21","doi-asserted-by":"crossref","unstructured":"Min, W., Liu, L., Luo, Z., Jiang, S.: Ingredient-guided cascaded multi-attention network for food recognition. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1331\u20131339 (2019)","DOI":"10.1145\/3343031.3350948"},{"key":"50_CR22","doi-asserted-by":"crossref","unstructured":"Min, W., et al.: ISIA food-500: a dataset for large-scale food recognition via stacked global-local attention network. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 393\u2013401 (2020)","DOI":"10.1145\/3394171.3414031"},{"key":"50_CR23","unstructured":"Min, W., et al.: Large scale visual food recognition. arXiv preprint arXiv:2103.16107 (2021)"},{"key":"50_CR24","doi-asserted-by":"crossref","unstructured":"Myers, A., et al.: Im2calories: towards an automated mobile vision food diary. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1233\u20131241 (2015)","DOI":"10.1109\/ICCV.2015.146"},{"key":"50_CR25","unstructured":"Qiu, J., Lo, F.P.W., Sun, Y., Wang, S., Lo, B.P.L.: Mining discriminative food regions for accurate food recognition. In: British Machine Vision Association (BMVC) (2019)"},{"key":"50_CR26","doi-asserted-by":"crossref","unstructured":"Salvador, A., Hynes, N., Aytar, Y., Mar\u00edn, J., Ofli, F., Weber, I., Torralba, A.: Learning cross-modal embeddings for cooking recipes and food images. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3068\u20133076 (2017)","DOI":"10.1109\/CVPR.2017.327"},{"key":"50_CR27","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"50_CR28","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"50_CR29","unstructured":"Wei, X.S., Xie, C.W., Wu, J.: Mask-CNN: localizing parts and selecting descriptors for fine-grained image recognition. arXiv preprint arXiv:1605.06878 (2016)"},{"key":"50_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, H., Yap, K.H., Kot, A.C.: Fusion learning using semantics and graph convolutional network for visual food recognition. In: 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1710\u20131719 (2021)","DOI":"10.1109\/WACV48630.2021.00175"}],"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\/978-3-031-18910-4_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T23:38:55Z","timestamp":1666827535000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-18910-4_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031189098","9783031189104"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-18910-4_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 October 2022","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":"Shenzhen","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/en.prcv.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","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"564","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":"233","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":"41% - 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":"3.03","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":"3.35","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)"}}]}}