{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:19:46Z","timestamp":1780607986859,"version":"3.54.1"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031234729","type":"print"},{"value":"9783031234736","type":"electronic"}],"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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-23473-6_21","type":"book-chapter","created":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T02:36:12Z","timestamp":1672540572000},"page":"266-277","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["GRVT: Toward Effective Grocery Recognition via\u00a0Vision Transformer"],"prefix":"10.1007","author":[{"given":"Shu","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengzhang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beiji","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,1]]},"reference":[{"key":"21_CR1","unstructured":"Wei, X.S., Cui, Q., Yang, L., Wang, P., Liu, L.: RPC: a large-scale retail product checkout dataset. arXiv preprint arXiv:1901.07249 (2019)"},{"key":"21_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-11024-6_1","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"M Leo","year":"2019","unstructured":"Leo, M., Furnari, A., Medioni, G.G., Trivedi, M., Farinella, G.M.: Deep learning for assistive computer vision. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11134, pp. 3\u201314. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11024-6_1"},{"key":"21_CR3","doi-asserted-by":"publisher","unstructured":"Wei, Y., Tran, S., Xu, S., Kang, B., Springer, M.: Deep learning for retail product recognition: challenges and techniques. Comput. Intell. Neurosci. 2020, 23 (2020). https:\/\/doi.org\/10.1155\/2020\/8875910. Article ID: 8875910","DOI":"10.1155\/2020\/8875910"},{"key":"21_CR4","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, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"21_CR5","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"21_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"21_CR8","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. In: International Conference on Learning Representations (2021)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: 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":"21_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"21_CR11","unstructured":"Jund, P., Abdo, N., Eitel, A., Burgard, W.: The freiburg groceries dataset. arXiv preprint arXiv:1611.05799 (2016)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Klasson, M., Zhang, C., Kjellstr\u00f6m, H.: A hierarchical grocery store image dataset with visual and semantic labels. In: 2019 IEEE Winter Conference on Applications of Computer Vision, pp. 491\u2013500. IEEE (2019)","DOI":"10.1109\/WACV.2019.00058"},{"key":"21_CR13","unstructured":"Hu, T., Qi, H., Huang, Q., Lu, Y.: See better before looking closer: weakly supervised data augmentation network for fine-grained visual classification. arXiv preprint arXiv:1901.09891 (2019)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bai, Y., Zhang, W., Mei, T.: Destruction and construction learning for fine-grained image recognition. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5157\u20135166 (2019)","DOI":"10.1109\/CVPR.2019.00530"},{"key":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/978-3-030-50347-5_8","volume-title":"Image Analysis and Recognition","author":"MM Srivastava","year":"2020","unstructured":"Srivastava, M.M.: Bag of tricks for retail product image classification. In: Campilho, A., Karray, F., Wang, Z. (eds.) ICIAR 2020. LNCS, vol. 12131, pp. 71\u201382. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-50347-5_8"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Ji, R., et al.: Attention convolutional binary neural tree for fine-grained visual categorization. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10468\u201310477 (2020)","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"21_CR17","unstructured":"He, J., et al.: TransFG: a transformer architecture for fine-grained recognition. arXiv preprint arXiv:2103.07976 (2021)"},{"key":"21_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/978-3-030-68790-8_26","volume-title":"Pattern Recognition. ICPR International Workshops and Challenges","author":"G Ciocca","year":"2021","unstructured":"Ciocca, G., Napoletano, P., Locatelli, S.G.: Multi-task learning for supervised and unsupervised classification of grocery images. In: Del Bimbo, A., et al. (eds.) ICPR 2021. LNCS, vol. 12662, pp. 325\u2013338. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-68790-8_26"},{"key":"21_CR19","unstructured":"Noy, A., et al.: ASAP: architecture search, anneal and prune. In: International Conference on Artificial Intelligence and Statistics, pp. 493\u2013503. PMLR (2020)"},{"key":"21_CR20","unstructured":"Nayman, N., Noy, A., Ridnik, T., Friedman, I., Jin, R., Zelnik, L.: XNAS: neural architecture search with expert advice. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"issue":"18","key":"21_CR21","doi-asserted-by":"publisher","first-page":"14613","DOI":"10.1007\/s00521-020-05148-3","volume":"32","author":"W Wang","year":"2020","unstructured":"Wang, W., Cui, Y., Li, G., Jiang, C., Deng, S.: A self-attention-based destruction and construction learning fine-grained image classification method for retail product recognition. Neural Comput. Appl. 32(18), 14613\u201314622 (2020). https:\/\/doi.org\/10.1007\/s00521-020-05148-3","journal-title":"Neural Comput. Appl."},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Leo, M., Carcagn\u00ec, P., Distante, C.: A systematic investigation on end-to-end deep recognition of grocery products in the wild. In: 2020 25th International Conference on Pattern Recognition, pp. 7234\u20137241. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413250"},{"key":"21_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"21_CR24","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"21_CR25","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":"21_CR26","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":"21_CR27","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23473-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T03:23:33Z","timestamp":1672543413000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23473-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031234729","9783031234736"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23473-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"1 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"39","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2022a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.cgs-network.org\/cgi22\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"139","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":"45","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":"32% - 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","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","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}