{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:35:26Z","timestamp":1772120126180,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T00:00:00Z","timestamp":1700611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T00:00:00Z","timestamp":1700611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802250"],"award-info":[{"award-number":["61802250"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s13735-023-00306-4","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T22:01:29Z","timestamp":1700604089000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["FOF: a fine-grained object detection and feature extraction end-to-end network"],"prefix":"10.1007","volume":"12","author":[{"given":"Wenzhong","family":"Shen","sequence":"first","affiliation":[]},{"given":"Jinpeng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"306_CR1","doi-asserted-by":"crossref","unstructured":"Wei X-S, Cui Q, Yang L, Wang P, Liu L, Yang J (2022) Rpc: a large-scale and fine-grained retail product checkout dataset","DOI":"10.1007\/s11432-022-3513-y"},{"key":"306_CR2","doi-asserted-by":"crossref","unstructured":"Ding Y, Zhou Y, Zhu Y, Ye Q, Jiao J (2019) Selective sparse sampling for fine-grained image recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6599\u20136608","DOI":"10.1109\/ICCV.2019.00670"},{"key":"306_CR3","doi-asserted-by":"crossref","unstructured":"Fu J, Zheng H, Mei T (2017) Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4438\u20134446","DOI":"10.1109\/CVPR.2017.476"},{"key":"306_CR4","doi-asserted-by":"crossref","unstructured":"Liu C, Xie H, Zha Z-J, Ma L, Lingyun Yu, Zhang Y (2020) Filtration and distillation: enhancing region attention for fine-grained visual categorization. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 11555\u201311562","DOI":"10.1609\/aaai.v34i07.6822"},{"issue":"3","key":"306_CR5","doi-asserted-by":"publisher","first-page":"1487","DOI":"10.1109\/TIP.2017.2774041","volume":"27","author":"Y Peng","year":"2017","unstructured":"Peng Y, He X, Zhao J (2017) Object-part attention model for fine-grained image classification. IEEE Trans Image Process 27(3):1487\u20131500","journal-title":"IEEE Trans Image Process"},{"key":"306_CR6","doi-asserted-by":"crossref","unstructured":"Zhang N, Donahue J, Girshick R, Darrell T (2014) Part-based r-cnns for fine-grained category detection. In: Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, part I 13. Springer, pp 834\u2013849","DOI":"10.1007\/978-3-319-10590-1_54"},{"issue":"2","key":"306_CR7","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1109\/TIP.2015.2509425","volume":"25","author":"X Zhang","year":"2015","unstructured":"Zhang X, Xiong H, Zhou W, Tian Q (2015) Fused one-vs-all features with semantic alignments for fine-grained visual categorization. IEEE Trans Image Process 25(2):878\u2013892","journal-title":"IEEE Trans Image Process"},{"key":"306_CR8","doi-asserted-by":"crossref","unstructured":"Zheng H, Fu J, Zha Z-J, Luo J (2019) Looking for the devil in the details: learning trilinear attention sampling network for fine-grained image recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5012\u20135021","DOI":"10.1109\/CVPR.2019.00515"},{"key":"306_CR9","doi-asserted-by":"publisher","first-page":"704","DOI":"10.1016\/j.patcog.2017.10.002","volume":"76","author":"X-S Wei","year":"2018","unstructured":"Wei X-S, Xie C-W, Jianxin W, Shen C (2018) Mask-cnn: localizing parts and selecting descriptors for fine-grained bird species categorization. Pattern Recogn 76:704\u2013714","journal-title":"Pattern Recogn"},{"key":"306_CR10","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Roy CA, Maji S (2015) Bilinear cnn models for fine-grained visual recognition. In: Proceedings of the IEEE international conference on computer vision, pp 1449\u20131457","DOI":"10.1109\/ICCV.2015.170"},{"key":"306_CR11","doi-asserted-by":"crossref","unstructured":"Zhao Y, Yan K, Huang F, Li J (2021) Graph-based high-order relation discovery for fine-grained recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15079\u201315088","DOI":"10.1109\/CVPR46437.2021.01483"},{"key":"306_CR12","first-page":"273","volume":"33","author":"X Sun","year":"2019","unstructured":"Sun X, Chen L, Yang J (2019) Learning from web data using adversarial discriminative neural networks for fine-grained classification. Proc AAAI Conf Artif Intell 33:273\u2013280","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"306_CR13","doi-asserted-by":"crossref","unstructured":"He X, Peng Y (2017) Fine-grained image classification via combining vision and language. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5994\u20136002","DOI":"10.1109\/CVPR.2017.775"},{"key":"306_CR14","unstructured":"Wei S, Guo R, Cui C, Lu B, Dong S, Gao T, Du Y, Zhou Y, Lyu X, Liu Q, et\u00a0al (2021) Pp-shitu: a practical lightweight image recognition system. arXiv:2111.00775"},{"key":"306_CR15","doi-asserted-by":"crossref","unstructured":"Wang Q, Rasmussen C (2019) Towards fine-grained recognition: joint learning for object detection and fine-grained classification. In: Advances in visual computing: 14th international symposium on visual computing, ISVC 2019, Lake Tahoe, NV, USA, October 7\u20139, 2019, proceedings, Part II 14. Springer, pp 332\u2013344","DOI":"10.1007\/978-3-030-33723-0_27"},{"key":"306_CR16","doi-asserted-by":"publisher","first-page":"107891","DOI":"10.1016\/j.asoc.2021.107891","volume":"113","author":"Z Lv","year":"2021","unstructured":"Lv Z, Wang W, Zhiqiang X, Zhang K, Fan Y, Song Y (2021) Fine-grained object detection method using attention mechanism and its application in coal-gangue detection. Appl Soft Comput 113:107891","journal-title":"Appl Soft Comput"},{"key":"306_CR17","doi-asserted-by":"crossref","unstructured":"Deng J, Guo J, Xue N, Zafeiriou S (2019) Arcface: additive angular margin loss for deep face recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4690\u20134699","DOI":"10.1109\/CVPR.2019.00482"},{"key":"306_CR18","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2022) Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"12","key":"306_CR19","doi-asserted-by":"publisher","first-page":"7722","DOI":"10.1109\/TII.2019.2954956","volume":"16","author":"H Zhang","year":"2020","unstructured":"Zhang H, Li D, Ji Y, Zhou H, Weiwei W, Liu K (2020) Toward new retail: a benchmark dataset for smart unmanned vending machines. IEEE Trans Industr Inf 16(12):7722\u20137731","journal-title":"IEEE Trans Industr Inf"},{"key":"306_CR20","unstructured":"Jocher G, et al (2021) ultralytics\/yolov5: v6.0 - YOLOv5n \u2019Nano\u2019 models, Roboflow integration, TensorFlow export, OpenCV DNN support"},{"key":"306_CR21","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) Yolox: exceeding yolo series in 2021. arXiv:2107.08430"},{"issue":"8","key":"306_CR22","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng Z, Wang P, Ren D, Liu W, Ye R, Qinghua H, Zuo W (2021) Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans Cybern 52(8):8574\u20138586","journal-title":"IEEE Trans Cybern"},{"key":"306_CR23","unstructured":"Van\u00a0der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9(11)"},{"key":"306_CR24","unstructured":"Yu G, Chang Q, Lv W, Chang X, Cui C, Ji W, Dang Q, Deng K, Wang G, Yuning D, Lai B, Liu Q, Hu X, Yu D, Ma Y (2021) A better real-time object detector on mobile devices, Pp-picodet"},{"key":"306_CR25","unstructured":"Cui C, Gao T, Wei S, Du Y, Guo R, Dong S, Bin L, Zhou Y, Lv X, Liu Q, Hu X, Yu D, Ma Y (2021) A lightweight cpu convolutional neural network, Pp-lcnet"},{"key":"306_CR26","doi-asserted-by":"crossref","unstructured":"Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906), vol\u00a02. IEEE, pp 1735\u20131742","DOI":"10.1109\/CVPR.2006.100"},{"key":"306_CR27","unstructured":"Hermans A, Beyer L, Leibe B (2017) In defense of the triplet loss for person re-identification. arXiv:1703.07737"},{"key":"306_CR28","doi-asserted-by":"crossref","unstructured":"Wen Y, Zhang K, Li Z, Qiao Y (2016) A discriminative feature learning approach for deep face recognition. In: Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, proceedings, part VII 14. Springer, pp 499\u2013515","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"306_CR29","unstructured":"Liu W, Wen Y, Yu Z, Yang M (2016) Large-margin softmax loss for convolutional neural networks. arXiv:1612.02295"},{"key":"306_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Wen Y, Yu Z, Li M, Raj B, Song L (2017) Sphereface: deep hypersphere embedding for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 212\u2013220","DOI":"10.1109\/CVPR.2017.713"},{"key":"306_CR31","doi-asserted-by":"crossref","unstructured":"Wang H, Wang Y, Zhou Z, Ji X, Gong D, Zhou J, Li Z, Liu W (2018) Cosface: large margin cosine loss for deep face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5265\u20135274","DOI":"10.1109\/CVPR.2018.00552"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00306-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-023-00306-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00306-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T09:18:13Z","timestamp":1701508693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-023-00306-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,22]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["306"],"URL":"https:\/\/doi.org\/10.1007\/s13735-023-00306-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2967577\/v1","asserted-by":"object"}]},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,22]]},"assertion":[{"value":"22 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"40"}}