{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T03:52:16Z","timestamp":1768276336431,"version":"3.49.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:00:00Z","timestamp":1665014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:00:00Z","timestamp":1665014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["the grant 62071171"],"award-info":[{"award-number":["the grant 62071171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s00521-022-07873-3","type":"journal-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T01:02:46Z","timestamp":1665018166000},"page":"1881-1897","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Fine-grained image retrieval by combining attention mechanism and context information"],"prefix":"10.1007","volume":"35","author":[{"given":"Xiaoqing","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7388-4295","authenticated-orcid":false,"given":"Jinwen","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"7873_CR1","unstructured":"Wah C, Branson S, Welinder P, Perona P, Belongie S (2011) The Caltech-UCSD Birds-200-2011 Dataset. Technical Report CNS-TR-2011-001, California Institute of Technology"},{"key":"7873_CR2","doi-asserted-by":"crossref","unstructured":"Krause J, Stark M, Deng J, Fei-Fei L (2013) 3d object representations for fine-grained categorization. In: Proceedings of the IEEE international conference on computer vision workshops, pp 554\u2013561","DOI":"10.1109\/ICCVW.2013.77"},{"key":"7873_CR3","unstructured":"Khosla A, Jayadevaprakash N, Yao B, Li F-F (2011) Novel dataset for fine-grained image categorization: Stanford dogs. In: Proc. CVPR workshop on fine-grained visual categorization (FGVC), vol 2. Citeseer"},{"issue":"6","key":"7873_CR4","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1109\/TCYB.2017.2712798","volume":"48","author":"X Zhang","year":"2017","unstructured":"Zhang X, Wang S, Li Z, Ma S (2017) Landmark image retrieval by jointing feature refinement and multimodal classifier learning. IEEE Trans Cybern 48(6):1682\u20131695","journal-title":"IEEE Trans Cybern"},{"key":"7873_CR5","doi-asserted-by":"crossref","unstructured":"D\u2019Innocente A, Garg N, Zhang Y, Bazzani L, Donoser M (2021) Localized triplet loss for fine-grained fashion image retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3910\u20133915","DOI":"10.1109\/CVPRW53098.2021.00435"},{"issue":"11","key":"7873_CR6","doi-asserted-by":"publisher","first-page":"7539","DOI":"10.1007\/s00521-019-04279-6","volume":"32","author":"SR Dubey","year":"2020","unstructured":"Dubey SR, Roy SK, Chakraborty S, Mukherjee S, Chaudhuri BB (2020) Local bit-plane decoded convolutional neural network features for biomedical image retrieval. Neural Comput Appl 32(11):7539\u20137551","journal-title":"Neural Comput Appl"},{"issue":"7","key":"7873_CR7","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi","year":"2018","unstructured":"Radenovi F, Tolias G, Chum O (2018) Fine-tuning CNN image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 41(7):1655\u20131668","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7873_CR8","doi-asserted-by":"crossref","unstructured":"Kim S, Seo M, Laptev I, Cho M, Kwak S (2019) Deep metric learning beyond binary supervision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2288\u20132297","DOI":"10.1109\/CVPR.2019.00239"},{"key":"7873_CR9","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.neucom.2021.04.030","volume":"453","author":"X Zeng","year":"2021","unstructured":"Zeng X, Liu S, Wang X, Zhang Y, Chen K, Li D (2021) Hard decorrelated centralized loss for fine-grained image retrieval. Neurocomputing 453:26\u201337","journal-title":"Neurocomputing"},{"key":"7873_CR10","doi-asserted-by":"crossref","unstructured":"Wang X, Han X, Huang W, Dong D, Scott MR (2019) Multi-similarity loss with general pair weighting for deep metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5022\u20135030","DOI":"10.1109\/CVPR.2019.00516"},{"key":"7873_CR11","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"7873_CR12","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV), pp 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"18","key":"7873_CR13","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 (2020) A self-attention-based destruction and construction learning fine-grained image classification method for retail product recognition. Neural Comput Appl 32(18):14613\u201314622","journal-title":"Neural Comput Appl"},{"issue":"6","key":"7873_CR14","doi-asserted-by":"publisher","first-page":"4733","DOI":"10.1007\/s00521-021-06627-x","volume":"34","author":"L Sa","year":"2022","unstructured":"Sa L, Yu C, Ma X, Zhao X, Xie T (2022) Attentive fine-grained recognition for cross-domain few-shot classification. Neural Comput Appl 34(6):4733\u20134746","journal-title":"Neural Comput Appl"},{"key":"7873_CR15","doi-asserted-by":"crossref","unstructured":"Lin H, Song Y, Zeng Z, Wang W, Wang J (2021) Aggregating object features based on attention weights for fine-grained image retrieval. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 2838\u20132844","DOI":"10.1109\/ICPR48806.2021.9412435"},{"key":"7873_CR16","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision. Springer, pp 213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"7873_CR17","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"7873_CR18","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems, pp 6000\u20136010"},{"key":"7873_CR19","unstructured":"Hu T, Qi H, Huang Q, Lu Y (2019) See better before looking closer: weakly supervised data augmentation network for fine-grained visual classification. arXiv preprint arXiv:1901.09891"},{"issue":"8","key":"7873_CR20","first-page":"6","volume":"134","author":"N Ranjan","year":"2016","unstructured":"Ranjan N, Mundada K, Phaltane K, Ahmad S (2016) A survey on techniques in NLP. Int J Comput Appl 134(8):6\u20139","journal-title":"Int J Comput Appl"},{"key":"7873_CR21","doi-asserted-by":"crossref","unstructured":"Zhang Y, Yu X, Cui Z, Wu S, Wen Z, Wang L (2020) Every document owns its structure: inductive text classification via graph neural networks. arXiv preprint arXiv:2004.13826","DOI":"10.18653\/v1\/2020.acl-main.31"},{"key":"7873_CR22","doi-asserted-by":"crossref","unstructured":"Liu X, You X, Zhang X, Wu J, Lv P (2020) Tensor graph convolutional networks for text classification. In: Proceedings of the AAAI conference on artificial intelligence, pp 8409\u20138416","DOI":"10.1609\/aaai.v34i05.6359"},{"key":"7873_CR23","doi-asserted-by":"crossref","unstructured":"Tu M, Wang G, Huang J, Tang Y, He X, Zhou B (2019) Multi-hop reading comprehension across multiple documents by reasoning over heterogeneous graphs. arXiv preprint arXiv:1905.07374","DOI":"10.18653\/v1\/P19-1260"},{"key":"7873_CR24","doi-asserted-by":"crossref","unstructured":"Visin F, Ciccone M, Romero A, Kastner K, Cho K, Bengio Y, Matteucci M, Courville A (2016) Reseg: a recurrent neural network-based model for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 41\u201348","DOI":"10.1109\/CVPRW.2016.60"},{"issue":"4","key":"7873_CR25","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7873_CR26","unstructured":"Yuan Y, Chen X, Wang J (2019) Object-contextual representations for semantic segmentation. arXiv preprint arXiv:1909.11065"},{"key":"7873_CR27","unstructured":"Zhou B, Liu X, Liu Y, Huang Y, Li\u00f2 P, Wang Y (2021) Spectral transform forms scalable transformer. arXiv preprint arXiv:2111.07602"},{"key":"7873_CR28","unstructured":"Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th international conference on neural information processing systems, pp 3844\u20133852"},{"key":"7873_CR29","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: 32nd AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"7873_CR30","doi-asserted-by":"crossref","unstructured":"Chen Z, Li S, Yang B, Li Q, Liu H (2021) Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 1113\u20131122","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"7873_CR31","doi-asserted-by":"crossref","unstructured":"Gao J, Zhang T, Xu C (2019) I know the relationships: Zero-shot action recognition via two-stream graph convolutional networks and knowledge graphs. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 8303\u20138311","DOI":"10.1609\/aaai.v33i01.33018303"},{"key":"7873_CR32","unstructured":"Hu T, Xu J, Huang C, Qi H, Huang Q, Lu Y (2018) Weakly supervised bilinear attention network for fine-grained visual classification. arXiv preprint arXiv:1808.02152"},{"key":"7873_CR33","doi-asserted-by":"crossref","unstructured":"Cao G, Zhu Y, Lu X (2021) Fine-grained image retrieval via multiple part-level feature ensemble. In: 2021 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1\u20136","DOI":"10.1109\/ICME51207.2021.9428460"},{"key":"7873_CR34","doi-asserted-by":"crossref","unstructured":"Ohsong H, Xiang Y, Jegelka S, Savarese S (2016) Deep metric learning via lifted structured feature embedding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4004\u20134012","DOI":"10.1109\/CVPR.2016.434"},{"key":"7873_CR35","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2014) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"7873_CR36","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167"},{"issue":"3","key":"7873_CR37","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"7873_CR38","doi-asserted-by":"crossref","unstructured":"Hadsell R, Chopra S, LeCun Y (2006) Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol 2. IEEE, pp 1735\u20131742","DOI":"10.1109\/CVPR.2006.100"},{"key":"7873_CR39","doi-asserted-by":"crossref","unstructured":"Hu J, Lu J, Tan Y-P (2014) Discriminative deep metric learning for face verification in the wild. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1875\u20131882","DOI":"10.1109\/CVPR.2014.242"},{"key":"7873_CR40","unstructured":"Sohn K (2016) Improved deep metric learning with multi-class n-pair loss objective. In: Advances in neural information processing systems, pp 1857\u20131865"},{"key":"7873_CR41","doi-asserted-by":"crossref","unstructured":"Movshovitz-Attias Y, Toshev A, Leung TK, Ioffe S, Singh S (2017) No fuss distance metric learning using proxies. In: Proceedings of the IEEE international conference on computer vision, pp 360\u2013368","DOI":"10.1109\/ICCV.2017.47"},{"key":"7873_CR42","doi-asserted-by":"crossref","unstructured":"Wu C-Y, Manmatha R, Smola AJ, Krahenbuhl P (2017) Sampling matters in deep embedding learning. In: Proceedings of the IEEE international conference on computer vision, pp 2840\u20132848","DOI":"10.1109\/ICCV.2017.309"},{"key":"7873_CR43","doi-asserted-by":"crossref","unstructured":"Roth K, Brattoli B, Ommer B (2019) Mic: mining interclass characteristics for improved metric learning. In: Proceedings of the IEEE international conference on computer vision, pp 8000\u20138009","DOI":"10.1109\/ICCV.2019.00809"},{"key":"7873_CR44","doi-asserted-by":"crossref","unstructured":"Yuan Y, Yang K, Zhang C (2017) Hard-aware deeply cascaded embedding. In: Proceedings of the IEEE international conference on computer vision, pp 814\u2013823","DOI":"10.1109\/ICCV.2017.94"},{"key":"7873_CR45","doi-asserted-by":"crossref","unstructured":"Opitz M, Waltner G, Possegger H, Bischof H (2018) Deep metric learning with bier: boosting independent embeddings robustly. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/ICCV.2017.555"},{"key":"7873_CR46","doi-asserted-by":"crossref","unstructured":"Kim W, Goyal B, Chawla K, Lee J, Kwon K (2018) Attention-based ensemble for deep metric learning. In: Proceedings of the European conference on computer vision, pp 736\u2013751","DOI":"10.1007\/978-3-030-01246-5_45"},{"key":"7873_CR47","doi-asserted-by":"crossref","unstructured":"Ge W (2018) Deep metric learning with hierarchical triplet loss. In: Proceedings of the European conference on computer vision, pp 269\u201328","DOI":"10.1007\/978-3-030-01231-1_17"},{"key":"7873_CR48","doi-asserted-by":"crossref","unstructured":"Zheng X, Ji R, Sun X, Zhang B, Wu Y, Huang F. Towards optimal fine grained retrieval via decorrelated centralized loss with normalize-scale layer. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 9291\u20139298","DOI":"10.1609\/aaai.v33i01.33019291"},{"key":"7873_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.10.006","volume":"93","author":"X Zeng","year":"2020","unstructured":"Zeng X, Zhang Y, Wang X, Chen K, Li D, Yang W (2020) Fine-grained image retrieval via piecewise cross entropy loss. Image Vis Comput 93:103820","journal-title":"Image Vis Comput"},{"key":"7873_CR50","doi-asserted-by":"crossref","unstructured":"Kim S, Kim D, Cho M, Kwak S (2020) Proxy anchor loss for deep metric learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3238\u20133247","DOI":"10.1109\/CVPR42600.2020.00330"},{"key":"7873_CR51","unstructured":"Seidenschwarz JD, Elezi I, Leal-Taix\u00e9 L (2021) Learning intra-batch connections for deep metric learning. In: International conference on machine learning. PMLR, pp 9410\u20139421"},{"issue":"6","key":"7873_CR52","doi-asserted-by":"publisher","first-page":"2868","DOI":"10.1109\/TIP.2017.2688133","volume":"26","author":"X-S Wei","year":"2017","unstructured":"Wei X-S, Luo J-H, Wu J, Zhou Z-H (2017) Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE Trans Image Process 26(6):2868\u20132881","journal-title":"IEEE Trans Image Process"},{"key":"7873_CR53","doi-asserted-by":"crossref","unstructured":"Zheng X, Ji R, Sun X, Wu Y, Huang F, Yang Y (2018) Centralized ranking loss with weakly supervised localization for fine-grained object retrieval. In: IJCAI, pp 1226\u20131233","DOI":"10.24963\/ijcai.2018\/171"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07873-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07873-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07873-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T17:28:21Z","timestamp":1673285301000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07873-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,6]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["7873"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07873-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,6]]},"assertion":[{"value":"13 February 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 September 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2022","order":3,"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"}}]}}