{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T19:58:59Z","timestamp":1779220739208,"version":"3.51.4"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["Appl Intell"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s10489-025-06513-2","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T13:46:51Z","timestamp":1743688011000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["SiamYOLOv8: a rapid conditional detection framework for one-shot object detection"],"prefix":"10.1007","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6533-2477","authenticated-orcid":false,"given":"Matthieu","family":"Desmarescaux","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wissam","family":"Kaddah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ayman","family":"Alfalou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isabelle","family":"Badoc","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,1]]},"reference":[{"key":"6513_CR1","unstructured":"Vinyals O, Blundell C, Lillicrap T, kavukcuoglu K, Wierstra D (2016) Matching networks for one shot learning. In: Advances in neural information processing systems, vol. 29. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2016\/hash\/90e1357833654983612fb05e3ec9148c-Abstract.html. Accessed 24 Jan 2023"},{"key":"6513_CR2","doi-asserted-by":"publisher","unstructured":"Fei-Fei L, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28(4):594\u2013611. https:\/\/doi.org\/10.1109\/TPAMI.2006.79. Accessed 17 Apr 2023","DOI":"10.1109\/TPAMI.2006.79"},{"key":"6513_CR3","doi-asserted-by":"publisher","unstructured":"Huang Q, Zhang H, Xue M, Song J, Song M (2022) A survey of deep learning for low-shot object detection. arXiv. arXiv:2112.02814 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2112.02814. http:\/\/arxiv.org\/abs\/2112.02814 Accessed on 23 Jan 2025","DOI":"10.48550\/arXiv.2112.02814"},{"key":"6513_CR4","doi-asserted-by":"publisher","unstructured":"Antonelli S, Avola D, Cinque L, Crisostomi D, Foresti GL, Galasso F, Marini MR, Mecca A, Pannone D (2022) Few-shot object detection: a survey. ACM Comput Surv 54(11s):1\u201337. https:\/\/doi.org\/10.1145\/3519022. . Accessed 23 Jan 2023","DOI":"10.1145\/3519022"},{"key":"6513_CR5","unstructured":"K\u00f6hler M, Eisenbach M, Gross H-M (2021) Few-shot object detection: a survey"},{"key":"6513_CR6","doi-asserted-by":"publisher","unstructured":"Liu T, Zhang L, Wang Y, Guan J, Fu Y, Zhou S (2022) An empirical study and comparison of recent few-shot object detection algorithms. arXiv. arXiv:2203.14205 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2203.14205. http:\/\/arxiv.org\/abs\/2203.14205. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.2203.14205"},{"key":"6513_CR7","doi-asserted-by":"publisher","unstructured":"Fu K, Zhang T, Zhang Y, Sun X (2021) OSCD: A one-shot conditional object detection framework. Neurocomputing 425:243\u2013255. https:\/\/doi.org\/10.1016\/j.neucom.2020.04.092. Accessed 23 Jan 2023","DOI":"10.1016\/j.neucom.2020.04.092"},{"key":"6513_CR8","doi-asserted-by":"publisher","unstructured":"Chen T-I, Liu Y-C, Su H-T, Chang Y-C, Lin Y-H, Yeh J-F, Chen W-C, Hsu WH (2023) Dual-awareness attention for few-shot object detection. IEEE Trans Multimedia 25:291\u2013301. https:\/\/doi.org\/10.1109\/TMM.2021.3125195. Conference Name: IEEE Transactions on Multimedia","DOI":"10.1109\/TMM.2021.3125195"},{"key":"6513_CR9","unstructured":"Gouda A, Roidl M (2023) DoUnseen: tuning-free class-adaptive object detection of unseen objects for robotic grasping. arXiv. arXiv:2304.02833 [cs]. http:\/\/arxiv.org\/abs\/2304.02833. Accessed 16 May 2024"},{"key":"6513_CR10","doi-asserted-by":"publisher","unstructured":"Rublee E, Rabaud V, Konolige K, Bradski G (2011) ORB: An efficient alternative to SIFT or SURF. In: 2011 International conference on computer vision, pp 2564\u20132571. https:\/\/doi.org\/10.1109\/ICCV.2011.6126544. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"6513_CR11","doi-asserted-by":"publisher","unstructured":"Leutenegger S, Chli M, Siegwart RY (2011) BRISK: binary robust invariant scalable keypoints. In: 2011 International conference on computer vision, pp 2548\u20132555. https:\/\/doi.org\/10.1109\/ICCV.2011.6126542. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2011.6126542"},{"key":"6513_CR12","doi-asserted-by":"publisher","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110. https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94. Accessed 24 Jan 2023","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"6513_CR13","doi-asserted-by":"publisher","unstructured":"Lowe DG (1999) Object recognition from local scale-invariant features. In: Proceedings of the Seventh IEEE international conference on computer vision, vol 2, pp 1150\u201311572. https:\/\/doi.org\/10.1109\/ICCV.1999.790410","DOI":"10.1109\/ICCV.1999.790410"},{"key":"6513_CR14","doi-asserted-by":"publisher","unstructured":"Bay H, Tuytelaars T, Van\u00a0Gool L (2006) SURF: speeded up robust features. In: Leonardis A, Bischof H, Pinz A (eds) Computer Vision \u2013 ECCV 2006. Lecture Notes in Computer Science. Springer, Berlin, Heidelberg, pp 404\u2013417. https:\/\/doi.org\/10.1007\/11744023_32","DOI":"10.1007\/11744023_32"},{"key":"6513_CR15","doi-asserted-by":"publisher","unstructured":"Fan Z, Yu J-G, Liang Z, Ou J, Gao C, Xia G-S, Li Y (2020) FGN: Fully guided network for few-shot instance segmentation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 9169\u20139178. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00919. ISSN: 2575-7075","DOI":"10.1109\/CVPR42600.2020.00919"},{"key":"6513_CR16","doi-asserted-by":"publisher","unstructured":"Han G, He Y, Huang S, Ma J, Chang S-F (2021) Query adaptive few-shot object detection with heterogeneous graph convolutional networks. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 3243\u20133252. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00325. ISSN: 2380-7504","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"6513_CR17","unstructured":"Hsieh T-I, Lo Y-C, Chen H-T, Liu T-L (2019) One-shot object detection with co-attention and co-excitation. In: Advances in neural information processing systems, vol. 32. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2019\/hash\/92af93f73faf3cefc129b6bc55a748a9-Abstract.html. Accessed 23 Jan 2023"},{"key":"6513_CR18","doi-asserted-by":"publisher","unstructured":"Nguyen K, Todorovic S (2021) FAPIS: A Few-shot Anchor-free Part-based Instance Segmenter. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 11094\u201311103. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01095. ISSN: 2575-7075","DOI":"10.1109\/CVPR46437.2021.01095"},{"key":"6513_CR19","doi-asserted-by":"publisher","unstructured":"Zhao Y, Guo X, Lu Y (2022) Semantic-aligned fusion transformer for one-shot object detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7591\u20137601. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00745. ISSN: 2575-7075","DOI":"10.1109\/CVPR52688.2022.00745"},{"key":"6513_CR20","doi-asserted-by":"publisher","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The Pascal Visual Object Classes (VOC) Challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4. Accessed 23 Jan 2023","DOI":"10.1007\/s11263-009-0275-4"},{"key":"6513_CR21","unstructured":"Lin T-Y, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Zitnick CL, Doll\u00e1r P (2015) Microsoft COCO: Common objects in context. arXiv. arXiv:1405.0312 [cs]. http:\/\/arxiv.org\/abs\/1405.0312 Accessed 23 Jan 2023"},{"key":"6513_CR22","doi-asserted-by":"publisher","unstructured":"Michaelis C, Ustyuzhaninov I, Bethge M, Ecker AS (2019) One-Shot Instance Segmentation. arXiv. arXiv:1811.11507 [cs]. https:\/\/doi.org\/10.48550\/arXiv.1811.11507 . http:\/\/arxiv.org\/abs\/1811.11507. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.1811.11507"},{"key":"6513_CR23","doi-asserted-by":"publisher","unstructured":"Osokin A, Sumin D, Lomakin V (2020) OS2D: One-stage one-shot object detection by matching anchor features. In: Vedaldi A, Bischof H, Brox T, Frahm J-M (eds) Computer Vision \u2013 ECCV 2020. Lecture Notes in Computer Science. Springer, Cham, pp 635\u2013652. https:\/\/doi.org\/10.1007\/978-3-030-58555-6_38","DOI":"10.1007\/978-3-030-58555-6_38"},{"key":"6513_CR24","doi-asserted-by":"publisher","unstructured":"Santra B, Shaw AK, Mukherjee DP (2020) Graph-based non-maximal suppression for detecting products on the rack. Pattern Recognit Lett 140:73\u201380. https:\/\/doi.org\/10.1016\/j.patrec.2020.09.023. Accessed 25 Oct 2023","DOI":"10.1016\/j.patrec.2020.09.023"},{"key":"6513_CR25","doi-asserted-by":"publisher","unstructured":"Santra B, Shaw AK, Mukherjee DP (2022) Part-based annotation-free fine-grained classification of images of retail products. Pattern Recognit 121:108257. https:\/\/doi.org\/10.1016\/j.patcog.2021.108257. Accessed 25 Oct 2023","DOI":"10.1016\/j.patcog.2021.108257"},{"key":"6513_CR26","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.1007\/s00521-020-05148-3. Accessed 25 Oct 2023","DOI":"10.1007\/s00521-020-05148-3"},{"key":"6513_CR27","doi-asserted-by":"publisher","unstructured":"George M, Floerkemeier C (2014) Recognizing products: A per-exemplar multi-label image classification approach. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision \u2013 ECCV 2014. Lecture Notes in Computer Science. Springer, Cham, pp 440\u2013455. https:\/\/doi.org\/10.1007\/978-3-319-10605-2_29","DOI":"10.1007\/978-3-319-10605-2_29"},{"key":"6513_CR28","doi-asserted-by":"publisher","unstructured":"Guimar\u00e3es V, Nascimento J, Viana P, Carvalho P (2023) A review of recent advances and challenges in grocery label detection and recognition. Appl Sci 13(5):2871. https:\/\/doi.org\/10.3390\/app13052871. Number: 5 Publisher: Multidisciplinary Digital Publishing Institute. Accessed 25 Oct 2023","DOI":"10.3390\/app13052871"},{"key":"6513_CR29","doi-asserted-by":"publisher","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PHS, Hospedales TM (2018) Learning to compare: relation network for few-shot learning. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 1199\u20131208. https:\/\/doi.org\/10.1109\/CVPR.2018.00131. ISSN: 2575-7075","DOI":"10.1109\/CVPR.2018.00131"},{"key":"6513_CR30","doi-asserted-by":"publisher","unstructured":"Kang B, Liu Z, Wang X, Yu F, Feng J, Darrell T (2019) Few-shot object detection via feature reweighting. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 8419\u20138428. https:\/\/doi.org\/10.1109\/ICCV.2019.00851. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2019.00851"},{"key":"6513_CR31","doi-asserted-by":"publisher","unstructured":"K\u00f6hler M, Eisenbach M, Gross H-M (2022) Few-shot object detection: a comprehensive survey. arXiv. arXiv:2112.11699 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2112.11699. http:\/\/arxiv.org\/abs\/2112.11699. Accessed 23 Jan 2023","DOI":"10.48550\/arXiv.2112.11699"},{"key":"6513_CR32","unstructured":"Jocher G, Chaurasia A, Qiu J (2023) Ultralytics YOLO. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"6513_CR33","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems, vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/14bfa6bb14875e45bba028a21ed38046-Abstract.html. Accessed 24 Jan 2023"},{"key":"6513_CR34","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp 1440\u20131448. https:\/\/doi.org\/10.1109\/ICCV.2015.169. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2015.169"},{"key":"6513_CR35","doi-asserted-by":"publisher","unstructured":"He K, Gkioxari G, Doll\u00e3r P, Girshick R (2017) Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp 2980\u20132988. https:\/\/doi.org\/10.1109\/ICCV.2017.322. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2017.322"},{"key":"6513_CR36","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You Only Look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 779\u2013788. https:\/\/doi.org\/10.1109\/CVPR.2016.91. ISSN: 1063-6919","DOI":"10.1109\/CVPR.2016.91"},{"key":"6513_CR37","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2017) YOLO9000: Better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 6517\u20136525. https:\/\/doi.org\/10.1109\/CVPR.2017.690. ISSN: 1063-6919","DOI":"10.1109\/CVPR.2017.690"},{"key":"6513_CR38","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: An Incremental Improvement. arXiv. arXiv:1804.02767 [cs] (2018). https:\/\/doi.org\/10.48550\/arXiv.1804.02767. http:\/\/arxiv.org\/abs\/1804.02767. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.1804.02767"},{"key":"6513_CR39","doi-asserted-by":"publisher","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) YOLOv4: optimal speed and accuracy of object detection. arXiv. arXiv:2004.10934[cs, eess] (2020). https:\/\/doi.org\/10.48550\/arXiv.2004.10934. http:\/\/arxiv.org\/abs\/2004.10934. Accessed 23 Jan 2023","DOI":"10.48550\/arXiv.2004.10934"},{"key":"6513_CR40","doi-asserted-by":"publisher","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) YOLOX: Exceeding YOLO Series in 2021. arXiv. arXiv:2107.08430 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2107.08430. http:\/\/arxiv.org\/abs\/2107.08430. Accessed 23 Jan 2023","DOI":"10.48550\/arXiv.2107.08430"},{"key":"6513_CR41","doi-asserted-by":"publisher","unstructured":"Bakkouri I, Bakkouri S (2024) 2mgas-net: multi-level multi-scale gated attentional squeezed network for polyp segmentation. 18(6):5377\u20135386. https:\/\/doi.org\/10.1007\/s11760-024-03240-y. Accessed 05 Dec 2024","DOI":"10.1007\/s11760-024-03240-y"},{"key":"6513_CR42","doi-asserted-by":"publisher","unstructured":"Bakkouri I, Afdel K (2020) DermoNet: A computer-aided diagnosis system for dermoscopic disease recognition. 12119:170\u2013177. https:\/\/doi.org\/10.1007\/978-3-030-51935-3_18. Accessed 05 Dec 2024","DOI":"10.1007\/978-3-030-51935-3_18"},{"key":"6513_CR43","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Dolla\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 936\u2013944. https:\/\/doi.org\/10.1109\/CVPR.2017.106. ISSN: 1063-6919","DOI":"10.1109\/CVPR.2017.106"},{"key":"6513_CR44","doi-asserted-by":"publisher","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. arXiv:2207.02696 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2207.02696. http:\/\/arxiv.org\/abs\/2207.02696. Accessed 09 Feb 2023","DOI":"10.48550\/arXiv.2207.02696"},{"key":"6513_CR45","doi-asserted-by":"publisher","unstructured":"Wang C-Y, Yeh I-H, Liao H-YM (2024) YOLOv9: Learning what you want to learn using programmable gradient information. arXiv:2402.13616 [cs] . https:\/\/doi.org\/10.48550\/arXiv.2402.13616. http:\/\/arxiv.org\/abs\/2402.13616. Accessed 01 Mar 2024","DOI":"10.48550\/arXiv.2402.13616"},{"key":"6513_CR46","unstructured":"Koch G, Zemel R, Salakhutdinov R et al (2015) Siamese neural networks for one-shot image recognition. In: ICML Deep learning workshop, vol. 2. Lille. Issue: 1"},{"key":"6513_CR47","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Advances in neural information processing systems, vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/cb8da6767461f2812ae4290eac7cbc42-Abstract.html. Accessed 24 Jan 2023"},{"key":"6513_CR48","doi-asserted-by":"publisher","unstructured":"Huynh D, Elhamifar E (2021) Compositional fine-grained low-shot learning. arXiv. https:\/\/doi.org\/10.48550\/ARXIV.2105.10438. Publisher: arXiv Version Number: 1. Accessed 17 Apr 2023","DOI":"10.48550\/ARXIV.2105.10438"},{"key":"6513_CR49","doi-asserted-by":"publisher","unstructured":"K\u00f6hler M, Eisenbach M, Gross H-M (2023) Few-shot object detection: a comprehensive survey. IEEE Trans Neural Netw Learn Syst 1\u201321. https:\/\/doi.org\/10.1109\/TNNLS.2023.3265051. Conference Name: IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2023.3265051"},{"key":"6513_CR50","doi-asserted-by":"publisher","unstructured":"Zhang L, Zhou S, Guan J, Zhang J (2021) Accurate few-shot object detection with support-query mutual guidance and hybrid loss. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 14419\u201314427. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01419. ISSN: 2575-7075","DOI":"10.1109\/CVPR46437.2021.01419"},{"key":"6513_CR51","doi-asserted-by":"publisher","unstructured":"Li Y, Feng W, Lyu S, Zhao Q, Li X (2020) MM-FSOD: Meta and metric integrated few-shot object detection. arXiv. arXiv:2012.15159 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2012.15159. http:\/\/arxiv.org\/abs\/2012.15159. Accessed 23 Jan 2023","DOI":"10.48550\/arXiv.2012.15159"},{"key":"6513_CR52","doi-asserted-by":"publisher","unstructured":"Lee H, Lee M, Kwak N (2022) Few-shot object detection by attending to per-sample-prototype. In: 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, Waikoloa, HI, USA, pp 1101\u20131110. https:\/\/doi.org\/10.1109\/WACV51458.2022.00117. https:\/\/ieeexplore.ieee.org\/document\/9706848\/. Accessed 28 Apr 2023","DOI":"10.1109\/WACV51458.2022.00117"},{"key":"6513_CR53","doi-asserted-by":"publisher","unstructured":"Michaelis C, Bethge M, Ecker AS (2022) A broad dataset is all you need for one-shot object detection. arXiv. arXiv:2011.04267 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2011.04267. http:\/\/arxiv.org\/abs\/2011.04267. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.2011.04267"},{"key":"6513_CR54","doi-asserted-by":"publisher","unstructured":"Zhang S, Wang L, Murray N, Koniusz P (2022) Kernelized Few-shot object detection with efficient integral aggregation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, New Orleans, LA, USA, pp 19185\u201319194. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01861. https:\/\/ieeexplore.ieee.org\/document\/9880443\/. Accessed 28 Apr 2023-04-28","DOI":"10.1109\/CVPR52688.2022.01861"},{"key":"6513_CR55","doi-asserted-by":"publisher","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition, pp. 7794\u20137803. IEEE, Salt Lake City, UT, USA. https:\/\/doi.org\/10.1109\/CVPR.2018.00813. https:\/\/ieeexplore.ieee.org\/document\/8578911\/. Accessed 14 June 2023","DOI":"10.1109\/CVPR.2018.00813"},{"key":"6513_CR56","doi-asserted-by":"publisher","unstructured":"Yang H, Lin Y, Zhang H, Zhang Y, Xu B (2021) Towards improving classification power for one-shot object detection. Neurocomputing 455:390\u2013400. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.116. Accessed 24 Jan 2023","DOI":"10.1016\/j.neucom.2021.04.116"},{"key":"6513_CR57","doi-asserted-by":"publisher","unstructured":"Yang H, Cai S, Sheng H, Deng B, Huang J, Hua X-S, Tang Y, Zhang Y (2022) Balanced and hierarchical relation learning for one-shot object detection. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 7581\u20137590. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00744. ISSN: 2575-7075","DOI":"10.1109\/CVPR52688.2022.00744"},{"key":"6513_CR58","doi-asserted-by":"publisher","unstructured":"Chen D-J, Hsieh H-Y, Liu T-L (2021) Adaptive image transformer for one-shot object detection. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12242\u201312251. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01207. ISSN: 2575-7075","DOI":"10.1109\/CVPR46437.2021.01207"},{"key":"6513_CR59","doi-asserted-by":"publisher","unstructured":"Lin W, Deng Y, Gao Y, Wang N, Zhou J, Liu L, Zhang L, Wang P (2021) CAT: Cross-attention transformer for one-shot object detection. arXiv. arXiv:2104.14984 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2104.14984. http:\/\/arxiv.org\/abs\/2104.14984. Accessed 23 Jan 2023","DOI":"10.48550\/arXiv.2104.14984"},{"key":"6513_CR60","unstructured":"Zhang X, Wang Y, Boularias A (2024) Detect everything with few examples. arXiv. arXiv:2309.12969 [cs]. http:\/\/arxiv.org\/abs\/2309.12969. Accessed 14 May 2024"},{"key":"6513_CR61","doi-asserted-by":"publisher","unstructured":"Minderer M, Gritsenko A, Stone A, Neumann M, Weissenborn D, Dosovitskiy A, Mahendran A, Arnab A, Dehghani M, Shen Z, Wang X, Zhai X, Kipf T, Houlsby N (2022) Simple open-vocabulary object detection. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer Vision \u2013 ECCV 2022. Springer, Cham, pp 728\u2013755. https:\/\/doi.org\/10.1007\/978-3-031-20080-9_42","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"6513_CR62","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, vol. 30. Curran Associates, Inc . https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html Accessed 2023-01-24"},{"key":"6513_CR63","doi-asserted-by":"publisher","unstructured":"Zhang T, Zhang Y, Sun X, Sun H, Yan M, Yang X, Fu K (2020) Comparison network for one-shot conditional object detection. arXiv. arXiv:1904.02317 [cs]. https:\/\/doi.org\/10.48550\/arXiv.1904.02317. http:\/\/arxiv.org\/abs\/1904.02317. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.1904.02317"},{"key":"6513_CR64","doi-asserted-by":"publisher","unstructured":"Gothai E, Bhatia S, Alabdali A, Sharma D, Kondamudi B, Dadheech P (2022) Design features of grocery product recognition using deep learning. 34(2):1231\u20131246. https:\/\/doi.org\/10.32604\/iasc.2022.026264. Publisher: Tech Science Press. Accessed 13 Mar 2024","DOI":"10.32604\/iasc.2022.026264"},{"key":"6513_CR65","doi-asserted-by":"publisher","unstructured":"Wu X, Sahoo D, Hoi S (2020) Meta-RCNN: meta learning for few-shot object detection. In: Proceedings of the 28th ACM international conference on multimedia. MM \u201920, pp 1679\u20131687. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/3394171.3413832. Accessed 24 Jan 2023","DOI":"10.1145\/3394171.3413832"},{"key":"6513_CR66","doi-asserted-by":"publisher","unstructured":"Zhang G, Luo Z, Cui K, Lu S (2021) Meta-DETR: Image-level few-shot object detection with inter-class correlation exploitation. arXiv. arXiv:2103.11731 [cs]. https:\/\/doi.org\/10.48550\/arXiv.2103.11731. http:\/\/arxiv.org\/abs\/2103.11731. Accessed 24 Jan 2023","DOI":"10.48550\/arXiv.2103.11731"},{"key":"6513_CR67","doi-asserted-by":"publisher","unstructured":"Han G, Huang S, Ma J, He Y, Chang S-F (2022) Meta faster R-CNN: towards accurate few-shot object detection with attentive feature alignment. Proceedings of the AAAI conference on artificial intelligence vol 36(1), pp 780\u2013789. https:\/\/doi.org\/10.1609\/aaai.v36i1.19959. Number: 1. Accessed 28 Apr 2023","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"6513_CR68","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. arXiv. arXiv:2005.12872 [cs]. http:\/\/arxiv.org\/abs\/2005.12872. Accessed 23 Jan 2023","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"6513_CR69","unstructured":"Li X, Zhang L, Chen YP, Tai Y-W, Tang C-K (2020) One-shot object detection without fine-tuning. arXiv. arXiv:2005.03819 [cs, eess]. http:\/\/arxiv.org\/abs\/2005.03819. Accessed 23 Jan 2023"},{"key":"6513_CR70","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. vol 8691, pp 346\u2013361. https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23 . arXiv:1406.4729 [cs]. http:\/\/arxiv.org\/abs\/1406.4729. Accessed 24 Feb 2024","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"6513_CR71","doi-asserted-by":"publisher","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path aggregation network for instance segmentation. arXiv. arXiv:1803.01534 [cs]. https:\/\/doi.org\/10.48550\/arXiv.1803.01534. http:\/\/arxiv.org\/abs\/1803.01534. Accessed 14 Feb 2024","DOI":"10.48550\/arXiv.1803.01534"},{"key":"6513_CR72","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2019) Distance-IoU loss: faster and better learning for bounding box regression. arXiv. arXiv:1911.08287 [cs]. http:\/\/arxiv.org\/abs\/1911.08287. Accessed 03 Nov 2023"},{"key":"6513_CR73","doi-asserted-by":"publisher","unstructured":"Li X, Lv C, Wang W, Li G, Yang L, Yang J (2022) Generalized focal loss: towards efficient representation learning for dense object detection. IEEE Trans Pattern Anal Mach Intell 1\u201314. https:\/\/doi.org\/10.1109\/TPAMI.2022.3180392. Accessed 03 Nov 2023","DOI":"10.1109\/TPAMI.2022.3180392"},{"key":"6513_CR74","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2020) Focal loss for dense object detection. IEEE Trans Pattern Anal Mach Intell 42(2):318\u2013327. https:\/\/doi.org\/10.1109\/TPAMI.2018.2858826. Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"6513_CR75","doi-asserted-by":"publisher","unstructured":"Sudre CH, Li W, Vercauteren T, Ourselin S, Cardoso MJ (2017) Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. vol. 10553, pp 240\u2013248. https:\/\/doi.org\/10.1007\/978-3-319-67558-9_28. http:\/\/arxiv.org\/abs\/1707.03237. Accessed 24 Jan 2025","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"6513_CR76","unstructured":"Wei X-S, Cui Q, Yang L, Wang P, Liu L (2019) RPC: A large-scale retail product checkout dataset. arXiv. arXiv:1901.07249 [cs]. http:\/\/arxiv.org\/abs\/1901.07249. Accessed 23 Jan 2023"},{"key":"6513_CR77","doi-asserted-by":"publisher","unstructured":"Fan Q, Zhuo W, Tang C-K, Tai Y-W (2020) Few-shot object detection with attention-rpn and multi-relation detector. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 4012\u20134021. https:\/\/doi.org\/10.1109\/CVPR42600.2020.00407. ISSN: 2575-7075","DOI":"10.1109\/CVPR42600.2020.00407"},{"key":"6513_CR78","doi-asserted-by":"publisher","unstructured":"Tonioni A, Di\u00a0Stefano L (2017) Product recognition in store shelves as a sub-graph isomorphism problem. In: Battiato S, Gallo G, Schettini R, Stanco F (eds) Image analysis and processing - ICIAP 2017. Lecture Notes in Computer Science. Springer, Cham, pp 682\u2013693. https:\/\/doi.org\/10.1007\/978-3-319-68560-1_61","DOI":"10.1007\/978-3-319-68560-1_61"},{"key":"6513_CR79","doi-asserted-by":"publisher","unstructured":"Hu T, Mettes P, Huang J-H, Snoek C (2019) SILCO: Show a few images, localize the common object. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 5066\u20135075. https:\/\/doi.org\/10.1109\/ICCV.2019.00517. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2019.00517"},{"key":"6513_CR80","doi-asserted-by":"publisher","unstructured":"Cai Z, Vasconcelos N (2018) Cascade R-CNN: Delving into high quality object detection. In: 2018 IEEE\/CVF Conference on computer vision and pattern recognition, pp 6154\u20136162. https:\/\/doi.org\/10.1109\/CVPR.2018.00644. ISSN: 2575-7075","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6513_CR81","doi-asserted-by":"publisher","unstructured":"Merler M, Galleguillos C, Belongie S (2007) Recognizing Groceries in situ using in vitro training data. In: 2007 IEEE Conference on computer vision and pattern recognition. IEEE, Minneapolis, MN, USA, pp 1\u20138. https:\/\/doi.org\/10.1109\/CVPR.2007.383486. http:\/\/ieeexplore.ieee.org\/document\/4270484\/. Accessed 17 Apr 2023","DOI":"10.1109\/CVPR.2007.383486"},{"key":"6513_CR82","doi-asserted-by":"publisher","unstructured":"Yan X, Chen Z, Xu A, Wang X, Liang X, Lin L (2019) Meta R-CNN: towards general solver for instance-level low-shot learning. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp 9576\u20139585. https:\/\/doi.org\/10.1109\/ICCV.2019.00967. ISSN: 2380-7504","DOI":"10.1109\/ICCV.2019.00967"},{"key":"6513_CR83","doi-asserted-by":"publisher","unstructured":"Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: 2018 IEEE\/CVF Conference on Computer\u00a0vision and pattern recognition, pp 8971\u20138980. https:\/\/doi.org\/10.1109\/CVPR.2018.00935. ISSN: 2575-7075","DOI":"10.1109\/CVPR.2018.00935"},{"key":"6513_CR84","doi-asserted-by":"publisher","unstructured":"Bertinetto L, Valmadre J, Henriques JF, Vedaldi A, Torr PHS (2016) Fully-convolutional siamese networks for object tracking. In: Hua G, J\u00e9gou H (eds) Computer Vision \u2013 ECCV 2016 Workshops. Lecture Notes in Computer Science. Springer, Cham, pp 850\u2013865. https:\/\/doi.org\/10.1007\/978-3-319-48881-3_56","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"6513_CR85","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A. Automatic differentiation in PyTorch"},{"key":"6513_CR86","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90. ISSN: 1063-6919","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06513-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06513-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06513-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T19:32:36Z","timestamp":1758310356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06513-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,1]]},"references-count":86,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["6513"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06513-2","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,1]]},"assertion":[{"value":"25 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":2,"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 competing financial interests or personal relationships that could have influenced the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"All authors consent to the publication of this work.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"609"}}