{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:21:22Z","timestamp":1740108082229,"version":"3.37.3"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T00:00:00Z","timestamp":1646870400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Center for Balance Architecture"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s00521-022-07089-5","type":"journal-article","created":{"date-parts":[[2022,3,10]],"date-time":"2022-03-10T14:03:07Z","timestamp":1646920987000},"page":"12017-12028","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RESC: REfine the SCore with adaptive transformer head for end-to-end object detection"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9779-4748","authenticated-orcid":false,"given":"Honglie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shouqian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,10]]},"reference":[{"issue":"1","key":"7089_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/BF01421486","volume":"14","author":"H Murase","year":"1995","unstructured":"Murase H, Nayar SK (1995) Visual learning and recognition of 3-d objects from appearance. Int J Comput Vis 14(1):5\u201324","journal-title":"Int J Comput Vis"},{"issue":"2","key":"7089_CR2","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1023\/A:1023052124951","volume":"53","author":"A Torralba","year":"2003","unstructured":"Torralba A (2003) Contextual priming for object detection. Int J Comput Vis 53(2):169\u2013191","journal-title":"Int J Comput Vis"},{"key":"7089_CR3","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"key":"7089_CR4","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) Cascade r-CNN: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"7089_CR5","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-CNN: towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst 28:91\u201399","journal-title":"Adv Neural Inf Process Syst"},{"key":"7089_CR6","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"7089_CR7","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"7089_CR8","unstructured":"Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"7089_CR9","first-page":"8577","volume":"33","author":"B Li","year":"2019","unstructured":"Li B, Liu Y, Wang X (2019) Gradient harmonized single-stage detector. Proc AAAI Confer Artif Intell 33:8577\u20138584","journal-title":"Proc AAAI Confer Artif Intell"},{"key":"7089_CR10","doi-asserted-by":"crossref","unstructured":"Bodla N, Singh B, Chellappa R, Davis LS (2017) Soft-NMS\u2014improving object detection with one line of code. In: Proceedings of the IEEE international conference on computer vision, pp 5561\u20135569","DOI":"10.1109\/ICCV.2017.593"},{"key":"7089_CR11","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Advances in neural information processing systems, pp 5998\u20136008"},{"key":"7089_CR12","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":"7089_CR13","doi-asserted-by":"crossref","unstructured":"Wang J, Song L, Li Z, Sun H, Sun J, Zheng N (2021) End-to-end object detection with fully convolutional network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 15849\u201315858","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"7089_CR14","unstructured":"Shao S, Zhao Z, Li B, Xiao T, Yu G, Zhang X, Sun J (2018) Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123"},{"key":"7089_CR15","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) Fcos: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"7089_CR16","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"7089_CR17","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"7089_CR18","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"7089_CR19","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"7089_CR20","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask r-CNN. In: Proceedings of the IEEE international conference on computer vision, pp 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"7089_CR21","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick R (2016) Training region-based object detectors with online hard example mining. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"7089_CR22","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li SZ (2020) Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9759\u20139768","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"7089_CR23","doi-asserted-by":"crossref","unstructured":"Stewart R, Andriluka M, Ng AY (2016) End-to-end people detection in crowded scenes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2325\u20132333","DOI":"10.1109\/CVPR.2016.255"},{"key":"7089_CR24","doi-asserted-by":"crossref","unstructured":"Sun P, Zhang R, Jiang Y, Kong T, Xu C, Zhan W, Tomizuka M, Li L, Yuan Z, Wang C, et al. (2021) Sparse r-CNN: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14454\u201314463","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"7089_CR25","doi-asserted-by":"crossref","unstructured":"Meng D, Chen X, Fan Z, Zeng G, Li H, Yuan Y, Sun L, Wang J (2021) Conditional detr for fast training convergence. arXiv preprint arXiv:2108.06152","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"7089_CR26","doi-asserted-by":"crossref","unstructured":"Gao P, Zheng M, Wang X, Dai J, Li H (2021) Fast convergence of detr with spatially modulated co-attention. arXiv preprint arXiv:2101.07448","DOI":"10.1109\/ICCV48922.2021.00360"},{"key":"7089_CR27","unstructured":"Sun P, Jiang Y, Xie E, Yuan Z, Wang C, Luo P (2020) Onenet: towards end-to-end one-stage object detection. arXiv preprint arXiv:2012.05780"},{"key":"7089_CR28","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 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"7089_CR29","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"7089_CR30","unstructured":"Fang Y, Liao B, Wang X, Fang J, Qi J, Wu R, Niu J, Liu W (2021) You only look at one sequence: rethinking transformer in vision through object detection. arXiv preprint arXiv:2106.00666"},{"key":"7089_CR31","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473"},{"key":"7089_CR32","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"7089_CR33","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159"},{"key":"7089_CR34","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y, Li Y, Zhang G, Hu H, Wei Y (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"7089_CR35","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"7089_CR36","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7089_CR37","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, pp 249\u2013256"},{"issue":"1","key":"7089_CR38","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"7089_CR39","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7089_CR40","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"7089_CR41","unstructured":"Fu C-Y, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: deconvolutional single shot detector. arXiv preprint arXiv:1701.06659"},{"key":"7089_CR42","doi-asserted-by":"crossref","unstructured":"Law H, Deng J (2018) Cornernet: detecting objects as paired keypoints. In: Proceedings of the European conference on computer vision (ECCV), pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"7089_CR43","doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S, Dai J (2019) Deformable convnets v2: more deformable, better results. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9308\u20139316","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07089-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07089-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07089-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T09:31:33Z","timestamp":1657877493000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07089-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,10]]},"references-count":43,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["7089"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07089-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2022,3,10]]},"assertion":[{"value":"16 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 March 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"}}]}}