{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T04:50:54Z","timestamp":1743396654012,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T00:00:00Z","timestamp":1619049600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T00:00:00Z","timestamp":1619049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2016YFC0802703"],"award-info":[{"award-number":["2016YFC0802703"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10489-021-02373-8","type":"journal-article","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T11:08:27Z","timestamp":1619089707000},"page":"9066-9080","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Coordinate-based anchor-free module for object detection"],"prefix":"10.1007","volume":"51","author":[{"given":"Zhiyong","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianbing","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7748-8591","authenticated-orcid":false,"given":"Zhongcai","family":"Pei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,4,22]]},"reference":[{"key":"2373_CR1","doi-asserted-by":"crossref","unstructured":"Bai Y, Zhang Y, Ding M, Ghanem B (2018) Finding tiny faces in the wild with generative adversarial network. In: CVPR","DOI":"10.1109\/CVPR.2018.00010"},{"key":"2373_CR2","doi-asserted-by":"crossref","unstructured":"Bell S, Lawrence Zitnick C, Bala K, Girshick R (2016) Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2874\u20132883","DOI":"10.1109\/CVPR.2016.314"},{"key":"2373_CR3","doi-asserted-by":"crossref","unstructured":"Bhagavatula C, Zhu C, Luu K, Savvides M (2017) Faster than real-time facial alignment: a 3d spatial transformer network approach in unconstrained poses. In: The IEEE international conference on computer vision (ICCV). 1","DOI":"10.1109\/ICCV.2017.429"},{"key":"2373_CR4","unstructured":"Bochkovskiy A, Wang CY, Liao HYM (2020) Yolov4: optimal speed and accuracy of object detection. arXiv:2004.10934. 11"},{"key":"2373_CR5","unstructured":"Cai Z, Vasconcelos N Cascade r-cnn: delving into high quality object detection. arXiv:1712.00726. 8"},{"key":"2373_CR6","doi-asserted-by":"crossref","unstructured":"Cai Z, Fan Q, Feris RS, Vasconcelos N (2016) A unified multi-scale deep convolutional neural network for fast object detection. In: European conference on computer vision. Springer, pp 354\u2013370","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"2373_CR7","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:2005.12872v3 (ECCV)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2373_CR8","unstructured":"Dai J, Li Y, He K, Sun J (2016) R-fcn: object detection via region-based fully convolutional networks. In: Advances in neural information processing systems, pp 379\u2013387"},{"key":"2373_CR9","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, FeiFei L (2009) Imagenet: a large-scale hierarchical image database. In: CVPR 2009. IEEE conference on computer vision and pattern recognition. 5. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2373_CR10","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) CenterNet: keypoint triplets for object detection. In: 2019 IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2373_CR11","doi-asserted-by":"crossref","unstructured":"Duan K, Xie L, Qi H, Bai S, Huang Q, Tian Q (2020) Corner proposal network for anchor-free, two-stage object detection. arXiv:2007.13816v1 (ECCV)","DOI":"10.1007\/978-3-030-58580-8_24"},{"key":"2373_CR12","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A The PASCAL visual object classes challenge 2007 (VOC2007) results. Available: http:\/\/www.pascalnetwork.org\/challenges\/VOC\/voc2007\/workshop\/index.html"},{"key":"2373_CR13","unstructured":"Fu C -Y, Liu W, Ranga A, Tyagi A, Berg AC (2017) Dssd: deconvolutional single shot detector. arXiv:1701.06659. 2, 3, 8"},{"key":"2373_CR14","doi-asserted-by":"crossref","unstructured":"Gidaris S, Komodakis N (2015) Object detection via a multi-region and semantic segmentation-aware cnn model. In: Proceedings of the IEEE international conference on computer vision, pp 1134\u20131142","DOI":"10.1109\/ICCV.2015.135"},{"key":"2373_CR15","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2373_CR16","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"2373_CR17","doi-asserted-by":"crossref","unstructured":"Hariharan B, Arbelaez P, Girshick R, Malik J (2015) Hypercolumns for object segmentation and fine-grained localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2, pp 447\u2013456","DOI":"10.1109\/CVPR.2015.7298642"},{"issue":"9","key":"2373_CR18","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans Pattern Anal Mach Intell 37(9):1904\u20131916","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2373_CR19","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar 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":"2373_CR20","doi-asserted-by":"crossref","unstructured":"Huang Y, Dai Q, Lu Y (2019) Decoupling localization and classification in single shot temporal action detection. In: IEEE international conference on multimedia and expo (ICME), p 2019","DOI":"10.1109\/ICME.2019.00224"},{"key":"2373_CR21","doi-asserted-by":"publisher","unstructured":"Kong T, Sun F, Liu H, Jiang Y, Shi J (2020) FoveaBox: Beyound Anchor-Based Object Detection, in IEEE Transactions on Image Processing, vol. 29, pp. 7389\u20137398, 2020, https:\/\/doi.org\/10.1109\/TIP.2020.3002345.","DOI":"10.1109\/TIP.2020.3002345."},{"key":"2373_CR22","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, pp 734\u2013750","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"2373_CR23","unstructured":"Li Z, Peng C, Yu G, Zhang X, Deng Y, Sun J Detnet: a backbone network for object detection. arXiv:1804.06215. 2"},{"key":"2373_CR24","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-aware trident networks for object detection. arXiv:1901.01892","DOI":"10.1109\/ICCV.2019.00615"},{"key":"2373_CR25","unstructured":"Liang X, Wang T, Yang L, Xing E Cirl: controllable imitative reinforcement learning for vision-based self-driving. arXiv:1807.03776. 1"},{"key":"2373_CR26","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision. 1, 2, 6. Springer, Cham, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2373_CR27","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Shou Z (2017) Single shot temporal action detection. In: ACM MM. ACM","DOI":"10.1145\/3123266.3123343"},{"key":"2373_CR28","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Dollar P, Girshick RB, He K, Hariharan B, Belongie SJ (2017) Feature pyramid networks for object detection. In: CVPR. 2, 5, 8, p 3","DOI":"10.1109\/CVPR.2017.106"},{"key":"2373_CR29","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Dollar P (2018) Focal loss for dense object detection. IEEE transactions on pattern analysis and machine intelligence. 1, 2, 3, 4, 5, 8"},{"key":"2373_CR30","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, 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":"2373_CR31","doi-asserted-by":"publisher","unstructured":"Lu X, Li B, Yue Y, Li Q, Yan J (2019) Grid R-CNN, 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 7355-7364, https:\/\/doi.org\/10.1109\/CVPR.2019.00754","DOI":"10.1109\/CVPR.2019.00754"},{"key":"2373_CR32","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":"2373_CR33","unstructured":"Redmon J, Farhadi A YOLOv3: an incremental improvement. Computer Vision and Pattern Recognition"},{"key":"2373_CR34","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":"2373_CR35","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, pp 91\u201399"},{"key":"2373_CR36","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, et al. (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115:211\u2013252","journal-title":"Int J Comput Vis"},{"key":"2373_CR37","doi-asserted-by":"crossref","unstructured":"Schroff F, Kalenichenko D, Philbin J (2015) FaceNet: a unified embedding for face recognition and clustering. In: 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 815\u2013823","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"2373_CR38","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2014) Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR. 2"},{"key":"2373_CR39","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A (2016) Contextual priming and feedback for faster r-cnn. In: European conference on computer vision, pp 330\u2013348","DOI":"10.1007\/978-3-319-46448-0_20"},{"issue":"4","key":"2373_CR40","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.physa.2015.12.041","volume":"447","author":"X Song","year":"2016","unstructured":"Song X, Ma L, et al. (2016) Selfishness- and Selflessness-based Models of Pedestrian Room Evacuation. Phys A-Stat Mech Appl 447(4):455\u2013466","journal-title":"Phys A-Stat Mech Appl"},{"issue":"11","key":"2373_CR41","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1016\/j.physa.2018.06.045","volume":"509","author":"X Song","year":"2018","unstructured":"Song X, Han D, et al. (2018) A data-driven neural network approach to simulate pedestrian movement. Phys A-Stat Mech Appl 509(11):827\u2013844","journal-title":"Phys A-Stat Mech Appl"},{"key":"2373_CR42","doi-asserted-by":"publisher","unstructured":"Song X, Chen K, et al. (2020) Pedestrian trajectory prediction based on deep convolutional LSTM network. IEEE Trans Intell Transp Syst 3. https:\/\/doi.org\/10.1109\/TITS.2020.2981118","DOI":"10.1109\/TITS.2020.2981118"},{"key":"2373_CR43","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object detection. arXiv:1911.09070v7 (CVPR)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"2373_CR44","doi-asserted-by":"crossref","unstructured":"Tang Z, Yang J, Pei Z, Song X, Ge B (2019) Multi-process training GAN for identity-preserving face synthesis. IEEE Access 7","DOI":"10.1109\/ACCESS.2019.2930203"},{"key":"2373_CR45","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith L, Petersson L (2017) Denet: scalable realtime object detection with directed sparse sampling. In: Proceedings of the IEEE international conference on computer vision, pp 428\u2013436","DOI":"10.1109\/ICCV.2017.54"},{"key":"2373_CR46","unstructured":"Wang J, Yuan Y, Yu G, Jian S Sface: an efficient network for face detection in large scale variations. arXiv:1804.06559. 3"},{"key":"2373_CR47","doi-asserted-by":"crossref","unstructured":"Wang S, Gong Y, Xing J, Huang L, Huang C, Hu W (2019) RDSNet: a new deep architecture for reciprocal object detection and instance segmentation. arXiv:1912.05070. 13 (AAAI)","DOI":"10.1609\/aaai.v34i07.6902"},{"key":"2373_CR48","doi-asserted-by":"crossref","unstructured":"Yang Z, Xu Y, Xue H, Zhang Z, Urtasun R, Wang L, Lin S, Hu H (2020) Dense RepPoints: representing visual objects with dense point sets. arXiv:1912.11473v3","DOI":"10.1007\/978-3-030-58589-1_14"},{"key":"2373_CR49","doi-asserted-by":"crossref","unstructured":"Yao L, Xu H, Zhang W, Liang X, Li Z (2020) SM-NAS: structural-to-modular neural architecture search for object detection. In: Proceedings of the AAAI conference on artificial intelligence (AAAI). 13","DOI":"10.1609\/aaai.v34i07.6958"},{"key":"2373_CR50","doi-asserted-by":"crossref","unstructured":"Zeng X, Ouyang W, Yang B, Yan J, Wang X (2016) Gated bi-directional cnn for object detection. In: European conference on computer vision. Springer, pp 354\u2013369","DOI":"10.1007\/978-3-319-46478-7_22"},{"key":"2373_CR51","doi-asserted-by":"crossref","unstructured":"Zhao Q, Sheng T, Wang Y, Tang Z, Chen Y, Cai L, Ling H (2019) M2det: a single-shot object detector based on multi-level feature pyramid network. In: Thirty-third AAAI conference on artificial intelligence. 2","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"2373_CR52","doi-asserted-by":"crossref","unstructured":"Zheng Y, Pal DK, Savvides M (2018) Ring loss: convex feature normalization for face recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 1, pp 5089\u20135097","DOI":"10.1109\/CVPR.2018.00534"},{"key":"2373_CR53","unstructured":"Zhong Z, Sun L, Huo Q An anchor-free region proposal network for faster r-cnn based text detection approaches. arXiv:1804.09003. 3"},{"key":"2373_CR54","doi-asserted-by":"crossref","unstructured":"Zhu Y, Zhao C, Wang J, Zhao X, Wu Y, Lu H et al (2017) Couplenet: coupling global structure with local parts for object detection. In: Proceedings of international conference on computer vision (ICCV). 8, vol 2","DOI":"10.1109\/ICCV.2017.444"},{"key":"2373_CR55","doi-asserted-by":"crossref","unstructured":"Zhu C, He Y, Savvides M (2019) Feature selective anchor-free module for single-shot object detection. In: Conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00093"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02373-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02373-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02373-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T05:15:12Z","timestamp":1636434912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02373-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,22]]},"references-count":55,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["2373"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02373-8","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2021,4,22]]},"assertion":[{"value":"22 March 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Author Zhiyong Tang declares that he has no conflict of interest. Author Jianbing Yang declares that he has no conflict of interest. Author Zhongcai Pei declares that he has no conflict of interest. Author Xiao Song declares that he has no conflict of interest. Author Pei Pei declares that he has no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of interest"}}]}}