{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T06:53:23Z","timestamp":1773212003701,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T00:00:00Z","timestamp":1629763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61771458"],"award-info":[{"award-number":["61771458"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"DOI":"10.1145\/3460426.3463628","type":"proceedings-article","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T22:50:29Z","timestamp":1630536629000},"page":"64-72","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["Dense Scale Network for Crowd Counting"],"prefix":"10.1145","author":[{"given":"Feng","family":"Dai","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications & Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Yike","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"given":"Qiang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2021,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00381"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2967300"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics. 315--323","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot , Antoine Bordes , and Yoshua Bengio . 2011 . Deep sparse rectifier neural networks . In Proceedings of the fourteenth international conference on artificial intelligence and statistics. 315--323 . Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics. 315--323."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350881"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.329"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 6126--6135","author":"Jiang X.","unstructured":"X. Jiang , Z. Xiao , B. Zhang , X. Zhen , X. Cao , D. Doermann , and L. Shao . 2019. Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks . In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 6126--6135 . X. Jiang, Z. Xiao, B. Zhang, X. Zhen, X. Cao, D. Doermann, and L. Shao. 2019. Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 6126--6135."},{"key":"e_1_3_2_1_12_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint:1412.6980 (2014)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of Conference on neural information processing systems. 1324--1332","author":"Lempitsky Victor","year":"2010","unstructured":"Victor Lempitsky and Andrew Zisserman . 2010 . Learning to count objects in images . In Proceedings of Conference on neural information processing systems. 1324--1332 . Victor Lempitsky and Andrew Zisserman. 2010. Learning to count objects in images. In Proceedings of Conference on neural information processing systems. 1324--1332."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00186"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 3220--3229","author":"Liu N.","unstructured":"N. Liu , Y. Long , C. Zou , Q. Niu , L. Pan , and H. Wu . 2019. ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding . In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 3220--3229 . N. Liu, Y. Long, C. Zou, Q. Niu, L. Pan, and H. Wu. 2019. ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 3220--3229."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"e_1_3_2_1_19_1","volume-title":"Hybrid Graph Neural Networks for Crowd Counting. In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI) .","author":"Luo Ao","year":"2020","unstructured":"Ao Luo , Fan Yang , Xin Li , Dong Nie , Zhicheng Jiao , Shangchen Zhou , and Hong. Cheng. 2020 . Hybrid Graph Neural Networks for Crowd Counting. In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI) . Ao Luo, Fan Yang, Xin Li, Dong Nie, Zhicheng Jiao, Shangchen Zhou, and Hong. Cheng. 2020. Hybrid Graph Neural Networks for Crowd Counting. In Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI) ."},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 6141--6150","author":"Ma Z.","unstructured":"Z. Ma , X. Wei , X. Hong , and Y. Gong . 2019. Bayesian Loss for Crowd Count Estimation With Point Supervision . In Proceedings of the IEEE International Conference on Computer Vision. 6141--6150 . Z. Ma, X. Wei, X. Hong, and Y. Gong. 2019. Bayesian Loss for Crowd Count Estimation With Point Supervision. In Proceedings of the IEEE International Conference on Computer Vision. 6141--6150."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.372"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"e_1_3_2_1_24_1","volume-title":"In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA). 423--431","author":"Lopez-Sastre Ricardo Roberto","year":"2015","unstructured":"Roberto Lopez-Sastre Ricardo Guerrero-Gomez-Olmedo, Beatriz Torre-Jimenez and Daniel Onoro-Rubio . 2015 . Extremely overlapping vehicle counting . In In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA). 423--431 . Roberto Lopez-Sastre Ricardo Guerrero-Gomez-Olmedo, Beatriz Torre-Jimenez and Daniel Onoro-Rubio. 2015. Extremely overlapping vehicle counting. In In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA). 423--431."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126526"},{"key":"e_1_3_2_1_26_1","volume-title":"Digital Image Computing: Techniques and Applications","author":"Ryan David","unstructured":"David Ryan , Simon Denman , Clinton Fookes , and Sridha Sridharan . 2009. Crowd counting using multiple local features . In Digital Image Computing: Techniques and Applications . IEEE , 81--88. David Ryan, Simon Denman, Clinton Fookes, and Sridha Sridharan. 2009. Crowd counting using multiple local features. In Digital Image Computing: Techniques and Applications. IEEE, 81--88."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.429"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532551"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 7271--7280","author":"Shi M.","unstructured":"M. Shi , Z. Yang , C. Xu , and Q. Chen . 2019. Revisiting Perspective Information for Efficient Crowd Counting . In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 7271--7280 . M. Shi, Z. Yang, C. Xu, and Q. Chen. 2019. Revisiting Perspective Information for Efficient Crowd Counting. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 7271--7280."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00564"},{"key":"e_1_3_2_1_31_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint:1409.1556 (2014)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.206"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350914"},{"key":"e_1_3_2_1_35_1","volume":"201","author":"Tian Y.","unstructured":"Y. Tian , Y. Lei , J. Zhang , and J. Z. Wang. 201 9. PaDNet: Pan-Density Crowd Counting. IEEE Transactions on Image Processing (2019). Y. Tian, Y. Lei, J. Zhang, and J. Z. Wang. 2019. PaDNet: Pan-Density Crowd Counting. IEEE Transactions on Image Processing (2019).","journal-title":"J. Z. Wang."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_41"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995698"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. IEEE, 90--97","author":"Wu Bo","year":"2005","unstructured":"Bo Wu and Ram Nevatia . 2005 . Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors . In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 90--97 . Bo Wu and Ram Nevatia. 2005. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In Proceedings of the IEEE International Conference on Computer Vision. IEEE, 90--97."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 952--961","author":"Yan Z.","unstructured":"Z. Yan , Y. Yuan , W. Zuo , X. Tan , Y. Wang , S. Wen , and E. Ding . 2019. Perspective-Guided Convolution Networks for Crowd Counting . In Proceedings of the IEEE International Conference on Computer Vision. 952--961 . Z. Yan, Y. Yuan, W. Zuo, X. Tan, Y. Wang, S. Wen, and E. Ding. 2019. Perspective-Guided Convolution Networks for Crowd Counting. In Proceedings of the IEEE International Conference on Computer Vision. 952--961."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00127"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"}],"event":{"name":"ICMR '21: International Conference on Multimedia Retrieval","location":"Taipei Taiwan","acronym":"ICMR '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2021 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463628","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3460426.3463628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:17:03Z","timestamp":1750191423000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3460426.3463628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,24]]},"references-count":43,"alternative-id":["10.1145\/3460426.3463628","10.1145\/3460426"],"URL":"https:\/\/doi.org\/10.1145\/3460426.3463628","relation":{},"subject":[],"published":{"date-parts":[[2021,8,24]]},"assertion":[{"value":"2021-09-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}