{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T16:32:52Z","timestamp":1772641972859,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,10,19]],"date-time":"2017-10-19T00:00:00Z","timestamp":1508371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123356","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"1023-1031","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Pedestrian Detection via Bi-directional Multi-scale Analysis"],"prefix":"10.1145","author":[{"given":"Zhenyu","family":"Duan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinpeng","family":"Lan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Ni","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lixue","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"234","article-title":"Frobnication","volume":"12","author":"Alpher A","year":"2002","journal-title":"Journal of Foo"},{"key":"e_1_3_2_1_2_1","first-page":"234","article-title":"Frobnication revisited","volume":"13","author":"Alpher A","year":"2003","journal-title":"Journal of Foo"},{"key":"e_1_3_2_1_3_1","first-page":"234","article-title":"Can a machine frobnicate","volume":"14","author":"Alpher A","year":"2004","journal-title":"Journal of Foo"},{"key":"e_1_3_2_1_4_1","unstructured":"Authors. 2014. The frobnicatable foo filter. (2014). Face and Gesture submission ID 324. Supplied as additional material fg324.pdf Authors. 2014. The frobnicatable foo filter. (2014). Face and Gesture submission ID 324. Supplied as additional material fg324.pdf"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Sean Bell C Lawrence Zitnick Kavita Bala and Ross Girshick. 2016. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2874--2883. Sean Bell C Lawrence Zitnick Kavita Bala and Ross Girshick. 2016. Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2874--2883.","DOI":"10.1109\/CVPR.2016.314"},{"key":"e_1_3_2_1_6_1","volume-title":"A unified multi-scale deep convolutional neural network for fast object detection European Conference on Computer Vision","author":"Cai Zhaowei"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.155"},{"key":"e_1_3_2_1_9_1","volume-title":"Sergio Guadarrama, Marcus Rohrbach, Subhashini Venugopalan, Kate Saenko, and Trevor Darrell.","author":"Donahue Jeffrey","year":"2015"},{"key":"e_1_3_2_1_10_1","volume-title":"Davis","author":"Du Xianzhi","year":"2016"},{"key":"e_1_3_2_1_11_1","volume-title":"A Mobile Vision System for Robust Multi-Person Tracking IEEE Conference on Computer Vision and Pattern Recognition (CVPR'08)","author":"Ess A."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Yunchao Gong Liwei Wang Ruiqi Guo and Svetlana Lazebnik. 2014. Multi-scale Orderless Pooling of Deep Convolutional Activation Features. (2014) 392--407. Yunchao Gong Liwei Wang Ruiqi Guo and Svetlana Lazebnik. 2014. Multi-scale Orderless Pooling of Deep Convolutional Activation Features. (2014) 392--407.","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"e_1_3_2_1_17_1","first-page":"753","article-title":"Bidirectional LSTM networks for improved phoneme classification and recognition","volume":"2005","author":"Graves Alex","year":"2005","journal-title":"Artificial Neural Networks: Formal Models and Their Applications--ICANN"},{"key":"e_1_3_2_1_18_1","volume-title":"2013 IEEE Workshop on. IEEE, 273--278","author":"Graves Alex","year":"2013"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299034"},{"key":"e_1_3_2_1_20_1","unstructured":"David Jacobs. 2014. Locally Scale-Invariant Convolutional Neural Networks. (2014) 1--11. {arxiv}arXiv:1412.5104v1 David Jacobs. 2014. Locally Scale-Invariant Convolutional Neural Networks. (2014) 1--11. {arxiv}arXiv:1412.5104v1"},{"key":"e_1_3_2_1_21_1","volume-title":"Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv preprint arXiv:1408.5093","author":"Jia Yangqing","year":"2014"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Tao Kong Anbang Yao Yurong Chen and Fuchun Sun. 2016. HyperNet: towards accurate region proposal generation and joint object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 845--853. Tao Kong Anbang Yao Yurong Chen and Fuchun Sun. 2016. HyperNet: towards accurate region proposal generation and joint object detection Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 845--853.","DOI":"10.1109\/CVPR.2016.98"},{"key":"e_1_3_2_1_23_1","volume-title":"Scale-aware fast R-CNN for pedestrian detection. arXiv preprint arXiv:1510.08160","author":"Li Jianan","year":"2015"},{"key":"e_1_3_2_1_24_1","volume-title":"SSD: Single Shot MultiBox Detector.","author":"Liu Wei","year":"2016"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.120"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.190"},{"key":"e_1_3_2_1_27_1","unstructured":"Woonhyun Nam Piotr Doll\u00e1r and Joon Hee Han. 2014. Local decorrelation for improved pedestrian detection Advances in Neural Information Processing Systems. 424--432. Woonhyun Nam Piotr Doll\u00e1r and Joon Hee Han. 2014. Local decorrelation for improved pedestrian detection Advances in Neural Information Processing Systems. 424--432."},{"key":"e_1_3_2_1_28_1","volume-title":"2012 IEEE Conference on. IEEE, 3258--3265","author":"Ouyang Wanli","year":"2012"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.414"},{"key":"e_1_3_2_1_30_1","volume-title":"Strengthening the effectiveness of pedestrian detection with spatially pooled features European Conference on Computer Vision","author":"Paisitkriangkrai Sakrapee"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Pingbo Pan Zhongwen Xu Yi Yang Fei Wu and Yueting Zhuang. 2016. Hierarchical recurrent neural encoder for video representation with application to captioning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1029--1038. Pingbo Pan Zhongwen Xu Yi Yang Fei Wu and Yueting Zhuang. 2016. Hierarchical recurrent neural encoder for video representation with application to captioning Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1029--1038.","DOI":"10.1109\/CVPR.2016.117"},{"key":"e_1_3_2_1_32_1","unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks Advances in neural information processing systems. 91--99. Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks Advances in neural information processing systems. 91--99."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_34_1","volume-title":"Parsing natural scenes and natural language with recursive neural networks Proceedings of the 28th international conference on machine learning (ICML-11). 129--136","author":"Socher Richard"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.221"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yonglong Tian Ping Luo Xiaogang Wang and Xiaoou Tang. 2015 b. Pedestrian detection aided by deep learning semantic tasks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5079--5087. Yonglong Tian Ping Luo Xiaogang Wang and Xiaoou Tang. 2015 b. Pedestrian detection aided by deep learning semantic tasks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5079--5087.","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"e_1_3_2_1_38_1","unstructured":"Kuiyuan Yang. 2014. Scale-Invariant Convolutional Neural Network. (2014). showeprint{arxiv}arXiv:1411.6369v1 Kuiyuan Yang. 2014. Scale-Invariant Convolutional Neural Network. (2014). showeprint{arxiv}arXiv:1411.6369v1"},{"key":"e_1_3_2_1_39_1","volume-title":"Comparative Study of CNN and RNN for Natural Language Processing. arXiv preprint arXiv:1702.01923","author":"Yin Wenpeng","year":"2017"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_22"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Liliang Zhang Liang Lin Xiaodan Liang and Kaiming He. 2016. Is Faster R-CNN Doing Well for Pedestrian Detection? Liliang Zhang Liang Lin Xiaodan Liang and Kaiming He. 2016. Is Faster R-CNN Doing Well for Pedestrian Detection?","DOI":"10.1007\/978-3-319-46475-6_28"},{"key":"e_1_3_2_1_42_1","volume-title":"2015 IEEE Conference on. IEEE, 1751--1760","author":"Zhang Shanshan","year":"2015"}],"event":{"name":"MM '17: ACM Multimedia Conference","location":"Mountain View California USA","acronym":"MM '17","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123356","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T16:40:02Z","timestamp":1750956002000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":42,"alternative-id":["10.1145\/3123266.3123356","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123356","relation":{},"subject":[],"published":{"date-parts":[[2017,10,19]]},"assertion":[{"value":"2017-10-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}