{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:35:27Z","timestamp":1750221327601,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"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"}],"funder":[{"name":"the 973 basic research program of China","award":["Grant No. 2014CB349303"],"award-info":[{"award-number":["Grant No. 2014CB349303"]}]},{"name":"the Strategic Priority Research Program of the CAS","award":["Grant No. XDB02070003"],"award-info":[{"award-number":["Grant No. XDB02070003"]}]},{"name":"the CAS External cooperation key project"},{"name":"MOE Tier-I","award":["R-263-000-C21-112"],"award-info":[{"award-number":["R-263-000-C21-112"]}]},{"name":"the Natural Science Foundation of China","award":["Grant No. U1636218 61472421"],"award-info":[{"award-number":["Grant No. U1636218 61472421"]}]},{"name":"NUS startup","award":["R-263-000-C08-133"],"award-info":[{"award-number":["R-263-000-C08-133"]}]},{"name":"IDS","award":["R-263-000-C67-646"],"award-info":[{"award-number":["R-263-000-C67-646"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,10,19]]},"DOI":"10.1145\/3123266.3123449","type":"proceedings-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T13:04:26Z","timestamp":1508504666000},"page":"226-234","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Robust Visual Object Tracking with Top-down Reasoning"],"prefix":"10.1145","author":[{"given":"Mengdan","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2017,10,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"M. Andriluka S. Roth and B. Schiele. 2008. People-tracking-by-detection and people-detection-by-tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 1--8.  M. Andriluka S. Roth and B. Schiele. 2008. People-tracking-by-detection and people-detection-by-tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 1--8.","DOI":"10.1109\/CVPR.2008.4587583"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"L. Bertinetto J. Valmadre J.F. Henriques A. Vedaldi and P.HS. Torr. 2016. Fully-convolutional siamese networks for object tracking Proc. of European Conference on Computer Vision. 850--865.  L. Bertinetto J. Valmadre J.F. Henriques A. Vedaldi and P.HS. Torr. 2016. Fully-convolutional siamese networks for object tracking Proc. of European Conference on Computer Vision. 850--865.","DOI":"10.1007\/978-3-319-48881-3_56"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"D.S. Bolme J.R. Beveridge B.A. Draper and Y. Lui. 2010. Visual object tracking using adaptive correlation filters Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 2544--2550.  D.S. Bolme J.R. Beveridge B.A. Draper and Y. Lui. 2010. Visual object tracking using adaptive correlation filters Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 2544--2550.","DOI":"10.1109\/CVPR.2010.5539960"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2669880"},{"volume-title":"Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 1449--1458","author":"Cui Z.","key":"e_1_3_2_1_5_1"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"volume-title":"ECO: Efficient Convolution Operators for Tracking. arXiv preprint arXiv:1611.09224","year":"2016","author":"Danelljan M.","key":"e_1_3_2_1_7_1"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"M. Danelljan G. H\"ager F.S. Khan and M. Felsberg. 2014. Accurate scale estimation for robust visual tracking Proc. of British Machine Vision Conference.  M. Danelljan G. H\"ager F.S. Khan and M. Felsberg. 2014. Accurate scale estimation for robust visual tracking Proc. of British Machine Vision Conference.","DOI":"10.5244\/C.28.65"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.490"},{"volume-title":"Proc. of IEEE Conference on Computer Vision and Pattern Recognition.","author":"Danelljan M.","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.143"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"M. Danelljan A. Robinson F.S. Khan and M. Felsberg. 2016. Beyond correlation filters: Learning continuous convolution operators for visual tracking Proc. of European Conference on Computer Vision. 472--488.  M. Danelljan A. Robinson F.S. Khan and M. Felsberg. 2016. Beyond correlation filters: Learning continuous convolution operators for visual tracking Proc. of European Conference on Computer Vision. 472--488.","DOI":"10.1007\/978-3-319-46454-1_29"},{"volume-title":"Imagenet: A large-scale hierarchical image database Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 248--255.","year":"2009","author":"Deng J.","key":"e_1_3_2_1_13_1"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2012.64"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2656628"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126251"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345390"},{"volume-title":"Proc. of International Conference on Machine Learning. 597--606","author":"Hong S.","key":"e_1_3_2_1_19_1"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Z. Hong Z. Chen C. Wang X. Mei D. Prokhorov and D. Tao. 2015 a. Multi-store tracker (MUSTer): A cognitive psychology inspired approach to object tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 749--758.  Z. Hong Z. Chen C. Wang X. Mei D. Prokhorov and D. Tao. 2015 a. Multi-store tracker (MUSTer): A cognitive psychology inspired approach to object tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 749--758.","DOI":"10.1109\/CVPR.2015.7298675"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Z. Kalal J. Matas and K. Mikolajczyk. 2010. PN learning: Bootstrapping binary classifiers by structural constraints Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 49--56.  Z. Kalal J. Matas and K. Mikolajczyk. 2010. PN learning: Bootstrapping binary classifiers by structural constraints Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 49--56.","DOI":"10.1109\/CVPR.2010.5540231"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.381"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Y. Li and J. Zhu. 2012. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration Proc. of European Conference on Computer Vision Workshops. 254--265.  Y. Li and J. Zhu. 2012. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration Proc. of European Conference on Computer Vision Workshops. 254--265.","DOI":"10.1007\/978-3-319-16181-5_18"},{"key":"e_1_3_2_1_26_1","unstructured":"L. Liu J. Xing H. Ai and X. Ruan. 2012. Hand posture recognition using finger geometric feature Proc. of IEEE International Conference on Pattern Recognition. 565--568.  L. Liu J. Xing H. Ai and X. Ruan. 2012. Hand posture recognition using finger geometric feature Proc. of IEEE International Conference on Pattern Recognition. 565--568."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.352"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"H. Nam and B. Han. 2016. Learning multi-domain convolutional neural networks for visual tracking. 4293--4302.  H. Nam and B. Han. 2016. Learning multi-domain convolutional neural networks for visual tracking. 4293--4302.","DOI":"10.1109\/CVPR.2016.465"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"J. Ning J. Yang S. Jiang L. Zhang and M.H. Yang. 2016. Object tracking via dual linear structured SVM and explicit feature map Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 4266--4274.  J. Ning J. Yang S. Jiang L. Zhang and M.H. Yang. 2016. Object tracking via dual linear structured SVM and explicit feature map Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 4266--4274.","DOI":"10.1109\/CVPR.2016.462"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Y. Qi S. Zhang L. Qin H. Yao Q. Huang J. Lim and M.-H. Yang. 2016. Hedged deep tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 4303--4311.  Y. Qi S. Zhang L. Qin H. Yao Q. Huang J. Lim and M.-H. Yang. 2016. Hedged deep tracking Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 4303--4311.","DOI":"10.1109\/CVPR.2016.466"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"volume-title":"Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 1--9.","author":"Szegedy C.","key":"e_1_3_2_1_32_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.348"},{"volume-title":"Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 1420--1429","author":"Tao R.","key":"e_1_3_2_1_34_1"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2019809"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.445"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.357"},{"volume-title":"Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach. arXiv preprint arXiv:1703.08448","year":"2017","author":"Wei Yunchao","key":"e_1_3_2_1_38_1"},{"volume-title":"HCP: A flexible CNN framework for multi-label image classification","year":"2016","author":"Wei Yunchao","key":"e_1_3_2_1_39_1"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.312"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388226"},{"volume-title":"Proc. of European Conference on Computer Vision. 188--203","author":"Zhang J.","key":"e_1_3_2_1_42_1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"M. Zhang J. Xing J. Gao and W. Hu. 2015. Robust visual tracking using joint scale-spatial correlation filters Proc. of IEEE International Conference on Image Processing. 1468--1472.  M. Zhang J. Xing J. Gao and W. Hu. 2015. Robust visual tracking using joint scale-spatial correlation filters Proc. of IEEE International Conference on Image Processing. 1468--1472.","DOI":"10.1109\/ICIP.2015.7351044"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"B. Zhou A. Khosla A. Lapedriza A. Oliva and A. Torralba. 2016. Learning deep features for discriminative localization Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 2921--2929.  B. Zhou A. Khosla A. Lapedriza A. Oliva and A. Torralba. 2016. Learning deep features for discriminative localization Proc. of IEEE Conference on Computer Vision and Pattern Recognition. 2921--2929.","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '17: ACM Multimedia Conference","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Mountain View California USA","acronym":"MM '17"},"container-title":["Proceedings of the 25th ACM international conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123449","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3123266.3123449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T02:14:04Z","timestamp":1750212844000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3123266.3123449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,19]]},"references-count":44,"alternative-id":["10.1145\/3123266.3123449","10.1145\/3123266"],"URL":"https:\/\/doi.org\/10.1145\/3123266.3123449","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"}}]}}