{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:26:29Z","timestamp":1750220789834,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T00:00:00Z","timestamp":1595635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the Major Fundamental Research Project in the Science and Technology Plan of Shenzhen","award":["JCYJ20190808172007500"],"award-info":[{"award-number":["JCYJ20190808172007500"]}]},{"name":"National Natural Science Foundation of China","award":["61602314"],"award-info":[{"award-number":["61602314"]}]},{"name":"Natural Science Foundation of Guangdong Province of China","award":["2016A030313043"],"award-info":[{"award-number":["2016A030313043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,7,25]]},"DOI":"10.1145\/3397271.3401176","type":"proceedings-article","created":{"date-parts":[[2020,7,25]],"date-time":"2020-07-25T07:50:08Z","timestamp":1595663408000},"page":"821-830","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Regional Relation Modeling for Visual Place Recognition"],"prefix":"10.1145","author":[{"given":"Yingying","family":"Zhu","sequence":"first","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biao","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiong","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang University, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,7,25]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Vqa: Visual question answering. In ICCV. 2425--2433.","author":"Antol Stanislaw","year":"2015","unstructured":"Stanislaw Antol , Aishwarya Agrawal , Jiasen Lu , Margaret Mitchell , Dhruv Batra , C Lawrence Zitnick , and Devi Parikh . 2015 . Vqa: Visual question answering. In ICCV. 2425--2433. Stanislaw Antol, Aishwarya Agrawal, Jiasen Lu, Margaret Mitchell, Dhruv Batra, C Lawrence Zitnick, and Devi Parikh. 2015. Vqa: Visual question answering. In ICCV. 2425--2433."},{"doi-asserted-by":"crossref","unstructured":"Relja Arandjelovi\u0107 Petr Gronat Akihiko Torii Tomas Pajdla and Josef Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR. 5297--5307.  Relja Arandjelovi\u0107 Petr Gronat Akihiko Torii Tomas Pajdla and Josef Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR. 5297--5307.","key":"e_1_3_2_2_2_1","DOI":"10.1109\/CVPR.2016.572"},{"doi-asserted-by":"crossref","unstructured":"Relja Arandjelovi\u0107 and Andrew Zisserman. 2013. All About VLAD. In CVPR. 1578--1585.  Relja Arandjelovi\u0107 and Andrew Zisserman. 2013. All About VLAD. In CVPR. 1578--1585.","key":"e_1_3_2_2_3_1","DOI":"10.1109\/CVPR.2013.207"},{"doi-asserted-by":"crossref","unstructured":"Relja Arandjelovi\u0107 and Andrew Zisserman. 2014. DisLocation: Scalable descriptor distinctiveness for location recognition. In ACCV. 188--204.  Relja Arandjelovi\u0107 and Andrew Zisserman. 2014. DisLocation: Scalable descriptor distinctiveness for location recognition. In ACCV. 188--204.","key":"e_1_3_2_2_4_1","DOI":"10.1007\/978-3-319-16817-3_13"},{"unstructured":"Artem Babenko and Victor Lempitsky. 2015. Aggregating local deep features for image retrieval. In ICCV. 1269--1277.  Artem Babenko and Victor Lempitsky. 2015. Aggregating local deep features for image retrieval. In ICCV. 1269--1277.","key":"e_1_3_2_2_5_1"},{"key":"e_1_3_2_2_6_1","volume-title":"Danilo Jimenez Rezende, et al","author":"Battaglia Peter","year":"2016","unstructured":"Peter Battaglia , Razvan Pascanu , Matthew Lai , Danilo Jimenez Rezende, et al . 2016 . Interaction networks for learning about objects, relations and physics. In NIPS. 4502--4510. Peter Battaglia, Razvan Pascanu, Matthew Lai, Danilo Jimenez Rezende, et al. 2016. Interaction networks for learning about objects, relations and physics. In NIPS. 4502--4510."},{"key":"e_1_3_2_2_7_1","volume-title":"Surf: Speeded up robust features. In ECCV. 404--417.","author":"Bay Herbert","year":"2006","unstructured":"Herbert Bay , Tinne Tuytelaars , and Luc Van Gool . 2006 . Surf: Speeded up robust features. In ECCV. 404--417. Herbert Bay, Tinne Tuytelaars, and Luc Van Gool. 2006. Surf: Speeded up robust features. In ECCV. 404--417."},{"doi-asserted-by":"crossref","unstructured":"David M. Chen Georges Baatz Kevin Koser Sam S. Tsai and Radek Grzeszczuk. 2011. City-scale landmark identification on mobile devices. In CVPR. 737--744.  David M. Chen Georges Baatz Kevin Koser Sam S. Tsai and Radek Grzeszczuk. 2011. City-scale landmark identification on mobile devices. In CVPR. 737--744.","key":"e_1_3_2_2_8_1","DOI":"10.1109\/CVPR.2011.5995610"},{"volume-title":"Only look once, mining distinctive landmarks from ConvNet for visual place recognition","author":"Chen Zetao","unstructured":"Zetao Chen , Fabiola Maffra , Inkyu Sa , and Margarita Chli . 2017. Only look once, mining distinctive landmarks from ConvNet for visual place recognition . In IEEE\/IROS. Zetao Chen, Fabiola Maffra, Inkyu Sa, and Margarita Chli. 2017. Only look once, mining distinctive landmarks from ConvNet for visual place recognition. In IEEE\/IROS.","key":"e_1_3_2_2_9_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_10_1","DOI":"10.1177\/0278364908090961"},{"doi-asserted-by":"crossref","unstructured":"Bo Dai Yuqi Zhang and Dahua Lin. 2017. Detecting visual relationships with deep relational networks. In CVPR. 3298--3308.  Bo Dai Yuqi Zhang and Dahua Lin. 2017. Detecting visual relationships with deep relational networks. In CVPR. 3298--3308.","key":"e_1_3_2_2_11_1","DOI":"10.1109\/CVPR.2017.352"},{"doi-asserted-by":"crossref","unstructured":"Carl Doersch Abhinav Gupta and Alexei A Efros. 2015. Unsupervised visual representation learning by context prediction. In ICCV. 1422--1430.  Carl Doersch Abhinav Gupta and Alexei A Efros. 2015. Unsupervised visual representation learning by context prediction. In ICCV. 1422--1430.","key":"e_1_3_2_2_12_1","DOI":"10.1109\/ICCV.2015.167"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_13_1","DOI":"10.1007\/s11263-009-0275-4"},{"doi-asserted-by":"crossref","unstructured":"Albert Gordo Jon Almaz\u00e1n Jerome Revaud and Diane Larlus. 2016. Deep image retrieval: Learning global representations for image search. In ECCV. 241--257.  Albert Gordo Jon Almaz\u00e1n Jerome Revaud and Diane Larlus. 2016. Deep image retrieval: Learning global representations for image search. In ECCV. 241--257.","key":"e_1_3_2_2_14_1","DOI":"10.1007\/978-3-319-46466-4_15"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_15_1","DOI":"10.1007\/s11263-017-1016-8"},{"key":"e_1_3_2_2_16_1","volume-title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People. arXiv preprint arXiv:1802.08218","author":"Gurari Danna","year":"2018","unstructured":"Danna Gurari , Qing Li , Abigale J Stangl , Anhong Guo , Chi Lin , Kristen Grauman , Jiebo Luo , and Jeffrey P Bigham . 2018. VizWiz Grand Challenge: Answering Visual Questions from Blind People. arXiv preprint arXiv:1802.08218 ( 2018 ). Danna Gurari, Qing Li, Abigale J Stangl, Anhong Guo, Chi Lin, Kristen Grauman, Jiebo Luo, and Jeffrey P Bigham. 2018. VizWiz Grand Challenge: Answering Visual Questions from Blind People. arXiv preprint arXiv:1802.08218 (2018)."},{"doi-asserted-by":"crossref","unstructured":"James Hays and Alexei A Efros. 2008. IM2GPS: estimating geographic information from a single image. In CVPR. 1--8.  James Hays and Alexei A Efros. 2008. IM2GPS: estimating geographic information from a single image. In CVPR. 1--8.","key":"e_1_3_2_2_17_1","DOI":"10.1109\/CVPR.2008.4587784"},{"unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.","key":"e_1_3_2_2_18_1"},{"doi-asserted-by":"crossref","unstructured":"Han Hu Jiayuan Gu Zheng Zhang Jifeng Dai and Yichen Wei. 2018. Relation Networks for Object Detection. In CVPR. 3588--3597.  Han Hu Jiayuan Gu Zheng Zhang Jifeng Dai and Yichen Wei. 2018. Relation Networks for Object Detection. In CVPR. 3588--3597.","key":"e_1_3_2_2_19_1","DOI":"10.1109\/CVPR.2018.00378"},{"doi-asserted-by":"crossref","unstructured":"Herve Jegou Matthijs Douze and Cordelia Schmid. 2008. Hamming embedding and weak geometric consistency for large scale image search. In ECCV. 304--317.  Herve Jegou Matthijs Douze and Cordelia Schmid. 2008. Hamming embedding and weak geometric consistency for large scale image search. In ECCV. 304--317.","key":"e_1_3_2_2_20_1","DOI":"10.1007\/978-3-540-88682-2_24"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_21_1","DOI":"10.1109\/TPAMI.2011.235"},{"unstructured":"Hyo Jin Kim Enrique Dunn and Jan-Michael Frahm. 2015. Predicting good features for image geo-localization using per-bundle vlad. In ICCV. 1170--1178.  Hyo Jin Kim Enrique Dunn and Jan-Michael Frahm. 2015. Predicting good features for image geo-localization using per-bundle vlad. In ICCV. 1170--1178.","key":"e_1_3_2_2_22_1"},{"key":"e_1_3_2_2_23_1","volume-title":"CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR. 1988--1997.","author":"Johnson Justin","year":"2017","unstructured":"Justin Johnson , Bharath Hariharan , Laurens van der Maaten , Li Fei-Fei , C Lawrence Zitnick , and Ross Girshick . 2017 . CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR. 1988--1997. Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Li Fei-Fei, C Lawrence Zitnick, and Ross Girshick. 2017. CLEVR: A diagnostic dataset for compositional language and elementary visual reasoning. In CVPR. 1988--1997."},{"unstructured":"Hyo Jin Kim Enrique Dunn and Jan-Michael Frahm. 2017. Learned contextual feature reweighting for image geo-localization. In CVPR. 2136--2145.  Hyo Jin Kim Enrique Dunn and Jan-Michael Frahm. 2017. Learned contextual feature reweighting for image geo-localization. In CVPR. 2136--2145.","key":"e_1_3_2_2_24_1"},{"key":"e_1_3_2_2_25_1","volume-title":"Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907","author":"Kipf Thomas N","year":"2016","unstructured":"Thomas N Kipf and Max Welling . 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 ( 2016 ). Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)."},{"doi-asserted-by":"crossref","unstructured":"Jan Knopp Josef Sivic and Tomas Pajdla. 2010. Avoiding confusing features in place recognition. ECCV 748--761.  Jan Knopp Josef Sivic and Tomas Pajdla. 2010. Avoiding confusing features in place recognition. ECCV 748--761.","key":"e_1_3_2_2_26_1","DOI":"10.1007\/978-3-642-15549-9_54"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_27_1","DOI":"10.1007\/s11263-016-0981-7"},{"unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In NIPS. 1097--1105.","key":"e_1_3_2_2_28_1"},{"unstructured":"Yujia Li Daniel Tarlow Marc Brockschmidt and Richard Zemel. 2015. Gated graph sequence neural networks. In ICLR.  Yujia Li Daniel Tarlow Marc Brockschmidt and Richard Zemel. 2015. Gated graph sequence neural networks. In ICLR.","key":"e_1_3_2_2_29_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_30_1","DOI":"10.1109\/ICCV.2019.01050"},{"doi-asserted-by":"crossref","unstructured":"Liu Liu Hongdong Li and Yuchao Dai. 2017. Efficient global 2d-3d matching for camera localization in a large-scale 3d map. In ICCV. 2391--2400.  Liu Liu Hongdong Li and Yuchao Dai. 2017. Efficient global 2d-3d matching for camera localization in a large-scale 3d map. In ICCV. 2391--2400.","key":"e_1_3_2_2_31_1","DOI":"10.1109\/ICCV.2017.260"},{"doi-asserted-by":"crossref","unstructured":"Yihang Lou Yan Bai Shiqi Wang and Ling-Yu Duan. 2018. Multi-Scale Context Attention Network for Image Retrieval. In ACM MM. 1128--1136.  Yihang Lou Yan Bai Shiqi Wang and Ling-Yu Duan. 2018. Multi-Scale Context Attention Network for Image Retrieval. In ACM MM. 1128--1136.","key":"e_1_3_2_2_32_1","DOI":"10.1145\/3240508.3240602"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_33_1","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"doi-asserted-by":"crossref","unstructured":"Cewu Lu Ranjay Krishna Michael Bernstein and Li Fei-Fei. 2016. Visual relationship detection with language priors. In ECCV. 852--869.  Cewu Lu Ranjay Krishna Michael Bernstein and Li Fei-Fei. 2016. Visual relationship detection with language priors. In ECCV. 852--869.","key":"e_1_3_2_2_34_1","DOI":"10.1007\/978-3-319-46448-0_51"},{"doi-asserted-by":"crossref","unstructured":"Colin McManus Winston Churchill Will Maddern Alexander D Stewart and Paul Newman. 2014. Shady dealings: Robust long-term visual localisation using illumination invariance. In ICRA. 901--906.  Colin McManus Winston Churchill Will Maddern Alexander D Stewart and Paul Newman. 2014. Shady dealings: Robust long-term visual localisation using illumination invariance. In ICRA. 901--906.","key":"e_1_3_2_2_35_1","DOI":"10.1109\/ICRA.2014.6906961"},{"unstructured":"Hyeonwoo Noh Andre Araujo Jack Sim Tobias Weyand and Bohyung Han. 2017. Largescale image retrieval with attentive deep local features. In ICCV. 3456--3465.  Hyeonwoo Noh Andre Araujo Jack Sim Tobias Weyand and Bohyung Han. 2017. Largescale image retrieval with attentive deep local features. In ICCV. 3456--3465.","key":"e_1_3_2_2_36_1"},{"doi-asserted-by":"crossref","unstructured":"Mehdi Noroozi and Paolo Favaro. 2016. Unsupervised learning of visual representations by solving jigsaw puzzles. In ECCV. 69--84.  Mehdi Noroozi and Paolo Favaro. 2016. Unsupervised learning of visual representations by solving jigsaw puzzles. In ECCV. 69--84.","key":"e_1_3_2_2_37_1","DOI":"10.1007\/978-3-319-46466-4_5"},{"doi-asserted-by":"crossref","unstructured":"James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2007. Object retrieval with large vocabularies and fast spatial matching. In CVPR. 1--8.  James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2007. Object retrieval with large vocabularies and fast spatial matching. In CVPR. 1--8.","key":"e_1_3_2_2_38_1","DOI":"10.1109\/CVPR.2007.383172"},{"doi-asserted-by":"crossref","unstructured":"James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2008. Lost in quantization: Improving particular object retrieval in large scale image databases. In CVPR. 1--8.  James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2008. Lost in quantization: Improving particular object retrieval in large scale image databases. In CVPR. 1--8.","key":"e_1_3_2_2_39_1","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"e_1_3_2_2_40_1","volume-title":"Fine-tuning CNN Image Retrieval with No Human Annotation. TPAMI","author":"Radenovic Filip","year":"2018","unstructured":"Filip Radenovic , Giorgos Tolias , and Ondej Chum . 2018. Fine-tuning CNN Image Retrieval with No Human Annotation. TPAMI ( 2018 ). Filip Radenovic, Giorgos Tolias, and Ondej Chum. 2018. Fine-tuning CNN Image Retrieval with No Human Annotation. TPAMI (2018)."},{"unstructured":"Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS. 91--99.  Shaoqing Ren Kaiming He Ross Girshick and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS. 91--99.","key":"e_1_3_2_2_41_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_42_1","DOI":"10.1109\/ICCV.2019.00521"},{"unstructured":"Adam Santoro David Raposo David G Barrett Mateusz Malinowski Razvan Pascanu Peter Battaglia and Tim Lillicrap. 2017. A simple neural network module for relational reasoning. In NIPS. 4967--4976.  Adam Santoro David Raposo David G Barrett Mateusz Malinowski Razvan Pascanu Peter Battaglia and Tim Lillicrap. 2017. A simple neural network module for relational reasoning. In NIPS. 4967--4976.","key":"e_1_3_2_2_43_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_44_1","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"e_1_3_2_2_45_1","volume-title":"Facenet: A unified embedding for face recognition and clustering. In CVPR. 815--823.","author":"Schroff Florian","year":"2015","unstructured":"Florian Schroff , Dmitry Kalenichenko , and James Philbin . 2015 . Facenet: A unified embedding for face recognition and clustering. In CVPR. 815--823. Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In CVPR. 815--823."},{"doi-asserted-by":"crossref","unstructured":"Paul Hongsuck Seo Tobias Weyand Jack Sim and Bohyung Han. 2018. CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps. In ECCV. 544--560.  Paul Hongsuck Seo Tobias Weyand Jack Sim and Bohyung Han. 2018. CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps. In ECCV. 544--560.","key":"e_1_3_2_2_46_1","DOI":"10.1007\/978-3-030-01249-6_33"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_47_1","DOI":"10.1109\/CVPR.2019.01192"},{"unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR.  Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In ICLR.","key":"e_1_3_2_2_48_1"},{"key":"e_1_3_2_2_49_1","volume-title":"Video Google: A text retrieval approach to object matching in videos. In ICCV. 1470--1477.","author":"Sivic Josef","year":"2003","unstructured":"Josef Sivic and Andrew Zisserman . 2003 . Video Google: A text retrieval approach to object matching in videos. In ICCV. 1470--1477. Josef Sivic and Andrew Zisserman. 2003. Video Google: A text retrieval approach to object matching in videos. In ICCV. 1470--1477."},{"doi-asserted-by":"crossref","unstructured":"Abby Stylianou Richard Souvenir and Robert Pless. 2019. Visualizing Deep Similarity Networks. In WACV.  Abby Stylianou Richard Souvenir and Robert Pless. 2019. Visualizing Deep Similarity Networks. In WACV.","key":"e_1_3_2_2_50_1","DOI":"10.1109\/WACV.2019.00220"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_51_1","DOI":"10.1007\/s11263-015-0810-4"},{"unstructured":"Giorgos Tolias Ronan Sicre and Herv\u00e9 J\u00e9gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In ICLR.  Giorgos Tolias Ronan Sicre and Herv\u00e9 J\u00e9gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In ICLR.","key":"e_1_3_2_2_52_1"},{"doi-asserted-by":"crossref","unstructured":"Akihiko Torii Relja Arandjelovic Josef Sivic Masatoshi Okutomi and Tomas Pajdla. 2015. 24\/7 place recognition by view synthesis. In CVPR. 1808--1817.  Akihiko Torii Relja Arandjelovic Josef Sivic Masatoshi Okutomi and Tomas Pajdla. 2015. 24\/7 place recognition by view synthesis. In CVPR. 1808--1817.","key":"e_1_3_2_2_53_1","DOI":"10.1109\/CVPR.2015.7298790"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_54_1","DOI":"10.1109\/TPAMI.2017.2667665"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_55_1","DOI":"10.1109\/TPAMI.2015.2409868"},{"doi-asserted-by":"crossref","unstructured":"Akihiko Torii Josef Sivic Tomas Pajdla and Masatoshi Okutomi. 2013. iVsual place recognition with repetitive structures. In CVPR. 883--890.  Akihiko Torii Josef Sivic Tomas Pajdla and Masatoshi Okutomi. 2013. iVsual place recognition with repetitive structures. In CVPR. 883--890.","key":"e_1_3_2_2_56_1","DOI":"10.1109\/CVPR.2013.119"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_57_1","DOI":"10.1109\/CVPR.2018.00813"},{"doi-asserted-by":"publisher","key":"e_1_3_2_2_58_1","DOI":"10.1007\/978-3-030-01228-1_25"},{"doi-asserted-by":"crossref","unstructured":"Xu Yang Hanwang Zhang and Jianfei Cai. 2018. Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features. In ECCV. 38--54.  Xu Yang Hanwang Zhang and Jianfei Cai. 2018. Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features. In ECCV. 38--54.","key":"e_1_3_2_2_59_1","DOI":"10.1007\/978-3-030-01258-8_3"},{"key":"e_1_3_2_2_60_1","volume-title":"Lu Li, Jianmin Ji, and Yuqing He.","author":"Yin Peng","year":"2019","unstructured":"Peng Yin , Lingyun Xu , Xueqian Li , Chen Yin , Yingli Li , Rangaprasad Arun Srivatsan , Lu Li, Jianmin Ji, and Yuqing He. 2019 . A Multi-Domain Feature Learning Method for Visual Place Recognition . arXiv preprint arXiv:1902.10058 (2019). Peng Yin, Lingyun Xu, Xueqian Li, Chen Yin, Yingli Li, Rangaprasad Arun Srivatsan, Lu Li, Jianmin Ji, and Yuqing He. 2019. A Multi-Domain Feature Learning Method for Visual Place Recognition. arXiv preprint arXiv:1902.10058 (2019)."},{"doi-asserted-by":"crossref","unstructured":"Liang Zheng Liyue Shen Lu Tian Shengjin Wang Jingdong Wang and Qi Tian. 2015. Scalable person re-identification: A benchmark. In ICCV. 1116--1124.  Liang Zheng Liyue Shen Lu Tian Shengjin Wang Jingdong Wang and Qi Tian. 2015. Scalable person re-identification: A benchmark. In ICCV. 1116--1124.","key":"e_1_3_2_2_61_1","DOI":"10.1109\/ICCV.2015.133"},{"key":"e_1_3_2_2_62_1","volume-title":"SIFT meets CNN: A decade survey of instance retrieval. TPAMI","author":"Zheng Liang","year":"2017","unstructured":"Liang Zheng , Yi Yang , and Qi Tian . 2017. SIFT meets CNN: A decade survey of instance retrieval. TPAMI ( 2017 ). Liang Zheng, Yi Yang, and Qi Tian. 2017. SIFT meets CNN: A decade survey of instance retrieval. TPAMI (2017)."},{"unstructured":"Yingying Zhu Jiong Wang Lingxi Xie and Liang Zheng. 2018. Attention-based Pyramid Aggregation Network for Visual Place Recognition. In ACM MM. 99--107.  Yingying Zhu Jiong Wang Lingxi Xie and Liang Zheng. 2018. Attention-based Pyramid Aggregation Network for Visual Place Recognition. In ACM MM. 99--107.","key":"e_1_3_2_2_63_1"}],"event":{"sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"acronym":"SIGIR '20","name":"SIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval","location":"Virtual Event China"},"container-title":["Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401176","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397271.3401176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:43Z","timestamp":1750200103000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397271.3401176"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,25]]},"references-count":63,"alternative-id":["10.1145\/3397271.3401176","10.1145\/3397271"],"URL":"https:\/\/doi.org\/10.1145\/3397271.3401176","relation":{},"subject":[],"published":{"date-parts":[[2020,7,25]]},"assertion":[{"value":"2020-07-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}