{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T10:56:03Z","timestamp":1761562563126,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T00:00:00Z","timestamp":1571097600000},"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":[[2019,10,15]]},"DOI":"10.1145\/3343031.3351005","type":"proceedings-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T16:32:26Z","timestamp":1571675546000},"page":"1703-1711","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Learning Local Similarity with Spatial Relations for Object Retrieval"],"prefix":"10.1145","author":[{"given":"Zhenfang","family":"Chen","sequence":"first","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanghui","family":"Kuang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wayne","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kwan-Yee K.","family":"Wong","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,10,15]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"R. Arandjelovi\u0107 P. Gronat A. Torii T. Pajdla and J. Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR .  R. Arandjelovi\u0107 P. Gronat A. Torii T. Pajdla and J. Sivic. 2016. NetVLAD: CNN architecture for weakly supervised place recognition. In CVPR .","DOI":"10.1109\/CVPR.2016.572"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Relja Arandjelovic and Andrew Zisserman. 2013. All About VLAD. In CVPR. 1578--1585.  Relja Arandjelovic and Andrew Zisserman. 2013. All About VLAD. In CVPR. 1578--1585.","DOI":"10.1109\/CVPR.2013.207"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Yannis Avrithis and Yannis Kalantidis. 2012. Approximate gaussian mixtures for large scale vocabularies. In ECCV. 15--28.  Yannis Avrithis and Yannis Kalantidis. 2012. Approximate gaussian mixtures for large scale vocabularies. In ECCV. 15--28.","DOI":"10.1007\/978-3-642-33712-3_2"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Artem Babenko Anton Slesarev Alexandr Chigorin and Victor Lempitsky. 2014. Neural codes for image retrieval. In ECCV. 584--599.  Artem Babenko Anton Slesarev Alexandr Chigorin and Victor Lempitsky. 2014. Neural codes for image retrieval. In ECCV. 584--599.","DOI":"10.1007\/978-3-319-10590-1_38"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126696"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Ondrej Chum Andrej Mikulik Michal Perdoch and Jiri Matas. 2011. Total recall II: Query expansion revisited. In CVPR. 889--896.  Ondrej Chum Andrej Mikulik Michal Perdoch and Jiri Matas. 2011. Total recall II: Query expansion revisited. In CVPR. 889--896.","DOI":"10.1109\/CVPR.2011.5995601"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Ondrej Chum James Philbin and Josef Sivic. 2007. Total recall: Automatic query expansion with a generative feature model for object retrieval. In ICCV .  Ondrej Chum James Philbin and Josef Sivic. 2007. Total recall: Automatic query expansion with a generative feature model for object retrieval. In ICCV .","DOI":"10.1109\/ICCV.2007.4408891"},{"volume-title":"Flownet: Learning optical flow with convolutional networks. In ICCV .","year":"2015","author":"Dosovitskiy Alexey","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"Debidatta Dwibedi Ishan Misra and Martial Hebert. 2017. Cut Paste and Learn: Surprisingly Easy Synthesis for Instance Detection. In ICCV .  Debidatta Dwibedi Ishan Misra and Martial Hebert. 2017. Cut Paste and Learn: Surprisingly Easy Synthesis for Instance Detection. In ICCV .","DOI":"10.1109\/ICCV.2017.146"},{"volume-title":"Jerome Revaud, and Diane Larlus.","year":"2016","author":"Gordo Albert","key":"e_1_3_2_1_10_1"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"volume-title":"Matchnet: Unifying feature and metric learning for patch-based matching. In CVPR . 3279--3286.","year":"2015","author":"Han Xufeng","key":"e_1_3_2_1_12_1"},{"key":"e_1_3_2_1_13_1","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_1_14_1","doi-asserted-by":"crossref","unstructured":"Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2018. Mining on manifolds: Metric learning without labels. In CVPR. 7642--7651.  Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2018. Mining on manifolds: Metric learning without labels. In CVPR. 7642--7651.","DOI":"10.1109\/CVPR.2018.00797"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Ahmet Iscen Giorgos Tolias Yannis Avrithis Teddy Furon and Ondrej Chum. 2017. Efficient diffusion on region manifolds: Recovering small objects with compact cnn representations. In CVPR .  Ahmet Iscen Giorgos Tolias Yannis Avrithis Teddy Furon and Ondrej Chum. 2017. Efficient diffusion on region manifolds: Recovering small objects with compact cnn representations. In CVPR .","DOI":"10.1109\/CVPR.2017.105"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Herv\u00e9 J\u00e9 gou and Matthijs Douze. 2010. Aggregating local descriptors into a compact image representation. In CVPR .  Herv\u00e9 J\u00e9 gou and Matthijs Douze. 2010. Aggregating local descriptors into a compact image representation. In CVPR .","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Product quantization for nearest neighbor search","volume":"33","author":"Herv\u00e9 J\u00e9","year":"2011","journal-title":"TPAMI"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Yannis Kalantidis Clayton Mellina and Simon Osindero. 2016. Cross-dimensional weighting for aggregated deep convolutional features. In ECCVW . 42.  Yannis Kalantidis Clayton Mellina and Simon Osindero. 2016. Cross-dimensional weighting for aggregated deep convolutional features. In ECCVW . 42.","DOI":"10.1007\/978-3-319-46604-0_48"},{"volume-title":"Microsoft coco: Common objects in context","author":"Lin Tsung-Yi","key":"e_1_3_2_1_19_1"},{"key":"e_1_3_2_1_20_1","unstructured":"Tsung-Yu Lin Aruni RoyChowdhury and Subhransu Maji. 2015. Bilinear cnn models for fine-grained visual recognition. In ICCV . 1449--1457.  Tsung-Yu Lin Aruni RoyChowdhury and Subhransu Maji. 2015. Bilinear cnn models for fine-grained visual recognition. In ICCV . 1449--1457."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_3_2_1_22_1","first-page":"2161","article-title":"Scalable recognition with a vocabulary tree","volume":"2","author":"Nister David","year":"2006","journal-title":"CVPR"},{"key":"e_1_3_2_1_23_1","unstructured":"Hyeonwoo Noh Andre Araujo Jack Sim Tobias Weyand and Bohyung Han. 2017. Large-Scale Image Retrieval with Attentive Deep Local Features. In ICCV .  Hyeonwoo Noh Andre Araujo Jack Sim Tobias Weyand and Bohyung Han. 2017. Large-Scale Image Retrieval with Attentive Deep Local Features. In ICCV ."},{"key":"e_1_3_2_1_24_1","unstructured":"Adam Paszke Sam Gross and Soumith Chintala. 2017. PyTorch. (2017).  Adam Paszke Sam Gross and Soumith Chintala. 2017. PyTorch. (2017)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Michal Perdoch Ondrej Chum and Jiri Matas. 2009. Efficient representation of local geometry for large scale object retrieval. In CVPR . 9--16.  Michal Perdoch Ondrej Chum and Jiri Matas. 2009. Efficient representation of local geometry for large scale object retrieval. In CVPR . 9--16.","DOI":"10.1109\/CVPR.2009.5206529"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Florent Perronnin and Christopher Dance. 2007. Fisher kernels on visual vocabularies for image categorization. In CVPR. 1--8.  Florent Perronnin and Christopher Dance. 2007. Fisher kernels on visual vocabularies for image categorization. In CVPR. 1--8.","DOI":"10.1109\/CVPR.2007.383266"},{"volume-title":"Jorge S\u00e1 nchez, and Herve Poirier","year":"2010","author":"Perronnin Florent","key":"e_1_3_2_1_27_1"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2007 a. 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 a. Object retrieval with large vocabularies and fast spatial matching. In CVPR . 1--8.","DOI":"10.1109\/CVPR.2007.383172"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"James Philbin Ondrej Chum Michael Isard Josef Sivic and Andrew Zisserman. 2007 b. 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 b. Object retrieval with large vocabularies and fast spatial matching. In CVPR . 1--8.","DOI":"10.1109\/CVPR.2007.383172"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"crossref","unstructured":"James Philbin Ondrej Chum Michael Isard Josef Sivic and A Zisserman. 2008. Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases. In CVPR .  James Philbin Ondrej Chum Michael Isard Josef Sivic and A Zisserman. 2008. Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases. In CVPR .","DOI":"10.1109\/CVPR.2008.4587635"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Filip Radenovi\u0107 Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2018. Revisiting oxford and paris: Large-scale image retrieval benchmarking. In CVPR . 5706--5715.  Filip Radenovi\u0107 Ahmet Iscen Giorgos Tolias Yannis Avrithis and Ondrej Chum. 2018. Revisiting oxford and paris: Large-scale image retrieval benchmarking. In CVPR . 5706--5715.","DOI":"10.1109\/CVPR.2018.00598"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Filip Radenovi\u0107 Giorgos Tolias and Ondrej Chum. 2016. CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples. In ECCV . 3--20.  Filip Radenovi\u0107 Giorgos Tolias and Ondrej Chum. 2016. CNN image retrieval learns from BoW: Unsupervised fine-tuning with hard examples. In ECCV . 3--20.","DOI":"10.1007\/978-3-319-46448-0_1"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Ali Sharif Razavian Hossein Azizpour Josephine Sullivan Stefan Carlsson Ali Sharif Razavian Hossein Azizpour Josephine Sullivan Stefan and K T H Royal. 2014a. CNN Features off-the-shelf : an Astounding Baseline for Recognition. In CVPRW . 512--519.  Ali Sharif Razavian Hossein Azizpour Josephine Sullivan Stefan Carlsson Ali Sharif Razavian Hossein Azizpour Josephine Sullivan Stefan and K T H Royal. 2014a. CNN Features off-the-shelf : an Astounding Baseline for Recognition. In CVPRW . 512--519.","DOI":"10.1109\/CVPRW.2014.131"},{"volume-title":"Visual instance retrieval with deep convolutional networks . arXiv preprint arXiv:1412.6574","year":"2014","author":"Razavian Ali Sharif","key":"e_1_3_2_1_34_1"},{"volume-title":"A Baseline for Visual Instance Retrieval with Deep Convolutional Networks. CoRR","year":"2014","author":"Razavian Ali Sharif","key":"e_1_3_2_1_35_1"},{"key":"e_1_3_2_1_36_1","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."},{"volume-title":"Convolutional neural network architecture for geometric matching. CVPR","year":"2017","author":"Rocco Ignacio","key":"e_1_3_2_1_37_1"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"volume-title":"Grad-cam: Visual explanations from deep networks via gradient-based localization. See https:\/\/arxiv. org\/abs\/1610.02391 v3","year":"2016","author":"Selvaraju Ramprasaath R","key":"e_1_3_2_1_39_1"},{"key":"e_1_3_2_1_40_1","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_1_41_1","first-page":"1470","article-title":"Video Google: a text retrieval approach to object matching in videos","volume":"2","author":"Sivic Josef","year":"2003","journal-title":"ICCV"},{"key":"e_1_3_2_1_42_1","unstructured":"Giorgos Tolias Ronan Sicre and Herv\u00e9 J\u00e9 gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In ICLR .  Giorgos Tolias Ronan Sicre and Herv\u00e9 J\u00e9 gou. 2016. Particular object retrieval with integral max-pooling of CNN activations. In ICLR ."},{"volume-title":"TILDE: A temporally invariant learned detector. In CVPR. 5279--5288.","year":"2015","author":"Verdie Yannick","key":"e_1_3_2_1_43_1"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2700292"},{"key":"e_1_3_2_1_45_1","unstructured":"Artem Babenko Yandex and Victor Lempitsky. 2015. Aggregating local deep features for image retrieval. In ICCV .  Artem Babenko Yandex and Victor Lempitsky. 2015. Aggregating local deep features for image retrieval. In ICCV ."},{"volume-title":"LIFT: Learned invariant feature transform. In ECCV. 467--483.","year":"2016","author":"Yi Kwang Moo","key":"e_1_3_2_1_46_1"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2015. Learning to compare image patches via convolutional neural networks. In CVPR . 4353--4361.  Sergey Zagoruyko and Nikos Komodakis. 2015. Learning to compare image patches via convolutional neural networks. In CVPR . 4353--4361.","DOI":"10.1109\/CVPR.2015.7299064"},{"volume-title":"SIFT meets CNN: A decade survey of instance retrieval. TPAMI","year":"2017","author":"Zheng Liang","key":"e_1_3_2_1_48_1"}],"event":{"name":"MM '19: The 27th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Nice France","acronym":"MM '19"},"container-title":["Proceedings of the 27th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351005","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3343031.3351005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:13:11Z","timestamp":1750201991000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3343031.3351005"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,15]]},"references-count":48,"alternative-id":["10.1145\/3343031.3351005","10.1145\/3343031"],"URL":"https:\/\/doi.org\/10.1145\/3343031.3351005","relation":{},"subject":[],"published":{"date-parts":[[2019,10,15]]},"assertion":[{"value":"2019-10-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}