{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T01:37:46Z","timestamp":1777599466882,"version":"3.51.4"},"reference-count":38,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2019,7,1]],"date-time":"2019-07-01T00:00:00Z","timestamp":1561939200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61603289"],"award-info":[{"award-number":["61603289"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573273"],"award-info":[{"award-number":["61573273"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State Key Laboratory of Rail Transit Engineering Informatization","award":["SKLK19-07"],"award-info":[{"award-number":["SKLK19-07"]}]},{"name":"Postdoctoral Science Foundation of Shaanxi","award":["2017BSHEDZZ89"],"award-info":[{"award-number":["2017BSHEDZZ89"]}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1016\/j.jvcir.2019.06.006","type":"journal-article","created":{"date-parts":[[2019,6,20]],"date-time":"2019-06-20T03:59:36Z","timestamp":1561003176000},"page":"368-380","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":14,"special_numbering":"C","title":["Co-weighting semantic convolutional features for object retrieval"],"prefix":"10.1016","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3081-8781","authenticated-orcid":false,"given":"Jihua","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Jiaxing","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7217-864X","authenticated-orcid":false,"given":"Shanmin","family":"Pang","sequence":"additional","affiliation":[]},{"given":"Weili","family":"Guan","sequence":"additional","affiliation":[]},{"given":"Zhongyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yaochen","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xueming","family":"Qian","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2019.06.006_b0005","series-title":"International Conference on Computer Vision","first-page":"1470","article-title":"Video google: a text retrieval approach to object matching in videos","author":"Sivic","year":"2003"},{"key":"10.1016\/j.jvcir.2019.06.006_b0010","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.neucom.2016.01.032","article-title":"Metric learning based object recognition and retrieval","volume":"190","author":"Yang","year":"2016","journal-title":"Neurocomputing"},{"issue":"1","key":"10.1016\/j.jvcir.2019.06.006_b0015","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","article-title":"Product quantization for nearest neighbor search","volume":"33","author":"Jegou","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2019.06.006_b0020","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1016\/j.media.2017.09.007","article-title":"Large-scale retrieval for medical image analytics: a comprehensive review","volume":"43","author":"Li","year":"2018","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.jvcir.2019.06.006_b0025","series-title":"Comput. Vision Pattern Recogn.","first-page":"3304","article-title":"Aggregating local descriptors into a compact image representation","author":"J\u00e9gou","year":"2010"},{"issue":"2","key":"10.1016\/j.jvcir.2019.06.006_b0030","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1109\/TIP.2018.2874286","article-title":"Unifying sum and weighted aggregations for efficient yet effective image representation computation","volume":"28","author":"Pang","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2019.06.006_b0035","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/j.neucom.2017.01.081","article-title":"Sift matching with cnn evidences for particular object retrieval","volume":"238","author":"Zhang","year":"2017","journal-title":"Neurocomputing"},{"issue":"2","key":"10.1016\/j.jvcir.2019.06.006_b0040","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1007\/s11263-017-1016-8","article-title":"End-to-end learning of deep visual representations for image retrieval","volume":"124","author":"Gordo","year":"2017","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.jvcir.2019.06.006_b0045","doi-asserted-by":"crossref","unstructured":"A. Alzu\u2019Bi, A. Amira, N. Ramzan, Content-based image retrieval with compact deep convolutional features, Neurocomputing, vol. 249.","DOI":"10.1016\/j.neucom.2017.03.072"},{"issue":"2","key":"10.1016\/j.jvcir.2019.06.006_b0050","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.jvcir.2019.06.006_b0055","series-title":"International Conference on Multimedia & Expo","first-page":"1","article-title":"Adaptive co-weighting deep convolutional features for object retrieval","author":"Wang","year":"2018"},{"key":"10.1016\/j.jvcir.2019.06.006_b0060","unstructured":"A. Krizhevsky, I. Sutskever, G.E. Hinton, Imagenet classification with deep convolutional neural networks, in: Advances in Neural Information Processing Systems, 2012, pp. 1097\u20131105."},{"key":"10.1016\/j.jvcir.2019.06.006_b0065","series-title":"European Conference on Computer Vision","first-page":"584","article-title":"Neural codes for image retrieval","author":"Babenko","year":"2014"},{"key":"10.1016\/j.jvcir.2019.06.006_b0070","series-title":"Computer Vision and Pattern Recognition Workshops","first-page":"512","article-title":"Cnn features off-the-shelf: an astounding baseline for recognition","author":"Razavian","year":"2014"},{"key":"10.1016\/j.jvcir.2019.06.006_b0075","series-title":"International Conference on Computer Vision","first-page":"1269","article-title":"Aggregating local deep features for image retrieval","author":"Babenko","year":"2015"},{"key":"10.1016\/j.jvcir.2019.06.006_b0080","series-title":"International Conference on Learning Representations","first-page":"1","article-title":"Particular object retrieval with integral max-pooling of cnn activations","author":"Tolias","year":"2016"},{"key":"10.1016\/j.jvcir.2019.06.006_b0085","series-title":"European Conference on Computer Vision","first-page":"685","article-title":"Cross-dimensional weighting for aggregated deep convolutional features","author":"Kalantidis","year":"2016"},{"key":"10.1016\/j.jvcir.2019.06.006_b0090","series-title":"Proceedings of the 2017 ACM on Multimedia Conference","first-page":"1600","article-title":"Selective deep convolutional features for image retrieval","author":"Hoang","year":"2017"},{"key":"10.1016\/j.jvcir.2019.06.006_b0095","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.patcog.2018.05.010","article-title":"Building discriminative cnn image representations for object retrieval using the replicator equation","volume":"83","author":"Pang","year":"2018","journal-title":"Pattern Recogn."},{"key":"10.1016\/j.jvcir.2019.06.006_b0100","unstructured":"K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556."},{"key":"10.1016\/j.jvcir.2019.06.006_b0105","series-title":"European Conference on Computer Vision","first-page":"3","article-title":"CNN image retrieval learns from BoW: unsupervised fine-tuning with hard examples","author":"Radenovi\u0107","year":"2016"},{"key":"10.1016\/j.jvcir.2019.06.006_b0110","series-title":"European Conference on Computer Vision","first-page":"241","article-title":"Deep image retrieval: learning global representations for image search","author":"Gordo","year":"2016"},{"key":"10.1016\/j.jvcir.2019.06.006_b0115","doi-asserted-by":"crossref","unstructured":"R. Arandjelovic, P. Gronat, A. Torii, T. Pajdla, J. Sivic, NetVLAD: CNN architecture for weakly supervised place recognition, in: Computer Vision and Pattern Recognition, 2016, pp. 5297\u20135307.","DOI":"10.1109\/CVPR.2016.572"},{"issue":"3","key":"10.1016\/j.jvcir.2019.06.006_b0120","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1007\/s11263-009-0285-2","article-title":"Improving bag-of-features for large scale image search","volume":"87","author":"J\u00e9gou","year":"2010","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.jvcir.2019.06.006_b0125","series-title":"Computer Vision and Pattern Recognition","first-page":"1","article-title":"Object retrieval with large vocabularies and fast spatial matching","author":"Philbin","year":"2007"},{"key":"10.1016\/j.jvcir.2019.06.006_b0130","series-title":"International Conference on Computer Vision","first-page":"1","article-title":"Total recall: automatic query expansion with a generative feature model for object retrieval","author":"Chum","year":"2007"},{"issue":"2","key":"10.1016\/j.jvcir.2019.06.006_b0135","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1109\/TIP.2018.2867104","article-title":"Unsupervised semantic-based aggregation of deep convolutional features","volume":"28","author":"Xu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2019.06.006_b0140","series-title":"Computer Vision and Pattern Recognition","first-page":"1169","article-title":"On the burstiness of visual elements","author":"J\u00e9gou","year":"2009"},{"key":"10.1016\/j.jvcir.2019.06.006_b0145","series-title":"Computer Vision and Pattern Recognition","first-page":"1","article-title":"Lost in quantization: improving particular object retrieval in large scale image databases","author":"Philbin","year":"2008"},{"key":"10.1016\/j.jvcir.2019.06.006_b0150","series-title":"ACM International Conference on Multimedia","first-page":"675","article-title":"Caffe: convolutional architecture for fast feature embedding","author":"Jia","year":"2014"},{"key":"10.1016\/j.jvcir.2019.06.006_b0155","series-title":"Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.jvcir.2019.06.006_b0160","series-title":"IEEE International Geoscience and Remote Sensing Symposium","first-page":"1824","article-title":"Deep residual networks for hyperspectral image classification","author":"Zhong","year":"2017"},{"key":"10.1016\/j.jvcir.2019.06.006_b0165","doi-asserted-by":"crossref","unstructured":"M. Liu, X. Wang, L. Nie, X. He, B. Chen, T.-S. Chua, Attentive moment retrieval in videos, in: ACM SIGIR Conference on Research & Development in Information Retrieval, 2018, pp. 15\u201324.","DOI":"10.1145\/3209978.3210003"},{"issue":"3","key":"10.1016\/j.jvcir.2019.06.006_b0170","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1109\/TIP.2018.2875363","article-title":"Online data organizer: micro-video categorization by structure-guided multimodal dictionary learning","volume":"28","author":"Liu","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.jvcir.2019.06.006_b0175","series-title":"ACM International Conference on Multimedia","first-page":"753","article-title":"Neurostylist: neural compatibility modeling for clothing matching","author":"Song","year":"2017"},{"key":"10.1016\/j.jvcir.2019.06.006_b0180","series-title":"ACM SIGIR Conference on Research & Development in Information Retrieval","first-page":"5","article-title":"Neural compatibility modeling with attentive knowledge distillation","author":"Song","year":"2018"},{"key":"10.1016\/j.jvcir.2019.06.006_b0185","unstructured":"E. Mohedano, K. McGuinness, X. Giro-i Nieto, N.E. O\u2019Connor, Saliency weighted convolutional features for instance search, arXiv preprint arXiv:1711.10795."},{"key":"10.1016\/j.jvcir.2019.06.006_b0190","unstructured":"A. Jimenez, J.M. Alvarez, X. Giro-i Nieto, Class-weighted convolutional features for visual instance search, arXiv preprint arXiv:1707.02581."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320319301798?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320319301798?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,11,27]],"date-time":"2019-11-27T02:24:03Z","timestamp":1574821443000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320319301798"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7]]},"references-count":38,"alternative-id":["S1047320319301798"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2019.06.006","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2019,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Co-weighting semantic convolutional features for object retrieval","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2019.06.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2019 Elsevier Inc. All rights reserved.","name":"copyright","label":"Copyright"}]}}