{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T21:13:43Z","timestamp":1757452423546,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T00:00:00Z","timestamp":1568419200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T00:00:00Z","timestamp":1568419200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100004462","name":"Consiglio Nazionale delle Ricerche","doi-asserted-by":"publisher","award":["CUP CIPE D55F17000290009"],"award-info":[{"award-number":["CUP CIPE D55F17000290009"]}],"id":[{"id":"10.13039\/501100004462","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s13735-019-00178-7","type":"journal-article","created":{"date-parts":[[2019,9,14]],"date-time":"2019-09-14T04:13:36Z","timestamp":1568434416000},"page":"113-124","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Learning visual features for relational CBIR"],"prefix":"10.1007","volume":"9","author":[{"given":"Nicola","family":"Messina","sequence":"first","affiliation":[]},{"given":"Giuseppe","family":"Amato","sequence":"additional","affiliation":[]},{"given":"Fabio","family":"Carrara","sequence":"additional","affiliation":[]},{"given":"Fabrizio","family":"Falchi","sequence":"additional","affiliation":[]},{"given":"Claudio","family":"Gennaro","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,14]]},"reference":[{"key":"178_CR1","doi-asserted-by":"crossref","unstructured":"Antol S, Agrawal A, Lu J, Mitchell M, Batra D, Zitnick CL, Parikh D (2015) VQA: visual question answering. CoRR \narXiv:1505.00468","DOI":"10.1109\/ICCV.2015.279"},{"key":"178_CR2","unstructured":"Belilovsky E, Blaschko MB, Kiros JR, Urtasun R, Zemel R (2017) Joint embeddings of scene graphs and images. ICLR"},{"key":"178_CR3","unstructured":"Cai H, Zheng VW, Chang KC (2017) A comprehensive survey of graph embedding: problems, techniques and applications. CoRR \narXiv:1709.07604"},{"key":"178_CR4","doi-asserted-by":"crossref","unstructured":"Dai B, Zhang Y, Lin D (2017) Detecting visual relationships with deep relational networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 3298\u20133308. IEEE","DOI":"10.1109\/CVPR.2017.352"},{"key":"178_CR5","unstructured":"Gordo A, Almazan J, Revaud J, Larlus D (2016) End-to-end learning of deep visual representations for image retrieval. arXiv preprint \narXiv:1610.07940"},{"key":"178_CR6","doi-asserted-by":"crossref","unstructured":"Hu R, Andreas J, Rohrbach M, Darrell T, Saenko K (2017) Learning to reason: end-to-end module networks for visual question answering. In: The IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.93"},{"key":"178_CR7","doi-asserted-by":"crossref","unstructured":"Johnson J, Hariharan B, van\u00a0der Maaten L, Fei-Fei L, Zitnick CL, Girshick R (2017) Clevr: a diagnostic dataset for compositional language and elementary visual reasoning","DOI":"10.1109\/CVPR.2017.215"},{"key":"178_CR8","doi-asserted-by":"crossref","unstructured":"Johnson J, Hariharan B, van\u00a0der Maaten L, Hoffman J, Fei-Fei L, Lawrence\u00a0Zitnick C, Girshick R (2017) Inferring and executing programs for visual reasoning. In: The IEEE international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2017.325"},{"key":"178_CR9","doi-asserted-by":"crossref","unstructured":"Johnson J, Krishna R, Stark M, Li LJ, Shamma D, Bernstein M, Fei-Fei L (2015) Image retrieval using scene graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3668\u20133678","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"178_CR10","unstructured":"Kahou SE, Atkinson A, Michalski V, K\u00e1d\u00e1r \u00c1, Trischler A, Bengio Y (2017) Figureqa: an annotated figure dataset for visual reasoning. CoRR \narXiv:1710.07300"},{"key":"178_CR11","doi-asserted-by":"crossref","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li LJ, Shamma DA, Bernstein M, Fei-Fei L (2016) Visual genome: connecting language and vision using crowdsourced dense image annotations","DOI":"10.1007\/s11263-016-0981-7"},{"key":"178_CR12","unstructured":"Kuznetsova A, Rom H, Alldrin N, Uijlings JRR, Krasin I, Pont-Tuset J, Kamali S, Popov S, Malloci M, Duerig T, Ferrari V (2018) The open images dataset V4: unified image classification, object detection, and visual relationship detection at scale. CoRR \narXiv:1811.00982"},{"key":"178_CR13","doi-asserted-by":"crossref","unstructured":"Lu C, Krishna R, Bernstein M, Fei-Fei L (2016) Visual relationship detection with language priors. In: European conference on computer vision","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"178_CR14","doi-asserted-by":"crossref","unstructured":"Lu P, Ji L, Zhang W, Duan N, Zhou M, Wang J (2018) R-VQA: learning visual relation facts with semantic attention for visual question answering. In: SIGKDD 2018","DOI":"10.1145\/3219819.3220036"},{"key":"178_CR15","unstructured":"Malinowski M, Fritz M (2014) A multi-world approach to question answering about real-world scenes based on uncertain input. In: Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger K (eds) Advances in neural information processing systems 27. Curran Associates Inc, pp 1682\u20131690"},{"key":"178_CR16","doi-asserted-by":"crossref","unstructured":"Mascharka D, Tran P, Soklaski R, Majumdar A (2018) Transparency by design: closing the gap between performance and interpretability in visual reasoning. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00519"},{"issue":"1","key":"178_CR17","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1145\/1273221.1273223","volume":"41","author":"M Melucci","year":"2007","unstructured":"Melucci M (2007) On rank correlation in information retrieval evaluation. SIGIR Forum 41(1):18\u201333. \nhttps:\/\/doi.org\/10.1145\/1273221.1273223","journal-title":"SIGIR Forum"},{"key":"178_CR18","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1007\/978-3-030-11018-5_40","volume-title":"Computer vision: ECCV 2018 workshops","author":"N Messina","year":"2019","unstructured":"Messina N, Amato G, Carrara F, Falchi F, Gennaro C (2019) Learning relationship-aware visual features. In: Leal-Taix\u00e9 L, Roth S (eds) Computer vision: ECCV 2018 workshops. Springer, Cham, pp 486\u2013501"},{"key":"178_CR19","doi-asserted-by":"crossref","unstructured":"Peyre J, Laptev I, Schmid C, Sivic J (2017) Weakly-supervised learning of visual relations. In: ICCV 2017\u2014international conference on computer vision 2017. Venice, Italy. \nhttps:\/\/hal.archives-ouvertes.fr\/hal-01576035","DOI":"10.1109\/ICCV.2017.554"},{"key":"178_CR20","unstructured":"Qi M, Li W, Yang Z, Wang Y, Luo J (2018) Attentive relational networks for mapping images to scene graphs. CoRR \narXiv:1811.10696"},{"key":"178_CR21","unstructured":"Raposo D, Santoro A, Barrett DGT, Pascanu R, Lillicrap TP, Battaglia PW (2017) Discovering objects and their relations from entangled scene representations. CoRR \narXiv:1702.05068"},{"key":"178_CR22","unstructured":"Ren M, Kiros R, Zemel R (2015) Exploring models and data for image question answering. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28. Curran Associates Inc, pp 2953\u20132961"},{"key":"178_CR23","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Cortes C, Lawrence ND, Lee DD, Sugiyama M, Garnett R (eds) Advances in neural information processing systems 28. Curran Associates Inc, pp 91\u201399"},{"issue":"7","key":"178_CR24","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1016\/j.imavis.2008.04.004","volume":"27","author":"K Riesen","year":"2009","unstructured":"Riesen K, Bunke H (2009) Approximate graph edit distance computation by means of bipartite graph matching. Image Vis Comput 27(7):950\u2013959. \nhttps:\/\/doi.org\/10.1016\/j.imavis.2008.04.004","journal-title":"Image Vis Comput"},{"key":"178_CR25","unstructured":"Santoro A, Raposo D, Barrett DG, Malinowski M, Pascanu R, Battaglia P, Lillicrap T (2017) A simple neural network module for relational reasoning. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems 30. Curran Associates Inc, pp 4967\u20134976"},{"key":"178_CR26","unstructured":"Tolias G, Sicre R, J\u00e9gou H (2015) Particular object retrieval with integral max-pooling of CNN activations. arXiv preprint \narXiv:1511.05879"},{"key":"178_CR27","doi-asserted-by":"crossref","unstructured":"Yang J, Lu J, Lee S, Batra D, Parikh D (2018) Graph R-CNN for scene graph generation. CoRR \narXiv:1808.00191","DOI":"10.1007\/978-3-030-01246-5_41"},{"key":"178_CR28","unstructured":"Yang Z, He X, Gao J, Deng L, Smola AJ (2015) Stacked attention networks for image question answering. CoRR \narXiv:1511.02274"},{"key":"178_CR29","doi-asserted-by":"crossref","unstructured":"Yao T, Pan Y, Li Y, Mei T (2018) Exploring visual relationship for image captioning. CoRR \narXiv:1809.07041","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"178_CR30","unstructured":"Zhang J, Kalantidis Y, Rohrbach M, Paluri M, Elgammal AM, Elhoseiny M (2018) Large-scale visual relationship understanding. CoRR \narXiv:1804.10660"},{"key":"178_CR31","unstructured":"Zhou, B., Tian, Y., Sukhbaatar, S., Szlam, A., Fergus R (2015) Simple baseline for visual question answering. CoRR \narXiv:1512.02167"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-019-00178-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13735-019-00178-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-019-00178-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,14]],"date-time":"2020-09-14T09:31:59Z","timestamp":1600075919000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13735-019-00178-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,14]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["178"],"URL":"https:\/\/doi.org\/10.1007\/s13735-019-00178-7","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"type":"print","value":"2192-6611"},{"type":"electronic","value":"2192-662X"}],"subject":[],"published":{"date-parts":[[2019,9,14]]},"assertion":[{"value":"15 April 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 September 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 September 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}