{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:28:22Z","timestamp":1770917302072,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:00:00Z","timestamp":1665014400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T00:00:00Z","timestamp":1665014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s13735-022-00258-1","type":"journal-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T15:10:23Z","timestamp":1665069023000},"page":"525-538","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Prototype local\u2013global alignment network for image\u2013text retrieval"],"prefix":"10.1007","volume":"11","author":[{"given":"Lingtao","family":"Meng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8153-9977","authenticated-orcid":false,"given":"Feifei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"258_CR1","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2018) Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"258_CR2","doi-asserted-by":"crossref","unstructured":"Chen H, Ding G, Liu X, Lin Z, Liu J, Han J (2020) Imram: iterative matching with recurrent attention memory for cross-modal image-text retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 12655\u201312663","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"258_CR3","doi-asserted-by":"crossref","unstructured":"Chen J, Hu H, Wu H, Jiang Y, Wang C (2021) Learning the best pooling strategy for visual semantic embedding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 15789\u201315798","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"258_CR4","first-page":"10583","volume":"34","author":"T Chen","year":"2020","unstructured":"Chen T, Luo J (2020) Expressing objects just like words: recurrent visual embedding for image-text matching. Proc Assoc Adv Artif Intell (AAAI) 34:10583\u201310590","journal-title":"Proc Assoc Adv Artif Intell (AAAI)"},{"key":"258_CR5","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In; Proceedings of the conference of the North American chapter of the association for computational linguistics (ACL), pp 4171\u20134186"},{"key":"258_CR6","doi-asserted-by":"crossref","unstructured":"Diao H, Zhang Y, Ma L, Lu H (2021) Similarity reasoning and filtration for image-text matching. In: Proceedings of the association for the advance of artificial intelligence (AAAI)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"258_CR7","unstructured":"Faghri F, Fleet DJ, Kiros JR, Fidler S Vse+ (2017) Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612"},{"key":"258_CR8","unstructured":"Ge Y, Zhu F, Chen D, Zhao R et al (2020) Self-paced contrastive learning with hybrid memory for domain adaptive object re-id. In: Proceedings of the conference and workshop on neural information processing systems (NIPS) 33:11309\u201311321"},{"key":"258_CR9","unstructured":"Jocher G et al (2021) Yolov5. https:\/\/github.com\/ultralytics\/yolov5"},{"key":"258_CR10","doi-asserted-by":"crossref","unstructured":"Gu J, Cai J, Joty SR, Niu L, Wang G (2018) Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 7181\u20137189","DOI":"10.1109\/CVPR.2018.00750"},{"issue":"5","key":"258_CR11","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MSP.2008.926652","volume":"25","author":"X He","year":"2008","unstructured":"He X, Deng L, Chou W (2008) Discriminative learning in sequential pattern recognition. IEEE Signal Process Mag (SPM) 25(5):14\u201336","journal-title":"IEEE Signal Process Mag (SPM)"},{"key":"258_CR12","doi-asserted-by":"crossref","unstructured":"Hu P, Peng X, Zhu H, Zhen L, Lin J (2021) Learning cross-modal retrieval with noisy labels. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5403\u20135413","DOI":"10.1109\/CVPR46437.2021.00536"},{"key":"258_CR13","doi-asserted-by":"crossref","unstructured":"Huang Y, Wang W, Wang L (2017) Instance-aware image and sentence matching with selective multimodal lstm. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 2310\u20132318","DOI":"10.1109\/CVPR.2017.767"},{"key":"258_CR14","doi-asserted-by":"crossref","unstructured":"Huang Y, Wu Q, Song C, Wang L (2018) Learning semantic concepts and order for image and sentence matching. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 6163\u20136171","DOI":"10.1109\/CVPR.2018.00645"},{"key":"258_CR15","doi-asserted-by":"crossref","unstructured":"Ji Z, Wang H, Han J, Pang Y (2019) Saliency-guided attention network for image-sentence matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5754\u20135763","DOI":"10.1109\/ICCV.2019.00585"},{"key":"258_CR16","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"258_CR17","unstructured":"Karpathy A, Joulin A, Fei-Fei L (2014) Deep fragment embeddings for bidirectional image sentence mapping. arXiv:1406.5679"},{"key":"258_CR18","unstructured":"Klein B, Lev G, Sadeh G, Wolf L (2015) Fisher vectors derived from hybrid gaussian-laplacian mixture models for image annotation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4437\u20134446"},{"issue":"1","key":"258_CR19","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"K Ranjay","year":"2017","unstructured":"Ranjay K, Yuke Z, Oliver G, Justin J, Kenji H, Joshua K, Stephanie C, Yannis K, Li-Jia L, Shamma David A et al (2017) Visual genome: connecting language and vision using crowdsourced dense image annotations. Int J Comput Vis (IJCV) 123(1):32\u201373","journal-title":"Int J Comput Vis (IJCV)"},{"key":"258_CR20","doi-asserted-by":"crossref","unstructured":"Lee K-H, Chen X, Hua G, Hu H, He X (2018) Stacked cross attention for image-text matching. In: Proceedings of the European conference on computer vision (ECCV), pp 201\u2013216","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"258_CR21","unstructured":"Li J, Zhou P, Xiong C, Hoi Steven\u00a0CH (2020) Prototypical contrastive learning of unsupervised representations. arXiv:2005.04966"},{"key":"258_CR22","doi-asserted-by":"crossref","unstructured":"Li K, Zhang Y, Li K, Li Y, Fu Y (2019) Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4654\u20134662","DOI":"10.1109\/ICCV.2019.00475"},{"key":"258_CR23","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Proceedings of the European conference on computer vision (ECCV), pp 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"258_CR24","unstructured":"Chunxiao L, Zhendong M, Tianzhu Z, Hongtao X, Bin W, Yongdong Z (2020) Graph structured network for image-text matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10921\u201310930"},{"key":"258_CR25","doi-asserted-by":"crossref","unstructured":"Liu Y, Guo Y, Bakker EM, Lew MS (2017) Learning a recurrent residual fusion network for multimodal matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4107\u20134116","DOI":"10.1109\/ICCV.2017.442"},{"key":"258_CR26","doi-asserted-by":"crossref","unstructured":"Nam H, Ha J-W, Kim J (2017) Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 299\u2013307","DOI":"10.1109\/CVPR.2017.232"},{"key":"258_CR27","doi-asserted-by":"crossref","unstructured":"Niu Z, Zhou M, Wang L, Gao X, Hua G (2017) Hierarchical multimodal lstm for dense visual-semantic embedding. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 1881\u20131889","DOI":"10.1109\/ICCV.2017.208"},{"key":"258_CR28","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic Differentiation in PyTorch. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems (NIPS). https:\/\/openreview.net\/forum?id=BJJsrmfCZ"},{"key":"258_CR29","doi-asserted-by":"crossref","unstructured":"Peng Y, Qi J (2019) CM-GANs: Cross-modal generative adversarial networks for common representation learning. ACM Trans Multimed Comput Commun Appl (TOMM) 15(1):1\u201324","DOI":"10.1145\/3284750"},{"key":"258_CR30","unstructured":"Peng Y, Huang X, Qi J (2016) Cross-media shared representation by hierarchical learning with multiple deep networks. In: International joint conferences on artificial intelligence organization (IJCAI), pp 3846\u20133853"},{"key":"258_CR31","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: towards real-time object detection with region proposal networks. In: Proceedings of the conference and workshop on neural information processing systems (NIPS) 28:91\u201399"},{"key":"258_CR32","doi-asserted-by":"crossref","unstructured":"Salvador A, Gundogdu E, Bazzani L, Donoser M (2021) Revamping cross-modal recipe retrieval with hierarchical transformers and self-supervised learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 15475\u201315484","DOI":"10.1109\/CVPR46437.2021.01522"},{"key":"258_CR33","doi-asserted-by":"crossref","unstructured":"Sarafianos N, Xu X, Kakadiaris IA (2019) Adversarial representation learning for text-to-image matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5814\u20135824","DOI":"10.1109\/ICCV.2019.00591"},{"key":"258_CR34","unstructured":"Snell J, Swersky K, Zemel RS (2017) Prototypical networks for few-shot learning. arXiv:1703.05175"},{"key":"258_CR35","unstructured":"Toyama J, Misono M, Suzuki M, Nakayama K, Matsuo Y (2016) Neural machine translation with latent semantic of image and text. arXiv:1611.08459"},{"key":"258_CR36","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN , Kaiser \u0141, Polosukhin I (2017) Attention is all you need. In: Proceedings of the conference and workshop on neural information processing systems (NIPS), vol\u00a030"},{"key":"258_CR37","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang Y, Ji Z, Pang Y, Ma L (2020) Consensus-aware visual-semantic embedding for image-text matching. In: Proceedings of the European conference on computer vision (ECCV), pp 18\u201334. Springer","DOI":"10.1007\/978-3-030-58586-0_2"},{"key":"258_CR38","doi-asserted-by":"crossref","unstructured":"Wang L, Li Y, Lazebnik S (2016) Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 5005\u20135013","DOI":"10.1109\/CVPR.2016.541"},{"issue":"2","key":"258_CR39","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang L, Li Y, Huang J, Lazebnik S (2018) Learning two-branch neural networks for image-text matching tasks. IEEE Trans Pattern Anal Mach Intell (TPAMI) 41(2):394\u2013407","journal-title":"IEEE Trans Pattern Anal Mach Intell (TPAMI)"},{"key":"258_CR40","doi-asserted-by":"crossref","unstructured":"Wang S, Wang R, Yao Z, Shan S, Chen X (2020) Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV), pp 1508\u20131517","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"258_CR41","doi-asserted-by":"crossref","unstructured":"Wang X, Liu Z, Yu SX (2021) Unsupervised feature learning by cross-level instance-group discrimination. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 12586\u201312595","DOI":"10.1109\/CVPR46437.2021.01240"},{"key":"258_CR42","doi-asserted-by":"crossref","unstructured":"Wang Z, Fang Z, Wang J, Yang Y (2020) Vitaa: visual-textual attributes alignment in person search by natural language. In: Proceedings of the European conference on computer vision (ECCV), pp 402\u2013420. Springer","DOI":"10.1007\/978-3-030-58610-2_24"},{"key":"258_CR43","doi-asserted-by":"crossref","unstructured":"Wehrmann J, Kolling C, Barros RC (2020) Adaptive cross-modal embeddings for image-text alignment. In: Proceedings of the association for the advance of artificial intelligence (AAAI), vol\u00a034, pp 12313\u201312320","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"258_CR44","doi-asserted-by":"crossref","unstructured":"Wei X, Zhang T, Li Y, Zhang Y, Feng W (2020) Multi-modality cross attention network for image and sentence matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 10941\u201310950","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"258_CR45","doi-asserted-by":"crossref","unstructured":"Yan F, Mikolajczyk K (2015) Deep correlation for matching images and text. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3441\u20133450","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"258_CR46","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist (TACL) 2:67\u201378","journal-title":"Trans Assoc Comput Linguist (TACL)"},{"key":"258_CR47","doi-asserted-by":"crossref","unstructured":"Zhang Q, Lei Z, Zhang Z, Li SZ (2020) Context-aware attention network for image-text retrieval. In; Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3536\u20133545","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"258_CR48","doi-asserted-by":"crossref","unstructured":"Zhang X, Ge Y, Qiao Y, Li H (2021) Refining pseudo labels with clustering consensus over generations for unsupervised object re-identification. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 3436\u20133445","DOI":"10.1109\/CVPR46437.2021.00344"},{"issue":"2","key":"258_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3383184","volume":"16","author":"Z Zheng","year":"2020","unstructured":"Zheng Z, Zheng L, Garrett M, Yang Y, Xu M, Shen Y-D (2020) Dual-path convolutional image-text embeddings with instance loss. ACM Trans Multimed Comput Commun Appl (TOMM) 16(2):1\u201323","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00258-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-022-00258-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-022-00258-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T14:23:44Z","timestamp":1671287024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-022-00258-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,6]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["258"],"URL":"https:\/\/doi.org\/10.1007\/s13735-022-00258-1","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,6]]},"assertion":[{"value":"22 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 October 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}