{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:46:44Z","timestamp":1762325204700,"version":"3.37.3"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:00:00Z","timestamp":1642377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s11760-021-02020-2","type":"journal-article","created":{"date-parts":[[2022,1,17]],"date-time":"2022-01-17T00:04:05Z","timestamp":1642377845000},"page":"797-805","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DADAN: dual-path attention with distribution analysis network for text-image matching"],"prefix":"10.1007","volume":"16","author":[{"given":"Wenhao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2122-7066","authenticated-orcid":false,"given":"Hongqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suyi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,17]]},"reference":[{"key":"2020_CR1","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s11760-019-01534-0","volume":"15","author":"L Yifan","year":"2021","unstructured":"Yifan, L., Xuan, W., Shuhan, Q., Chengkai, H., Zoe, J., et al.: Self-supervised learning-based weight adaptive hashing for fast cross-modal retrieval. Signal Image Video Process. 15, 673\u2013680 (2021)","journal-title":"Signal Image Video Process."},{"key":"2020_CR2","unstructured":"Faghri, F., Fleet, D. J., Kiros, J. R., et\u00a0al.: VSE++: Improving visual-semantic embeddings with hard negatives. In: Proc. British. Mach Vision Conf. pp. 935\u2013943 (2018)"},{"key":"2020_CR3","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guo, Y., Bakker, E. M., et\u00a0al.: Learning a recurrent residual fusion network for multimodal matching. In: Proc. IEEE Int. Conf. Comput. Vision., pp. 4107\u20134116 (2017)","DOI":"10.1109\/ICCV.2017.442"},{"key":"2020_CR4","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal LSTM. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2310\u20132318 (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"2020_CR5","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., et\u00a0al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"2020_CR6","doi-asserted-by":"crossref","unstructured":"Lee, K. H., Chen, X., Hua, G., et\u00a0al.: Stacked cross attention for image-text matching. In: Proc. European Conf. Comput. Vision., pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"2020_CR7","unstructured":"Lee, K. H., Palangi, H., Chen, X., et\u00a0al.: Learning visual relation priors for image-text matching and image captioning with neural scene graph generators. arXiv preprint arXiv:1909.09953 (2019)"},{"key":"2020_CR8","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, X., Li, H., et\u00a0al.: CAMP: Cross-modal adaptive message passing for text-image retrieval. In: Proc. IEEE Int. Conf. Comput Vision., pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"2020_CR9","doi-asserted-by":"publisher","first-page":"1180","DOI":"10.1109\/TIP.2020.3042086","volume":"30","author":"Z Wen","year":"2021","unstructured":"Wen, Z., Xin, W., Jie, L.: Cross-domain image captioning via cross-modal retrieval and model adaptation. IEEE Trans. Image Process. 30, 1180\u20131192 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2020_CR10","doi-asserted-by":"crossref","unstructured":"Liu, C., Mao, Z., Liu, A. A., et al: Focus your attention: a bidirectional focal attention network for image-text matching. In: Proc 27th ACM Int Conf. Multimedia, pp. 3\u201311 (2019)","DOI":"10.1145\/3343031.3350869"},{"key":"2020_CR11","doi-asserted-by":"crossref","unstructured":"Xia, Y., Huang, L., Wang, W., et\u00a0al.: Exploring entity-Level spatial relationships for image-text matching. In: Proc. IEEE Int. Conf. Acoustics, Speech, Signal Process., pp. 4452\u20134456 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054758"},{"key":"2020_CR12","doi-asserted-by":"crossref","unstructured":"Wang, S., Wang, R., Yao, Z., et\u00a0al.: Cross-modal scene graph matching for relationship-aware image-text retrieval. In: Proc. IEEE Winter Conf. Applications of Comput. Vision, pp. 1508\u20131517 (2020)","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"2020_CR13","doi-asserted-by":"publisher","first-page":"38438","DOI":"10.1109\/ACCESS.2020.2975594","volume":"8","author":"Z Ji","year":"2020","unstructured":"Ji, Z., Lin, Z., Wang, H., et al.: Multi-modal memory enhancement attention network for image-text matching. IEEE Access 8, 38438\u201338447 (2020)","journal-title":"IEEE Access"},{"issue":"62","key":"2020_CR14","first-page":"1137","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(62), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2020_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et\u00a0al.: Deep residual learning for image recognition. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2020_CR16","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"2020_CR17","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van Gool, L.: Efficient non-maximum suppression. In: Proc. IEEE Int. Conf. Pattern Recognit., pp. 850\u2013855 (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"2020_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T. Y., Maire, M., Belongie, S., et\u00a0al.: Microsoft COCO: Common objects in context. In: Proc. European Conf. Comput. Vision., pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2020_CR19","doi-asserted-by":"crossref","unstructured":"Plummer, B. A., Wang, L., Cervantes, C. M., et\u00a0al.: Flickr 30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proc. IEEE Int. Conf. Comput. Vision., pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"2020_CR20","doi-asserted-by":"crossref","unstructured":"Niu, Z., Zhou, M., Wang, L., et\u00a0al.: Hierarchical multimodal lstm for dense visual-semantic embedding. In: Proc. IEEE Int. Conf. Comput Vision., pp. 1881\u20131889 (2017)","DOI":"10.1109\/ICCV.2017.208"},{"key":"2020_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wu, Q., Song, C., et\u00a0al.: Learning semantic concepts and order for image and sentence matching. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 6163\u20136171 (2018)","DOI":"10.1109\/CVPR.2018.00645"},{"key":"2020_CR22","doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S. R., Niu, L., Wang, G.: Look, imagine and match: Improving textual-visual cross-modal retrieval with generative models. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 7181\u20137189 (2018)","DOI":"10.1109\/CVPR.2018.00750"},{"key":"2020_CR23","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02020-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-021-02020-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-021-02020-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T12:02:18Z","timestamp":1726488138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-021-02020-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,17]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["2020"],"URL":"https:\/\/doi.org\/10.1007\/s11760-021-02020-2","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2022,1,17]]},"assertion":[{"value":"23 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}