{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:30:13Z","timestamp":1742949013077,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787944"},{"type":"electronic","value":"9789819787951"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8795-1_21","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:03:27Z","timestamp":1730588607000},"page":"306-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fine-grained Feature Assisted Cross-modal Image-text Retrieval"],"prefix":"10.1007","author":[{"given":"Chaofei","family":"Bu","sequence":"first","affiliation":[]},{"given":"Xueliang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Yuling","family":"Su","sequence":"additional","affiliation":[]},{"given":"Junfeng","family":"Tu","sequence":"additional","affiliation":[]},{"given":"Richang","family":"Hong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Bu, H.H., Kim, N.C., Kim, S.H.: Content-based image retrieval using a fusion of global and local features. ETRI J. (2023)","DOI":"10.4218\/etrij.2022-0071"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., Han, J.: 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, pp. 12655\u201312663 (2020)","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., El\u00a0Kholy, A., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: Uniter: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Cheng, M., Sun, Y., Wang, L., Zhu, X., Yao, K., Chen, J., Song, G., Han, J., Liu, J., Ding, E., et\u00a0al.: Vista: vision and scene text aggregation for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5184\u20135193 (2022)","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Chopra, S., Hadsell, R., LeCun, Y.: Learning a similarity metric discriminatively, with application to face verification. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol.\u00a01, pp. 539\u2013546. IEEE (2005)","DOI":"10.1109\/CVPR.2005.202"},{"key":"21_CR6","unstructured":"Chun, S.: Improved probabilistic image-text representations. arXiv preprint arXiv:2305.18171 (2023)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Chun, S., Oh, S.J., De\u00a0Rezende, R.S., Kalantidis, Y., Larlus, D.: Probabilistic embeddings for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8415\u20138424 (2021)","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yu, Z., Wang, C., Zhao, Z., Zhang, J., Wang, M., Yu, J.: Rosita: enhancing vision-and-language semantic alignments via cross-and intra-modal knowledge integration. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 797\u2013806 (2021)","DOI":"10.1145\/3474085.3475251"},{"key":"21_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR10","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"21_CR11","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: Vse++: improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)"},{"issue":"10","key":"21_CR12","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.3390\/math11102279","volume":"11","author":"L He","year":"2023","unstructured":"He, L., Liu, S., An, R., Zhuo, Y., Tao, J.: An end-to-end framework based on vision-language fusion for remote sensing cross-modal text-image retrieval. Mathematics 11(10), 2279 (2023)","journal-title":"Mathematics"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Hu, R., Singh, A., Darrell, T., Rohrbach, M.: Iterative answer prediction with pointer-augmented multimodal transformers for textvqa. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9992\u201310002 (2020)","DOI":"10.1109\/CVPR42600.2020.01001"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Y., Wang, W., Wang, L.: Instance-aware image and sentence matching with selective multimodal lstm. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2310\u20132318 (2017)","DOI":"10.1109\/CVPR.2017.767"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Ji, Z., Chen, K., Wang, H.: Step-wise hierarchical alignment network for image-text matching. arXiv preprint arXiv:2106.06509 (2021)","DOI":"10.24963\/ijcai.2021\/106"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Ji, Z., Wang, H., Han, J., Pang, Y.: Saliency-guided attention network for image-sentence matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5754\u20135763 (2019)","DOI":"10.1109\/ICCV.2019.00585"},{"key":"21_CR17","unstructured":"Jia, C., Yang, Y., Xia, Y., Chen, Y.T., Parekh, Z., Pham, H., Le, Q., Sung, Y.H., Li, Z., Duerig, T.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"21_CR19","doi-asserted-by":"crossref","unstructured":"Kim, D., Kim, N., Kwak, S.: Improving cross-modal retrieval with set of diverse embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23422\u201323431 (2023)","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Kuo, C.W., Kira, Z.: Beyond a pre-trained object detector: cross-modal textual and visual context for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17969\u201317979 (2022)","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"21_CR22","unstructured":"Li, H., Song, J., Gao, L., Zhu, X., Shen, H.: Prototype-based aleatoric uncertainty quantification for cross-modal retrieval. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"21_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Mafla, A., Rezende, R.S., Gomez, L., Larlus, D., Karatzas, D.: Stacmr: scene-text aware cross-modal retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2220\u20132230 (2021)","DOI":"10.1109\/WACV48630.2021.00227"},{"key":"21_CR26","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Ren, S., Lin, J., Zhao, G., Men, R., Yang, A., Zhou, J., Sun, X., Yang, H.: Learning relation alignment for calibrated cross-modal retrieval. arXiv preprint arXiv:2105.13868 (2021)","DOI":"10.18653\/v1\/2021.acl-long.43"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"21_CR29","unstructured":"Wang, C.Y., Yeh, I.H., Liao, H.Y.M.: You only learn one representation: unified network for multiple tasks. arXiv preprint arXiv:2105.04206 (2021)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Wang, T., Xu, X., Yang, Y., Hanjalic, A., Shen, H.T., Song, J.: Matching images and text with multi-modal tensor fusion and re-ranking. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 12\u201320 (2019)","DOI":"10.1145\/3343031.3350875"},{"key":"21_CR31","first-page":"1","volume":"60","author":"Z Yuan","year":"2022","unstructured":"Yuan, Z., Zhang, W., Tian, C., Rong, X., Zhang, Z., Wang, H., Fu, K., Sun, X.: Remote sensing cross-modal text-image retrieval based on global and local information. IEEE Trans. Geosci. Remote Sens. 60, 1\u201316 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Zeng, S., Liu, C., Zhou, J., Chen, Y., Jiang, A., Li, H.: Learning hierarchical semantic correspondences for cross-modal image-text retrieval. In: Proceedings of the 2022 International Conference on Multimedia Retrieval, pp. 239\u2013248 (2022)","DOI":"10.1145\/3512527.3531358"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, H., Ye, M.: Negative pre-aware for noisy cross-modal matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 7341\u20137349 (2024)","DOI":"10.1609\/aaai.v38i7.28564"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, H.: Deep cross-modal projection learning for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 686\u2013701 (2018)","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8795-1_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:04:58Z","timestamp":1730588698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8795-1_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819787944","9789819787951"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8795-1_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}