{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:09:55Z","timestamp":1742933395674,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031783043"},{"type":"electronic","value":"9783031783050"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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\/978-3-031-78305-0_5","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T10:14:06Z","timestamp":1733220846000},"page":"63-79","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Novel Clustering Aggregation and Multi-grained Alignment for Image-Text Matching"],"prefix":"10.1007","author":[{"given":"Shuming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donglin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"issue":"11","key":"5_CR1","doi-asserted-by":"publisher","first-page":"2274","DOI":"10.1109\/TPAMI.2012.120","volume":"34","author":"R Achanta","year":"2012","unstructured":"Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., S\u00fcsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274\u20132282 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., Zhang, L.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"5_CR3","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":"5_CR4","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Liu, W., Ruan, X., Lu, H.: Plug-and-play regulators for image-text matching. IEEE Transactions on Image Processing (2023)","DOI":"10.1109\/TIP.2023.3266887"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Diao, H., Zhang, Y., Ma, L., Lu, H.: Similarity reasoning and filtration for image-text matching. In: Proceedings of the AAAI conference on artificial intelligence. vol.\u00a035, pp. 1218\u20131226 (2021)","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"5_CR6","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)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Kumari, N., Zhang, B., Zhang, R., Shechtman, E., Zhu, J.Y.: Multi-concept customization of text-to-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1931\u20131941 (2023)","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"5_CR8","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":"5_CR9","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5_CR10","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":"5_CR11","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5_CR12","unstructured":"Ma, X., Zhou, Y., Wang, H., Qin, C., Sun, B., Liu, C., Fu, Y.: Image as set of points. arXiv preprint arXiv:2303.01494 (2023)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Esuli, A., Falchi, F., Gennaro, C., Marchand-Maillet, S.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM) 17(4), 1\u201323 (2021)","DOI":"10.1145\/3451390"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Messina, N., Falchi, F., Esuli, A., Amato, G.: Transformer reasoning network for image-text matching and retrieval. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 5222\u20135229. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9413172"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Pont-Tuset, J., Uijlings, J., Changpinyo, S., Soricut, R., Ferrari, V.: Connecting vision and language with localized narratives (2019)","DOI":"10.1007\/978-3-030-58558-7_38"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, M., Wu, J., Gao, Z., Nie, L.: Dynamic modality interaction modeling for image-text retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. pp. 1104\u20131113 (2021)","DOI":"10.1145\/3404835.3462829"},{"key":"5_CR17","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Shi, B., Ji, L., Lu, P., Niu, Z., Duan, N.: Knowledge aware semantic concept expansion for image-text matching. In: IJCAI. vol.\u00a01, p.\u00a02 (2019)","DOI":"10.24963\/ijcai.2019\/720"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, H., Qian, X., Ma, L., Lu, J., Li, B., Fan, X.: Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 (2019)","DOI":"10.24963\/ijcai.2019\/526"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Yan, S., Yu, L., Xie, Y.: Discrete-continuous action space policy gradient-based attention for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8096\u20138105 (2021)","DOI":"10.1109\/CVPR46437.2021.00800"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Yang, F., Sun, Q., Jin, H., Zhou, Z.: Superpixel segmentation with fully convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 13964\u201313973 (2020)","DOI":"10.1109\/CVPR42600.2020.01398"},{"key":"5_CR23","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.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics 2, 67\u201378 (2014)","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wu, X.J., Liu, Z., Yu, J., Kitter, J.: Fast discrete cross-modal hashing based on label relaxation and matrix factorization. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 4845\u20134850. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412497"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wu, X.J., Yu, J.: Discrete bidirectional matrix factorization hashing for zero-shot cross-media retrieval. In: Chinese conference on pattern recognition and computer vision (PRCV). pp. 524\u2013536. Springer (2021)","DOI":"10.1007\/978-3-030-88007-1_43"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, H., Mao, Z., Zhang, K., Zhang, Y.: Show your faith: Cross-modal confidence-aware network for image-text matching. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 3262\u20133270 (2022)","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mao, Z., Wang, Q., Zhang, Y.: Negative-aware attention framework for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15661\u201315670 (2022)","DOI":"10.1109\/CVPR52688.2022.01521"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78305-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T11:11:01Z","timestamp":1733224261000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78305-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031783043","9783031783050"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78305-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}