{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T04:19:01Z","timestamp":1743826741782,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031887109","type":"print"},{"value":"9783031887116","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-88711-6_11","type":"book-chapter","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T17:14:28Z","timestamp":1743786868000},"page":"169-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MVAM: Multi-View Attention Method for\u00a0Fine-Grained Image-Text Matching"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5015-5252","authenticated-orcid":false,"given":"Wanqing","family":"Cui","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1530-190X","authenticated-orcid":false,"given":"Rui","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5201-8195","authenticated-orcid":false,"given":"Xueqi","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,4]]},"reference":[{"key":"11_CR1","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":"11_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: Spatext: spatio-textual representation for controllable image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18370\u201318380 (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: learning universal image-text representations (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR5","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":"11_CR6","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"11_CR7","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\,\\times \\,$$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR8","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":"11_CR9","doi-asserted-by":"crossref","unstructured":"He, W., Jamonnak, S., Gou, L., Ren, L.: CLIP-S4: language-guided self-supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11207\u201311216 (2023)","DOI":"10.1109\/CVPR52729.2023.01078"},{"key":"11_CR10","unstructured":"Humeau, S., Shuster, K., Lachaux, M.A., Weston, J.: Poly-encoders: transformer architectures and pre-training strategies for fast and accurate multi-sentence scoring. arXiv preprint arXiv:1905.01969 (2019)"},{"key":"11_CR11","unstructured":"Huo, Y., et\u00a0al.: WenLan: bridging vision and language by large-scale multi-modal pre-training. arXiv preprint arXiv:2103.06561 (2021)"},{"key":"11_CR12","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"11_CR13","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":"11_CR14","doi-asserted-by":"crossref","unstructured":"Khattab, O., Zaharia, M.: ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 39\u201348 (2020)","DOI":"10.1145\/3397271.3401075"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: DiffusionCLIP: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"11_CR16","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":"11_CR17","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Bak, S., Carr, P., Wang, X.: Diversity regularized spatiotemporal attention for video-based person re-identification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 369\u2013378 (2018)","DOI":"10.1109\/CVPR.2018.00046"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., et\u00a0al.: Oscar: Object-semantics aligned pre-training for vision-language tasks. In: European Conference on Computer Vision, pp. 121\u2013137. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Fan, Z., Tou, H., Chen, J., Wei, Z., Huang, X.: MVPTR: multi-level semantic alignment for vision-language pre-training via multi-stage learning. In: Proceedings of the 30th ACM International Conference on Multimedia (2022). https:\/\/api.semanticscholar.org\/CorpusID:252222245","DOI":"10.1145\/3503161.3548341"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Clip is also an efficient segmenter: a text-driven approach for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15305\u201315314 (2023)","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"11_CR23","unstructured":"Lin, Z., et al.: A structured self-attentive sentence embedding. arXiv preprint arXiv:1703.03130 (2017)"},{"key":"11_CR24","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: ViLBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Lu, X., Zhao, T., Lee, K.: VisualSparta: an embarrassingly simple approach to large-scale text-to-image search with weighted bag-of-words. arXiv preprint arXiv:2101.00265 (2021)","DOI":"10.18653\/v1\/2021.acl-long.389"},{"key":"11_CR26","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1162\/tacl_a_00369","volume":"9","author":"Y Luan","year":"2021","unstructured":"Luan, Y., Eisenstein, J., Toutanova, K., Collins, M.: Sparse, dense, and attentional representations for text retrieval. Trans. Assoc. Comput. Linguist. 9, 329\u2013345 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"11_CR27","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: SegCLIP: patch aggregation with learnable centers for open-vocabulary semantic segmentation. In: International Conference on Machine Learning, pp. 23033\u201323044. PMLR (2023)"},{"key":"11_CR28","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: Text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2085\u20132094 (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"11_CR30","unstructured":"Qi, D., Su, L., Song, J., Cui, E., Bharti, T., Sacheti, A.: ImageBERT: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)"},{"key":"11_CR31","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR32","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"11_CR33","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Sun, S., Chen, Y.C., Li, L., Wang, S., Fang, Y., Liu, J.: LightningDOT: pre-training visual-semantic embeddings for real-time image-text retrieval. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 982\u2013997 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"11_CR36","unstructured":"Wang, Z., Liu, W., He, Q., Wu, X., Yi, Z.: CLIP-GEN: language-free training of a text-to-image generator with clip. arXiv preprint arXiv:2203.00386 (2022)"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, X., Li, H., Sheng, L., Yan, J., Wang, X., Shao, J.: Camp: cross-modal adaptive message passing for text-image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5764\u20135773 (2019)","DOI":"10.1109\/ICCV.2019.00586"},{"key":"11_CR38","unstructured":"Wu, B., et al.: Visual Transformers: token-based image representation and processing for computer vision (2020)"},{"key":"11_CR39","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. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lei, Z., Zhang, Z., Li, S.Z.: Context-aware attention network for image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3536\u20133545 (2020)","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Lei, Y., Zhang, B., Liu, L., Liu, Y.: ZegCLIP: towards adapting clip for zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11175\u201311185 (2023)","DOI":"10.1109\/CVPR52729.2023.01075"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-88711-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T17:14:47Z","timestamp":1743786887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-88711-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031887109","9783031887116"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-88711-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"4 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lucca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"47","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2025.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}