{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:28:53Z","timestamp":1768375733667,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556786","type":"print"},{"value":"9789819556793","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5679-3_11","type":"book-chapter","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:40Z","timestamp":1768329400000},"page":"149-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["False Negatives Do Matter: A Novel Soft Label and\u00a0Reranking Based Plug-in Method for\u00a0Image-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Heng-yang","family":"Lu","sequence":"first","affiliation":[]},{"given":"Yiyang","family":"Sung","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: 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":"Baldrati, A., Bertini, M., Uricchio, T., Del\u00a0Bimbo, A.: Effective conditioned and composed image retrieval combining clip-based features. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21466\u201321474 (2022)","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association For Computational Linguistics: Human Language Technologies, vol. 1 (long and short papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"11_CR4","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":"11_CR5","doi-asserted-by":"crossref","unstructured":"Fu, Z., Mao, Z., Song, Y., Zhang, Y.: Learning semantic relationship among instances for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15159\u201315168 (2023)","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"11_CR6","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey. arxiv preprint arxiv:2312.109972(1) (2023)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Huang, H., Nie, Z., Wang, Z., Shang, Z.: Cross-modal and UNI-modal soft-label alignment for image-text retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a038, pp. 18298\u201318306 (2024)","DOI":"10.1609\/aaai.v38i16.29789"},{"key":"11_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":"11_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":"11_CR11","doi-asserted-by":"publisher","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"11_CR12","unstructured":"Liu, H., Zhang, Y.: Image-text retrieval with intra-modal soft labels. Available at SSRN 4068211"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Liu, X., He, J., Sung, Y., Lu, H.y.: Chinese vision-language understanding based on multimodal pre-trained models. In: 2024 China Automation Congress (CAC), pp. 4236\u20134239. IEEE (2024)","DOI":"10.1109\/CAC63892.2024.10864877"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"L\u00fclf, C., Lima\u00a0Martins, D.M., Vaz\u00a0Salles, M.A., Zhou, Y., Gieseke, F.: Clip-branches: interactive fine-tuning for text-image retrieval. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2719\u20132723 (2024)","DOI":"10.1145\/3626772.3657678"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Luo, Z., et al.: Lexlip: lexicon-bottlenecked language-image pre-training for large-scale image-text sparse retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11206\u201311217 (2023)","DOI":"10.1109\/ICCV51070.2023.01029"},{"key":"11_CR16","unstructured":"OpenAI: Gpt-3.5 technical report. https:\/\/platform.openai.com\/docs\/models\/gpt-3-5 (2023), Accessed via OpenAI API at https:\/\/platform.openai.com"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"Peng, S.J., He, Y., Liu, X., Cheung, Y.m., Xu, X., Cui, Z.: Relation-aggregated cross-graph correlation learning for fine-grained image\u2013text retrieval. IEEE Trans. Neural Netw. Learn. Syst. 35(2), 2194\u20132207 (2022)","DOI":"10.1109\/TNNLS.2022.3188569"},{"key":"11_CR18","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_CR19","doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201358 (2016)","DOI":"10.1109\/CVPR.2016.13"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"11_CR21","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":"11_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107807","volume":"239","author":"Y Sun","year":"2022","unstructured":"Sun, Y., et al.: Unsupervised deep hashing through learning soft pseudo label for remote sensing image retrieval. Knowl. Based Syst. 239, 107807 (2022)","journal-title":"Knowl. Based Syst."},{"key":"11_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535373","volume-title":"Dynamic visual semantic sub-embeddings and fast re-ranking for image-text retrieval","author":"W Wei","year":"2025","unstructured":"Wei, W., Gui, Z., Wu, C., Zhao, A., Peng, D., Wu, H.: Dynamic visual semantic sub-embeddings and fast re-ranking for image-text retrieval. IEEE Trans, Multimedia (2025)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492\u20131500 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"11_CR25","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. Linguistics 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguistics"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Zhang, X., Li, H., Wang, J., Zhang, J., Zhou, W.: X\u02c6{2}2-VLM: All-in-one pre-trained model for vision-language tasks. IEEE Trans. Patt. Anal. Mach. Intell. 46(5), 3156\u20133168 (2023)","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Jin, Q., Bao, T., Li, W.: Multi-modal knowledge hypergraph for diverse image retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a037, pp. 3376\u20133383 (2023)","DOI":"10.1609\/aaai.v37i3.25445"},{"key":"11_CR28","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":"11_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, X., Niu, X., Fournier-Viger, P., Dai, X.: Image-text retrieval via preserving main semantics of vision. In: 2023 IEEE International Conference on Multimedia and Expo (ICME), pp. 1967\u20131972. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00337"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Masking-based cross-modal remote sensing image-text retrieval via dynamic contrastive learning. IEEE Trans. Geosci. Remote Sens. (2024)","DOI":"10.1109\/TGRS.2024.3406897"}],"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\/978-981-95-5679-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T18:36:44Z","timestamp":1768329404000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5679-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556786","9789819556793"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5679-3_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"14 January 2026","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":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}