{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T19:10:09Z","timestamp":1749928209821,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819681693","type":"print"},{"value":"9789819681709","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\/978-981-96-8170-9_31","type":"book-chapter","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:50:21Z","timestamp":1749927021000},"page":"397-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Fine-Grained Relation Alignment for\u00a0Multimedia Information Retrieval"],"prefix":"10.1007","author":[{"given":"Min","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Chunpeng","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,15]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: Spice: semantic propositional image caption evaluation. In: European Conference on Computer Vision, pp. 3745\u20133757 (2016)","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10638\u201310647 (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Zhao, Y., Jin, Q., Wu, Q.: Fine-grained video-text retrieval with hierarchical graph reasoning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10635\u201310644 (2020)","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, J., Lin, L., Qi, Z., Ma, J., Shan, Y.: Tagging before alignment: integrating multi-modal tags for video-text retrieval. In: AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 396\u2013404 (2023)","DOI":"10.1609\/aaai.v37i1.25113"},{"key":"31_CR5","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. ArXiv abs\/ arXiv: 1810.04805 (2019)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Partially relevant video retrieval. In: ACM International Conference on Multimedia, pp. 246\u2013257 (2022)","DOI":"10.1145\/3503161.3547976"},{"key":"31_CR7","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TMM.2018.2832602","volume":"20","author":"J Dong","year":"2017","unstructured":"Dong, J., Li, X., Snoek, C.: Predicting visual features from text for image and video caption retrieval. IEEE Trans. Multimedia 20, 3377\u20133388 (2017)","journal-title":"IEEE Trans. Multimedia"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9338\u20139347 (2018)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"31_CR9","doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Dual encoding for zero-example video retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9346\u20139355 (2019)","DOI":"10.1109\/CVPR.2019.00957"},{"key":"31_CR10","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":"31_CR11","doi-asserted-by":"crossref","unstructured":"He, X., Peng, Y., Xi-e, L.: A new benchmark and approach for fine-grained cross-media retrieval. In: ACM International Conference on Multimedia, pp. 1740\u20131748 (2019)","DOI":"10.1145\/3343031.3350974"},{"key":"31_CR12","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TCYB.2018.2879846","volume":"50","author":"X Huang","year":"2017","unstructured":"Huang, X., Peng, Y., Yuan, M.: Mhtn: modal-adversarial hybrid transfer network for cross-modal retrieval. IEEE Trans. Cybernet. 50, 1047\u20131059 (2017)","journal-title":"IEEE Trans. Cybernet."},{"key":"31_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)"},{"key":"31_CR14","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Li, X., Xu, C., Yang, G., Chen, Z., Dong, J.: W2vv++ fully deep learning for ad-hoc video search. In: ACM International Conference on Multimedia, pp. 1786\u20131794 (2019)","DOI":"10.1145\/3343031.3350906"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Lin, C., et al.: Text-adaptive multiple visual prototype matching for video-text retrieval. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 38655\u201338666 (2022)","DOI":"10.1186\/s13634-022-00887-y"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Livio Baldini\u00a0Soares, Nicholas\u00a0FitzGerald, J.L.T.K.: Matching the blanks: distributional similarity for relation learning. Annual Meeting of the Association for Computational Linguistics, pp. 2895\u20132905 (2019)","DOI":"10.18653\/v1\/P19-1279"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Mandal, D., Chaudhury, K.N., Biswas, S.: Generalized semantic preserving hashing for n-label cross-modal retrieval.In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2633\u20132641 (2017)","DOI":"10.1109\/CVPR.2017.282"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: ACM on International Conference on Multimedia Retrieval, pp. 19\u201327 (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Mithun, N.C., Li, J.B., Metze, F., Roy-Chowdhury, A.K.: Learning joint embedding with multimodal cues for cross-modal video-text retrieval. In: ACM on International Conference on Multimedia Retrieval, pp. 19\u201327 (2018)","DOI":"10.1145\/3206025.3206064"},{"key":"31_CR22","unstructured":"Peng, Y., Huang, X., Qi, J.: Cross-media shared representation by hierarchical learning with multiple deep networks. In: International Joint Conference on Artificial Intelligence, pp. 3846\u20133853 (2016)"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Song, Y., Soleymani, M.: Polysemous visual-semantic embedding for cross-modal retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1979\u20131988 (2019)","DOI":"10.1109\/CVPR.2019.00208"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Wang, B., Yang, Y., Xu, X., Hanjalic, A., Shen, H.T.: Adversarial cross-modal retrieval. In: ACM International Conference on Multimedia, pp. 154\u2013162 (2017)","DOI":"10.1145\/3123266.3123326"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Wang, X.E., Wu, J., Chen, J., Li, L., Fang Wang, Y., Wang, W.Y.: Vatex: a large-scale, high-quality multilingual dataset for video-and-language research. In: IEEE International Conference on Computer Vision, pp. 4580\u20134590 (2019)","DOI":"10.1109\/ICCV.2019.00468"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Z., Sung, Y.L., Cheng, F., Bertasius, G., Bansal, M.: Unified coarse-to-fine alignment for video-text retrieval. In: International Conference on Computer Vision, pp. 2816\u20132827 (2023)","DOI":"10.1109\/ICCV51070.2023.00264"},{"issue":"6","key":"31_CR27","doi-asserted-by":"publisher","first-page":"2868","DOI":"10.1109\/TIP.2017.2688133","volume":"26","author":"XS Wei","year":"2017","unstructured":"Wei, X.S., Luo, J.H., Wu, J., Zhou, Z.H.: Selective convolutional descriptor aggregation for fine-grained image retrieval. IEEE Trans. Image Process. 26(6), 2868\u20132881 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"31_CR28","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1109\/TPAMI.2021.3126648","volume":"44","author":"XS Wei","year":"2021","unstructured":"Wei, X.S., et al.: Fine-grained image analysis with deep learning: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 8927\u20138948 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Wray, M., Larlus, D., Csurka, G., Damen, D.: Fine-grained action retrieval through multiple parts-of-speech embeddings. In: IEEE International Conference on Computer Vision, pp. 450\u2013459 (2019)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"31_CR30","doi-asserted-by":"crossref","unstructured":"Wu, P., He, X., Tang, M., Lv, Y., Liu, J.: Hanet: hierarchical alignment networks for video-text retrieval. In: ACM MM.,pp. 3518\u20133527 (2021)","DOI":"10.1145\/3474085.3475515"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: Msr-vtt: a large video description dataset for bridging video and language. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Yang, X., Dong, J., Cao, Y., Wang, X., Wang, M., Chua, T.S.: Tree-augmented cross-modal encoding for complex-query video retrieval. ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1339\u20131348 (2020)","DOI":"10.1145\/3397271.3401151"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: ECCV, pp. 471\u2013487 (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Zellers, R., Yatskar, M., Thomson, S., Choi, Y.: Neural motifs: scene graph parsing with global context. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5831\u20135840 (2017)","DOI":"10.1109\/CVPR.2018.00611"},{"issue":"6","key":"31_CR35","first-page":"965","volume":"24","author":"X Zhai","year":"2013","unstructured":"Zhai, X., Peng, Y., Xiao, J.: Learning cross-media joint representation with sparse and semisupervised regularization. IEEE TCSVT 24(6), 965\u2013978 (2013)","journal-title":"IEEE TCSVT"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, G., Ren, J., Gu, J., Tresp, V.: Multi-event video-text retrieval. In: International Conference on Computer Vision, pp. 22113\u201322123 (2023)","DOI":"10.1109\/ICCV51070.2023.02021"},{"key":"31_CR37","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zheng, K., Zha, Z.: Stacked convolutional deep encoding network for video-text retrieval. In: IEEE ICME, pp.\u00a01\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102913"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8170-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T18:50:32Z","timestamp":1749927032000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8170-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819681693","9789819681709"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8170-9_31","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":"15 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2025.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}