{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T22:07:43Z","timestamp":1742940463669,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819601240"},{"type":"electronic","value":"9789819601257"}],"license":[{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T00:00:00Z","timestamp":1731369600000},"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\/978-981-96-0125-7_16","type":"book-chapter","created":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T03:06:48Z","timestamp":1731812808000},"page":"190-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RSANet: Relationship-Aware Symmetric Alignment Network for\u00a0Fine-Grained Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Min","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunpeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghe","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,12]]},"reference":[{"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)","key":"16_CR1","DOI":"10.1109\/CVPR42600.2020.01065"},{"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)","key":"16_CR2","DOI":"10.1109\/CVPR42600.2020.01065"},{"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)","key":"16_CR3","DOI":"10.1609\/aaai.v37i1.25113"},{"doi-asserted-by":"crossref","unstructured":"Cheng, D., Gong, Y., Zhou, S., Wang, J., Zheng, N.: Person re-identification by multi-channel parts-based CNN with improved triplet loss function. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1335\u20131344 (2016)","key":"16_CR4","DOI":"10.1109\/CVPR.2016.149"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv abs\/1810.04805 (2019)","key":"16_CR5"},{"doi-asserted-by":"crossref","unstructured":"Dong, J., et al.: Partially relevant video retrieval. In: ACM International Conference on Multimedia, pp. 246\u2013257 (2022)","key":"16_CR6","DOI":"10.1145\/3503161.3547976"},{"key":"16_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.G.M.: Predicting visual features from text for image and video caption retrieval. IEEE Trans. Multimedia 20, 3377\u20133388 (2017)","journal-title":"IEEE Trans. Multimedia"},{"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)","key":"16_CR8","DOI":"10.1109\/CVPR.2019.00957"},{"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)","key":"16_CR9","DOI":"10.1109\/CVPR.2019.00957"},{"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":"16_CR10"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"16_CR11","DOI":"10.1109\/CVPR.2016.90"},{"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)","key":"16_CR12","DOI":"10.1145\/3343031.3350974"},{"key":"16_CR13","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. Cybern. 50, 1047\u20131059 (2017)","journal-title":"IEEE Trans. Cybern."},{"doi-asserted-by":"crossref","unstructured":"Jiang, D., Ye, M.: Cross-modal implicit relation reasoning and aligning for text-to-image person retrieval. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2787\u20132797 (2023)","key":"16_CR14","DOI":"10.1109\/CVPR52729.2023.00273"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)","key":"16_CR15"},{"unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)","key":"16_CR16"},{"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)","key":"16_CR17","DOI":"10.1145\/3343031.3350906"},{"doi-asserted-by":"crossref","unstructured":"Lin, Z., Yu, S., Kuang, Z., Pathak, D., Ramanan, D.: Multimodality helps unimodality: cross-modal few-shot learning with multimodal models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 19325\u201319337 (2023)","key":"16_CR18","DOI":"10.1109\/CVPR52729.2023.01852"},{"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)","key":"16_CR19","DOI":"10.1109\/CVPR.2017.282"},{"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)","key":"16_CR20","DOI":"10.1145\/3206025.3206064"},{"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)","key":"16_CR21","DOI":"10.1145\/3206025.3206064"},{"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":"16_CR22"},{"unstructured":"Shi, P., Lin, J.: Simple bert models for relation extraction and semantic role labeling. arXiv preprint arXiv:1904.05255 (2019)","key":"16_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)","key":"16_CR24","DOI":"10.1109\/CVPR.2019.00208"},{"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)","key":"16_CR25","DOI":"10.1145\/3123266.3123326"},{"doi-asserted-by":"crossref","unstructured":"Wang, X.E., Wu, J., Chen, J., Li, L., Wang, Y.F., 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)","key":"16_CR26","DOI":"10.1109\/ICCV.2019.00468"},{"key":"16_CR27","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."},{"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)","key":"16_CR28","DOI":"10.1109\/ICCV.2019.00054"},{"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 International Conference on Multimedia, pp. 3518\u20133527 (2021)","key":"16_CR29","DOI":"10.1145\/3474085.3475515"},{"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)","key":"16_CR30","DOI":"10.1109\/CVPR.2016.571"},{"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. In: ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1339\u20131348 (2020)","key":"16_CR31","DOI":"10.1145\/3397271.3401151"},{"doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: European Conference on Computer Vision, pp. 471\u2013487 (2018)","key":"16_CR32","DOI":"10.1007\/978-3-030-01234-2_29"},{"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)","key":"16_CR33","DOI":"10.1109\/CVPR.2018.00611"},{"issue":"6","key":"16_CR34","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TCSVT.2013.2276704","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 Trans. Circuits Syst. Video Technol. 24(6), 965\u2013978 (2013)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"doi-asserted-by":"crossref","unstructured":"Zhao, R., Zheng, K., Zha, Z.: Stacked convolutional deep encoding network for video-text retrieval. In: IEEE International Conference on Multimedia and Expo, pp.\u00a01\u20136 (2020)","key":"16_CR35","DOI":"10.1109\/ICME46284.2020.9102913"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2024: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0125-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,17]],"date-time":"2024-11-17T04:29:22Z","timestamp":1731817762000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0125-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,12]]},"ISBN":["9789819601240","9789819601257"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0125-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,12]]},"assertion":[{"value":"12 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}