{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:16:18Z","timestamp":1783102578497,"version":"3.54.6"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819699209","type":"print"},{"value":"9789819699216","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\/978-981-96-9921-6_30","type":"book-chapter","created":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T06:15:44Z","timestamp":1753424144000},"page":"370-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SDHNet: Semantic Disentanglement and Heterogeneous Feature Fusion Network for Composed Image Retrieval"],"prefix":"10.1007","author":[{"given":"Dian","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shikui","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, Y., Lazebnik, S.: Learning deep structure-preserving image-text embeddings. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5005\u20135013 (2016)","DOI":"10.1109\/CVPR.2016.541"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Gordo, A., Almaz\u00e1n, J., Revaud, J., Larlus, D.: Deep image retrieval: learning global representations for image search. In: European Conference on Computer Vision (ECCV 2016), pp. 1\u201316(2016)","DOI":"10.1007\/978-3-319-46466-4_15"},{"key":"30_CR3","unstructured":"Shin, M., Cho, Y., Ko, B., Gu, G.: RTIC: residual learning for text and image composition using graph convolutional network. ArXiv abs\/2104.03015 (2021)"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Kim, J., Yu, Y., Kim, H., Kim, G.: Dual compositional learning in interactive image retrieval. In: 35th AAAI Conference on Artificial Intelligence(AAAI 2021), pp. 1771\u20131779 (2021)","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Gong, S., Bazzani, L.: Image search with text feedback by visiolinguistic attention learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2998\u20133008 (2020)","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Lee, S., Kim, D., Han, B.: Cosmo: content-style modulation for image retrieval with text feedback. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 802\u2013812 (2021)","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"30_CR7","doi-asserted-by":"crossref","unstructured":"Anwaar, M.U., Labintcev, E., Kleinsteuber, M.: Compositional learning of image-text query for image retrieval. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 1140\u20131149 (2021)","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Fu, Z., Chen, X., Dong, J., Ji, S.: Multi-order adversarial representation learning for composed query image retrieval. In: ICASSP 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1685\u20131689 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414436"},{"key":"30_CR9","doi-asserted-by":"publisher","first-page":"8346","DOI":"10.1109\/TMM.2023.3235495","volume":"25","author":"Y Xu","year":"2023","unstructured":"Xu, Y., Bin, Y., Wei, J., Yang, Y., Wang, G., Shen, H.T.: Multi-modal transformer with global-local alignment for composed query image retrieval. IEEE Trans. Multimedia 25, 8346\u20138357 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: CAT: Cross Attention in Vision Transformer. 2022 IEEE International Conference on Multimedia and Expo (ICME).pp.1--6 (2021)","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"30_CR11","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: Multi-head attention: collaborate instead of concatenate. ArXiv abs\/2006.16362 (2020)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Yang, X., Liu, D., Zhang, H., Luo, Y., Wang, C., Zhang, J.: Decomposing semantic shifts for composed image retrieval. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence and 36th Conference on Innovative Applications of Artificial Intelligence and 14th Symposium on Educational Advances in Artificial Intelligence. (AAAI 2024).AAAI Press(2024)","DOI":"10.1609\/aaai.v38i7.28479"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"Vo, N., Jiang, L., Sun, C., Murphy, K., Li, L.J., Fei-Fei, L., Hays, J.: Composing text and image for image retrieval: an empirical odyssey. In:2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6432\u20136441(2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with pre-trained vision-and-language models. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2105\u20132114 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Goenka, S., Zheng, Z., Jaiswal, A., Chada, R., Wu, Y., Hedau, V.,Natarajan, P.: FashionVLP: Vision language transformer for fashion retrieval with feedback. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14085\u201314095 (2022)","DOI":"10.1109\/CVPR52688.2022.01371"},{"issue":"3","key":"30_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3617597","volume":"20","author":"A Baldrati","year":"2023","unstructured":"Baldrati, A., Bertini, M., Uricchio, T., Del Bimbo, A.: Composed image retrieval using contrastive learning and task-oriented CLIP-based features. ACM Trans. Multimed. Comput. Commun. Appl. 20(3), 1\u201324 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"30_CR17","doi-asserted-by":"publisher","first-page":"4543","DOI":"10.1109\/TIP.2023.3299791","volume":"32","author":"Q Yang","year":"2023","unstructured":"Yang, Q., Ye, M., Cai, Z., Su, K., Du, B.: Composed image retrieval via cross relation network with hierarchical aggregation transformer. IEEE Trans. Image Process. 32, 4543\u20134554 (2023)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"30_CR18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3519030","volume":"19","author":"H Zhu","year":"2023","unstructured":"Zhu, H., Wei, Y., Zhao, Y., Zhang, C., Huang, S.: AMC: adaptive multi-expert collaborative network for text-guided image retrieval. ACM Trans. Multimed. Comput. Commun. Appl. 19(1), 1\u201322 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"30_CR19","unstructured":"Guo, X., Wu, H., Gao, Y., Rennie, S.J., Feris, R.S.: FashionIQ: a new dataset towards retrieving images by natural language feedback. ArXiv: Computer Vision and Pattern Recognition (2019)"},{"key":"30_CR20","unstructured":"Suhr, A., Zhou, S., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. ArXiv abs\/1811.00491 (2018)"},{"key":"30_CR21","unstructured":"Delmas, G., de Rezende, R.S., Csurka, G., Larlus, D.: Artemis: Attention-based retrieval with text-explicit matching and implicit similarity. ArXiv abs\/2206.01304 (2022)"},{"key":"30_CR23","unstructured":"Radford, A., et al.: Learning Transferable Visual Models from Natural Language Supervision. In: International Conference on Machine Learning (ICML 2021). pp. 8748\u20138763(2021)"},{"key":"30_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017)"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Patel, Y., Tolias, G., Matas, J.: Recall@k surrogate loss with large batches and similarity mixup. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7492\u20137501 (2022)","DOI":"10.1109\/CVPR52688.2022.00735"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-9921-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:30:53Z","timestamp":1783099853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-9921-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819699209","9789819699216"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-9921-6_30","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":"26 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","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":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}