{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:45:07Z","timestamp":1743032707491,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819786190"},{"type":"electronic","value":"9789819786206"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-981-97-8620-6_28","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"410-423","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficiency-Aware Fine-Grained Vision-Language Retrieval via\u00a0a\u00a0Global-Contextual Autoencoder"],"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":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinghe","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cuncun","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bogolin, S.V., Croitoru, I., Jin, H., Liu, Y., Albanie, S.: Cross modal retrieval with querybank normalisation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5184\u20135195 (2021)","key":"28_CR1","DOI":"10.1109\/CVPR52688.2022.00513"},{"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":"28_CR2","DOI":"10.1109\/CVPR42600.2020.01065"},{"doi-asserted-by":"crossref","unstructured":"Cheng, G., Li, Q., Wang, G., Xie, X., Min, L., Han, J.: SFRNet: Fine-grained oriented object recognition via separate feature refinement. IEEE Trans. Geosci. Remote. Sens. (2023)","key":"28_CR3","DOI":"10.1109\/TGRS.2023.3277626"},{"unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding (2019). arXiv:abs\/1810.04805","key":"28_CR4"},{"unstructured":"Dong, Y., Cordonnier, J.B., Loukas, A.: Attention is not all you need: pure attention loses rank doubly exponentially with depth. In: International Conference on Machine Learning, pp. 2793\u20132803 (2021)","key":"28_CR5"},{"unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Machine Learning (2021). arXiv:abs\/2010.11929","key":"28_CR6"},{"doi-asserted-by":"crossref","unstructured":"Du, R., Yu, W., Wang, H., Lin, T.E., Chang, D., Ma, Z.: Multi-view active fine-grained visual recognition. In: IEEE International Conference on Computer Vision, pp. 1568\u20131578 (2023)","key":"28_CR7","DOI":"10.1109\/ICCV51070.2023.00151"},{"unstructured":"Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. In: IEEE Conference on Computer Vision and Pattern Recognition Workshop, pp. 178\u2013178 (2004)","key":"28_CR8"},{"doi-asserted-by":"crossref","unstructured":"Gu, J., Cai, J., Joty, S.R., Niu, L., Wang, G.: Look, imagine and match: improving textual-visual cross-modal retrieval with generative models. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7181\u20137189 (2018)","key":"28_CR9","DOI":"10.1109\/CVPR.2018.00750"},{"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":"28_CR10","DOI":"10.1145\/3343031.3350974"},{"key":"28_CR11","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":"28_CR12","DOI":"10.1109\/CVPR52729.2023.00273"},{"doi-asserted-by":"crossref","unstructured":"Kodirov, E., Xiang, T., Gong, S.: Semantic autoencoder for zero-shot learning. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4447\u20134456 (2017)","key":"28_CR13","DOI":"10.1109\/CVPR.2017.473"},{"doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X.D., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching (2018). arXiv:abs\/1803.08024","key":"28_CR14","DOI":"10.1007\/978-3-030-01225-0_13"},{"doi-asserted-by":"crossref","unstructured":"Li, X., Ma, T., Hou, Y., Shi, B., Yang, Y., Liu, Y., Wu, X., Chen, Q., Li, Y., Qiao, Y., et\u00a0al.: Logonet: Towards accurate 3d object detection with local-to-global cross-modal fusion. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17524\u201317534 (2023)","key":"28_CR15","DOI":"10.1109\/CVPR52729.2023.01681"},{"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":"28_CR16","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"28_CR17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1049\/el:19710123","volume":"7","author":"CS Lu","year":"1971","unstructured":"Lu, C.S.: Solution of the matrix equation ax + xb = c. Electron. Lett. 7, 185\u2013186 (1971)","journal-title":"Electron. Lett."},{"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":"28_CR18","DOI":"10.1109\/CVPR.2017.282"},{"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":"28_CR19"},{"doi-asserted-by":"crossref","unstructured":"Reed, S., Akata, Z., Lee, H., Schiele, B.: Learning deep representations of fine-grained visual descriptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201358 (2016)","key":"28_CR20","DOI":"10.1109\/CVPR.2016.13"},{"unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Machine Learning, pp. 1\u201314 (2015)","key":"28_CR21"},{"unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The Caltech-UCSD Birds-200-2011 Dataset. Tech. rep. (2011)","key":"28_CR22"},{"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":"28_CR23","DOI":"10.1145\/3123266.3123326"},{"key":"28_CR24","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TPAMI.2017.2699960","volume":"40","author":"J Wang","year":"2016","unstructured":"Wang, J., Zhang, T., Song, J., Sebe, N., Shen, H.T.: A survey on learning to hash. IEEE Trans. Pattern Anal. Mach. Intell. 40, 769\u2013790 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR25","doi-asserted-by":"publisher","first-page":"8927","DOI":"10.1109\/TPAMI.2021.3126648","volume":"44","author":"XS Wei","year":"2021","unstructured":"Wei, X.S., Song, Y.Z., Aodha, O.M., Wu, J., Peng, Y., Tang, J., Yang, J., Belongie, S.J.: 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":"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":"28_CR26","DOI":"10.1145\/3474085.3475515"},{"doi-asserted-by":"crossref","unstructured":"Zha, Z., Tang, H., Sun, Y., Tang, J.: Boosting few-shot fine-grained recognition with background suppression and foreground alignment. IEEE Trans. Circuits Syst. Video Technol. (2023)","key":"28_CR27","DOI":"10.1109\/TCSVT.2023.3236636"},{"key":"28_CR28","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1109\/TCSVT.2013.2276704","volume":"24","author":"X Zhai","year":"2014","unstructured":"Zhai, X., Peng, Y., Xiao, J.: Learning cross-media joint representation with sparse and semisupervised regularization. IEEE Trans. Circuits Syst. Video Technol. 24, 965\u2013978 (2014)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"28_CR29","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1109\/LSP.2021.3065595","volume":"28","author":"M Zheng","year":"2021","unstructured":"Zheng, M., Wang, W., Li, Q.: Fine-grained image-text retrieval via discriminative latent space learning. IEEE Signal Process. Lett. 28, 643\u2013647 (2021)","journal-title":"IEEE Signal Process. Lett."},{"doi-asserted-by":"crossref","unstructured":"Zheng, M., Wu, C., Qin, J., Liu, W., Chen, M., lin, L., Zhou, F.: Global-to-contextual shared semantic learning for fine-grained vision-language alignment. In: International Conference on Artificial Neural Networks, pp. 281\u2013293 (2023)","key":"28_CR30","DOI":"10.1007\/978-3-031-44198-1_24"}],"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\/978-981-97-8620-6_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T20:16:25Z","timestamp":1736885785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8620-6_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9789819786190","9789819786206"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8620-6_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}