{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:44:47Z","timestamp":1742960687693,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031533105"},{"type":"electronic","value":"9783031533112"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53311-2_29","type":"book-chapter","created":{"date-parts":[[2024,1,27]],"date-time":"2024-01-27T21:37:36Z","timestamp":1706391456000},"page":"396-409","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MoPE: Mixture of\u00a0Pooling Experts Framework for\u00a0Image-Text Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1128-3259","authenticated-orcid":false,"given":"Jiangfeng","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7563-9050","authenticated-orcid":false,"given":"Bowen","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7783-3399","authenticated-orcid":false,"given":"Yongrui","family":"Qin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5843-7844","authenticated-orcid":false,"given":"Chenxi","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-7959","authenticated-orcid":false,"given":"Gang","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1765-1171","authenticated-orcid":false,"given":"Qinpei","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Chen, H., Ding, G., Liu, X., Lin, Z., Liu, J., Han, J.: IMRAM: iterative matching with recurrent attention memory for cross-modal image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12655\u201312663 (2020)","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Chen, J., Hu, H., Wu, H., Jiang, Y., Wang, C.: Learning the best pooling strategy for visual semantic embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15789\u201315798 (2021)","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"29_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1007\/978-3-030-58601-0_33","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Chen","year":"2020","unstructured":"Chen, T., Deng, J., Luo, J.: Adaptive offline quintuplet loss for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 549\u2013565. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_33"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: More than just attention: improving cross-modal attentions with contrastive constraints for image-text matching. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4432\u20134440 (2023)","DOI":"10.1109\/WACV56688.2023.00441"},{"key":"29_CR5","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)"},{"issue":"1","key":"29_CR6","first-page":"5232","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(1), 5232\u20135270 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Han, N., Chen, J., Xiao, G., Zhang, H., Zeng, Y., Chen, H.: Fine-grained cross-modal alignment network for text-video retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3826\u20133834 (2021)","DOI":"10.1145\/3474085.3475241"},{"issue":"1","key":"29_CR8","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural Comput. 3(1), 79\u201387 (1991)","journal-title":"Neural Comput."},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Kim, S., Shim, K., Nguyen, L.T., Shim, B.: Semantic-preserving augmentation for robust image-text retrieval. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023, pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096661"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Lee, K.H., Chen, X., Hua, G., Hu, H., He, X.: Stacked cross attention for image-text matching. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 201\u2013216 (2018)","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"29_CR11","unstructured":"Lepikhin, D., et al.: GShard: scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)"},{"key":"29_CR12","doi-asserted-by":"publisher","first-page":"9193","DOI":"10.1109\/TIP.2021.3123553","volume":"30","author":"J Li","year":"2021","unstructured":"Li, J., Liu, L., Niu, L., Zhang, L.: Memorize, associate and match: embedding enhancement via fine-grained alignment for image-text retrieval. IEEE Trans. Image Process. 30, 9193\u20139207 (2021)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"29_CR13","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1109\/TPAMI.2022.3148470","volume":"45","author":"K Li","year":"2022","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Image-text embedding learning via visual and textual semantic reasoning. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 641\u2013656 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","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"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2641\u20132649 (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Qu, L., Liu, M., Cao, D., Nie, L., Tian, Q.: Context-aware multi-view summarization network for image-text matching. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1047\u20131055 (2020)","DOI":"10.1145\/3394171.3413961"},{"key":"29_CR17","unstructured":"Shazeer, N., et al.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"29_CR18","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv (2017)"},{"key":"29_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/978-3-030-58586-0_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Wang","year":"2020","unstructured":"Wang, H., Zhang, Y., Ji, Z., Pang, Y., Ma, L.: Consensus-aware visual-semantic embedding for image-text matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 18\u201334. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_2"},{"issue":"2","key":"29_CR20","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1109\/TPAMI.2018.2797921","volume":"41","author":"L Wang","year":"2018","unstructured":"Wang, L., Li, Y., Huang, J., Lazebnik, S.: Learning two-branch neural networks for image-text matching tasks. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 394\u2013407 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Wehrmann, J., Kolling, C., Barros, R.C.: Adaptive cross-modal embeddings for image-text alignment. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12313\u201312320 (2020)","DOI":"10.1609\/aaai.v34i07.6915"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wehrmann, J., Souza, D.M., Lopes, M.A., Barros, R.C.: Language-agnostic visual-semantic embeddings. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5804\u20135813 (2019)","DOI":"10.1109\/ICCV.2019.00590"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, G., Wei, S., Pang, H., Zhao, Y.: Heterogeneous feature fusion and cross-modal alignment for composed image retrieval. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 5353\u20135362 (2021)","DOI":"10.1145\/3474085.3475659"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, K., Mao, Z., Wang, Q., Zhang, Y.: Negative-aware attention framework for image-text matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15661\u201315670 (2022)","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Improving visual-semantic embedding with adaptive pooling and optimization objective. arXiv preprint arXiv:2210.02206 (2022)","DOI":"10.18653\/v1\/2023.eacl-main.87"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53311-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T15:30:17Z","timestamp":1710257417000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53311-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031533105","9783031533112"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53311-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"28 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclaimer"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"29 January 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 February 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"297","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"112","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}