{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T08:51:29Z","timestamp":1743065489187,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031466731"},{"type":"electronic","value":"9783031466748"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46674-8_39","type":"book-chapter","created":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:02:29Z","timestamp":1699102949000},"page":"563-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TSCMR:Two-Stage Cross-Modal Retrieval"],"prefix":"10.1007","author":[{"given":"Zhihao","family":"Chen","sequence":"first","affiliation":[]},{"given":"Hongya","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,5]]},"reference":[{"key":"39_CR1","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, 30 (2017)"},{"key":"39_CR2","unstructured":"Li, L.H., Yatskar, M., Yin, D., et al.: Visualbert: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., et al.: Unicoder-vl: a universal encoder for vision and language by cross-modal pre-training. Proc. AAAI Conf. Artif. Intell. 34(07), 11336\u201311344 (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"39_CR4","unstructured":"Qi, D., Su, L., Song, J., et al.: Imagebert: cross-modal pre-training with large-scale weak-supervised image-text data. arXiv preprint arXiv:2001.07966 (2020)"},{"key":"39_CR5","unstructured":"Lu, J., Batra, D., Parikh, D., et al.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, 32 (2019)"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M., Lxmert: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"39_CR7","unstructured":"Huang, Z., Zeng, Z., Liu, B., et al.: Pixel-Bert: aligning image pixels with text by deep multi-modal transformers. arXiv preprint arXiv:2004.00849 (2020)"},{"key":"39_CR8","unstructured":"Ren, S., He, K., Girshick, R., et al.: Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, 28 (2015)"},{"key":"39_CR9","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"39_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Messina, N., Amato, G., Esuli, A., et al.: Fine-grained visual textual alignment for cross-modal retrieval using transformer encoders. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 17(4), 1\u201323 (2021)","DOI":"10.1145\/3451390"},{"key":"39_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Freitag, M., Al-Onaizan, Y., Sankaran, B.: Ensemble distillation for neural machine translation. arXiv preprint arXiv:1702.01802 (2017)","DOI":"10.18653\/v1\/W17-3207"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Jiao, X., Yin, Y., Shang, L., et al.: Tinybert: distilling bert for natural language understanding. arXiv preprint arXiv:1909.10351 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"39_CR15","unstructured":"Sanh, V., Debut, L., Chaumond, J., et al.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Sun, Z., Yu, H., Song, X., et al.: Mobilebert: a compact task-agnostic BERT for resource-limited devices. arXiv preprint arXiv:2004.02984 (2020)","DOI":"10.18653\/v1\/2020.acl-main.195"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Xia, M., et al.: Structured pruning learns compact and accurate models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1513\u20131528 (2022)","DOI":"10.18653\/v1\/2022.acl-long.107"},{"key":"39_CR18","unstructured":"Faghri, F., Fleet, D.J., Kiros, J.R., Fidler, S.: VSE++: improving visual-semantic embeddings with hard negatives. In: BMVC. BMV A Press, 12 (2018)"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"39_CR20","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":"39_CR21","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V","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.) Computer Vision \u2013 ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"39_CR22","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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, Y., Li, K., Li, Y., Fu, Y.: Visual semantic reasoning for image-text matching. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4654\u20134662 (2019)","DOI":"10.1109\/ICCV.2019.00475"},{"key":"39_CR24","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":"39_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Position focused attention network for image-text matching. arXiv preprint arXiv:1907.09748 (2019)","DOI":"10.24963\/ijcai.2019\/526"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, T., Li, Y., Zhang, Y., Wu, F.: Multi-modality cross attention network for image and sentence matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10941\u201310950 (2020)","DOI":"10.1109\/CVPR42600.2020.01095"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46674-8_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,4]],"date-time":"2023-11-04T13:20:29Z","timestamp":1699104029000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46674-8_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031466731","9783031466748"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46674-8_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2023.uqcloud.net\/","order":11,"name":"conference_url","label":"Conference URL","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":"Yes. Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"503","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":"216","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":"43% - 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":"2.97","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":"3.77","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}