{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T06:27:22Z","timestamp":1769063242498,"version":"3.49.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030983574","type":"print"},{"value":"9783030983581","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98358-1_33","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:06:56Z","timestamp":1647259616000},"page":"416-427","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Embedding for\u00a0Lifelog Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8743","authenticated-orcid":false,"given":"Liting","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2903-3968","authenticated-orcid":false,"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"33_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"issue":"1","key":"33_CR2","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1017\/S1351324916000334","volume":"23","author":"KW Church","year":"2017","unstructured":"Church, K.W.: Word2Vec. Nat. Lang. Eng. 23(1), 155\u2013162 (2017)","journal-title":"Nat. Lang. Eng."},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Cornia, M., et al.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"33_CR4","unstructured":"Devlin, J., et al.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"33_CR5","unstructured":"Faghri, F., et al.: Vse++: Improving visual-semantic embeddings with hard negatives. arXiv preprint arXiv:1707.05612 (2017)"},{"key":"33_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-15561-1_2","volume-title":"Computer Vision","author":"A Farhadi","year":"2010","unstructured":"Farhadi, A., et al.: Every picture tells a story: generating sentences from images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 15\u201329. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2"},{"issue":"2","key":"33_CR7","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/s11263-013-0658-4","volume":"106","author":"Y Gong","year":"2014","unstructured":"Gong, Y., et al.: A multi-view embedding space for modeling internet images, tags, and their semantics. Int. J. Comput. Vis. 106(2), 210\u2013233 (2014)","journal-title":"Int. J. Comput. Vis."},{"issue":"1","key":"33_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/1500000033","volume":"8","author":"C Gurrin","year":"2014","unstructured":"Gurrin, C., Smeaton, A.F., Doherty, A.R.: Lifelogging: personal big data. Found. Trends Inf. Retrieval 8(1), 1\u2013125 (2014)","journal-title":"Found. Trends Inf. Retrieval"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Gurrin, C., et al.: Introduction to the Fourth Annual Lifelog Search Challenge, In: Proceedings of the 2021 International Conference on Multimedia Retrieval, LSC 2021 (2021)","DOI":"10.1145\/3460426.3470945"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Gurrin, C., et al.: Overview of NTCIR-13 Lifelog-2 task (2017)","DOI":"10.1145\/2911451.2914680"},{"key":"33_CR11","doi-asserted-by":"crossref","unstructured":"He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR12","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh, M., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Li, F.F.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"33_CR14","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv:1411.2539 (2014)"},{"key":"33_CR15","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1162\/tacl_a_00188","volume":"2","author":"P Kuznetsova","year":"2014","unstructured":"Kuznetsova, P., et al.: Treetalk: composition and compression of trees for image descriptions. Trans. Assoc. Comput. Linguist. 2, 351\u2013362 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"33_CR16","unstructured":"Lample, G., Alexis, C.: Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291 (2019)"},{"key":"33_CR17","unstructured":"Lee, H.: Unsupervised feature learning via sparse hierarchical representations. Stanford University (2010)"},{"key":"33_CR18","doi-asserted-by":"crossref","unstructured":"Mason, R., Eugene, C.: Nonparametric method for data-driven image captioning. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (2014)","DOI":"10.3115\/v1\/P14-2097"},{"key":"33_CR19","first-page":"1143","volume":"24","author":"V Ordonez","year":"2011","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: describing images using 1 million captioned photographs. Adv. Neural Inf. Process. Syst. 24, 1143\u20131151 (2011)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"33_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-642-40763-5_31","volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"A Prasoon","year":"2013","unstructured":"Prasoon, A., Petersen, K., Igel, C., Lauze, F., Dam, E., Nielsen, M.: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 246\u2013253. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40763-5_31"},{"key":"33_CR22","unstructured":"Radford, A., et al.: Improving language understanding by generative pre-training (2018)"},{"key":"33_CR23","first-page":"91","volume":"28","author":"S Ren","year":"2015","unstructured":"Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process Syst. 28, 91\u201399 (2015)","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Reimers, N., Iryna, G.: Sentence-bert: sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"33_CR25","unstructured":"Yang, S.: Feature engineering in fine-grained image classification. Diss. (2013)"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Zhou, L., et al.: Lifer: an interactive lifelog retrieval system. In: Proceedings of the 2018 ACM Workshop on The Lifelog Search Challenge (2018)","DOI":"10.1145\/3210539.3210542"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98358-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T10:13:34Z","timestamp":1708337614000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98358-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983574","9783030983581"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98358-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Phu Quoc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2022","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":"212","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":"84","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":"40% - 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","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":"4","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)"}}]}}