{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T08:19:03Z","timestamp":1772698743238,"version":"3.50.1"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032101914","type":"print"},{"value":"9783032101921","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-10192-1_42","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:45:45Z","timestamp":1767314745000},"page":"499-511","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["How Far Can Off-the-Shelf Multimodal Large Language Models Go in Online Episodic Memory Question Answering?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4209-6852","authenticated-orcid":false,"given":"Giuseppe","family":"Lando","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2334-0307","authenticated-orcid":false,"given":"Rosario","family":"Forte","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6034-0432","authenticated-orcid":false,"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6911-0302","authenticated-orcid":false,"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"42_CR1","doi-asserted-by":"publisher","unstructured":"B\u00e4rmann, L., Waibel, A.: Where did i leave my keys?\u2014Episodic-memory-based question answering on egocentric videos. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1559\u20131567 (2022). https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00162","DOI":"10.1109\/CVPRW56347.2022.00162"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Di, S., Xie, W.: Grounded question-answering in long egocentric videos. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01229"},{"key":"42_CR3","unstructured":"Di, S., Yu, Z., Zhang, G., Li, H., Zhong, T., Cheng, H., Li, B., He, W., Shu, F., Jiang, H.: Streaming video question-answering with in-context video kv-cache retrieval (2025). https:\/\/arxiv.org\/abs\/2503.00540"},{"key":"42_CR4","unstructured":"Grauman, K., et\u00a0al.: Ego4d: Around the world in 3,000 hours of egocentric video (2022). https:\/\/arxiv.org\/abs\/2110.07058"},{"key":"42_CR5","unstructured":"Li, B., Zhang, Y., Guo, D., Zhang, R., Li, F., Zhang, H., Zhang, K., Li, Y., Liu, Z., Li, C.: Llava-onevision: Easy visual task transfer (2024). arXiv:2408.03326"},{"key":"42_CR6","unstructured":"Patel, A., Chitalia, V., Yang, Y.: Advancing egocentric video question answering with multimodal large language models (2025). https:\/\/arxiv.org\/abs\/2504.04550"},{"key":"42_CR7","unstructured":"Qwen, et\u00a0al.: Qwen2.5 technical report (2025). https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"42_CR8","unstructured":"Ryoo, M., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: adaptive space-time tokenization for videos. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol.\u00a034, pp. 12786\u201312797. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/6a30e32e56fce5cf381895dfe6ca7b6f-Paper.pdf"},{"key":"42_CR9","unstructured":"Team, G., et\u00a0al.: Gemini: A family of highly capable multimodal models (2024). https:\/\/arxiv.org\/abs\/2312.11805"},{"issue":"381\u2013403","key":"42_CR10","first-page":"1","volume":"1","author":"E Tulving","year":"1972","unstructured":"Tulving, E., et al.: Episodic and semantic memory. Organ. Mem. 1(381\u2013403), 1 (1972)","journal-title":"Organ. Mem."},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, K., Li, X., Yu, J., He, Y., Wang, C., Chen, G., Pei, B., Yan, Z., Zheng, R., Xu, J., Wang, Z., Shi, Y., Jiang, T., Li, S., Zhang, H., Huang, Y., Qiao, Y., Wang, Y., Wang, L.: Internvideo2: scaling foundation models for multimodal video understanding (2024). https:\/\/arxiv.org\/abs\/2403.15377","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"42_CR12","doi-asserted-by":"crossref","unstructured":"Yang, J., Liu, S., Guo, H., Dong, Y., Zhang, X., Zhang, S., Wang, P., Zhou, Z., Xie, B., Wang, Z., Ouyang, B., Lin, Z., Cominelli, M., Cai, Z., Zhang, Y., Zhang, P., Hong, F., Widmer, J., Gringoli, F., Yang, L., Li, B., Liu, Z.: Egolife: towards egocentric life assistant (2025). https:\/\/arxiv.org\/abs\/2503.03803","DOI":"10.1109\/CVPR52734.2025.02690"},{"key":"42_CR13","unstructured":"Zhang, B., Li, K., Cheng, Z., Hu, Z., Yuan, Y., Chen, G., Leng, S., Jiang, Y., Zhang, H., Li, X., Jin, P., Zhang, W., Wang, F., Bing, L., Zhao, D.: Videollama 3: frontier multimodal foundation models for image and video understanding (2025). https:\/\/arxiv.org\/abs\/2501.13106"},{"key":"42_CR14","unstructured":"Zhang, M., Press, O., Merrill, W., Liu, A., Smith, N.A.: How language model hallucinations can snowball. In: Forty-first International Conference on Machine Learning (2024). https:\/\/openreview.net\/forum?id=FPlaQyAGHu"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10192-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:37:53Z","timestamp":1772696273000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10192-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032101914","9783032101921"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10192-1_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}