{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:40:02Z","timestamp":1782834002850,"version":"3.54.5"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733963","type":"print"},{"value":"9783031733970","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-3-031-73397-0_15","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T19:09:54Z","timestamp":1730574594000},"page":"251-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Goldfish: Vision-Language Understanding of\u00a0Arbitrarily Long Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0495-2171","authenticated-orcid":false,"given":"Kirolos","family":"Ataallah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6284-520X","authenticated-orcid":false,"given":"Xiaoqian","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eslam","family":"Abdelrahman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1505-6694","authenticated-orcid":false,"given":"Essam","family":"Sleiman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2561-7712","authenticated-orcid":false,"given":"Mingchen","family":"Zhuge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7188-5884","authenticated-orcid":false,"given":"Jian","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8014-7309","authenticated-orcid":false,"given":"Deyao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1468-6758","authenticated-orcid":false,"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9659-1551","authenticated-orcid":false,"given":"Mohamed","family":"Elhoseiny","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Brown, A., Zisserman, A.: Condensed movies: story based retrieval with contextual embeddings. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69541-5_28"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Caba\u00a0Heilbron, F., Escorcia, V., Ghanem, B., Carlos\u00a0Niebles, J.: ActivityNet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"15_CR4","unstructured":"Chen, J., et al.: MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., Hu, H., Chen, X., Verga, P., Cohen, W.W.: MuRAG: multimodal retrieval-augmented generator for open question answering over images and text (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"15_CR6","unstructured":"Doe, J.: The needle in a haystack test (2021). https:\/\/towardsdatascience.com\/the-needle-in-a-haystack-test-a94974c1ad38"},{"key":"15_CR7","unstructured":"Gu, J., Wang, Y., Cho, K., Li, V.O.K.: Search engine guided non-parametric neural machine translation (2018)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Q., Xiong, Y., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding (2020)","DOI":"10.1007\/978-3-030-58548-8_41"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"15_CR11","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: nearest neighbor language models (2020)"},{"key":"15_CR12","unstructured":"Khattab, O., et al.: Demonstrate-search-predict: composing retrieval and language models for knowledge-intensive NLP (2023)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Le, H., Chen, N.F., Hoi, S.C.H.: VGNMN: video-grounded neural module network to video-grounded language tasks (2022)","DOI":"10.18653\/v1\/2022.naacl-main.247"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering (2019)","DOI":"10.18653\/v1\/D18-1167"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVR: a large-scale dataset for video-subtitle moment retrieval. arXiv preprint arXiv:2001.09099 (2020)","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"15_CR16","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks (2021)"},{"key":"15_CR17","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"15_CR18","unstructured":"Li, K., et al.: VideoChat: chat-centric video understanding (2024)"},{"key":"15_CR19","unstructured":"Li, X., et al.: Chain-of-knowledge: grounding large language models via dynamic knowledge adapting over heterogeneous sources (2024)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, C., Jia, J.: LLAMA-VID: an image is worth 2 tokens in large language models (2023)","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., Xu, L.: InterGen: diffusion-based multi-human motion generation under complex interactions (2023)","DOI":"10.1007\/s11263-024-02042-6"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-LLaVA: learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Lin, W., Byrne, B.: Retrieval augmented visual question answering with outside knowledge (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"key":"15_CR24","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Liu, R., Li, C., Ge, Y., Shan, Y., Li, T.H., Li, G.: One for all: video conversation is feasible without video instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.01296"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.S.: Video-chatGPT: towards detailed video understanding via large vision and language models. arXiv preprint arXiv:2306.05424 (2023)","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"15_CR28","unstructured":"OpenAI: New embedding models and API updates (2024). https:\/\/openai.com\/blog\/new-embedding-models-and-api-updates"},{"key":"15_CR29","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. Adv. Neural Inf. Process. Syst. 24 (2011)"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Peng, H., Parikh, A.P., Faruqui, M., Dhingra, B., Das, D.: Text generation with exemplar-based adaptive decoding (2019)","DOI":"10.18653\/v1\/N19-1263"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Ram, O., et al.: In-context retrieval-augmented language models (2023)","DOI":"10.1162\/tacl_a_00605"},{"key":"15_CR32","unstructured":"Reimers, N.: Pretrained models (2024). https:\/\/www.sbert.net\/docs\/pretrained_models.html"},{"key":"15_CR33","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs (2021)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Song, E., et al.: MovieChat: from dense token to sparse memory for long video understanding (2023)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"15_CR36","unstructured":"Sun, Q., Fang, Y., Wu, L., Wang, X., Cao, Y.: EVA-CLIP: improved training techniques for clip at scale. arXiv preprint arXiv:2303.15389 (2023)"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4631\u20134640 (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"15_CR38","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, P., Sun, M., Liu, Y.: Self-knowledge guided retrieval augmentation for large language models (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.691"},{"key":"15_CR40","doi-asserted-by":"crossref","unstructured":"Weston, J., Dinan, E., Miller, A.H.: Retrieve and refine: improved sequence generation models for dialogue (2018)","DOI":"10.18653\/v1\/W18-5713"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Whitehead, S., Ji, H., Bansal, M., Chang, S.F., Voss, C.: Incorporating background knowledge into video description generation. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3992\u20134001 (2018)","DOI":"10.18653\/v1\/D18-1433"},{"key":"15_CR42","unstructured":"Wu, Y., Wei, F., Huang, S., Wang, Y., Li, Z., Zhou, M.: Response generation by context-aware prototype editing (2018)"},{"key":"15_CR43","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1645\u20131653 (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"15_CR44","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models (2022)"},{"key":"15_CR45","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: ActivityNet-QA: a dataset for understanding complex web videos via question answering (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"15_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-Llama: an instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, J., Utiyama, M., Sumita, E., Neubig, G., Nakamura, S.: Guiding neural machine translation with retrieved translation pieces (2018)","DOI":"10.18653\/v1\/N18-1120"},{"key":"15_CR48","unstructured":"Zhang, R., et al.: LLaMA-Adapter: efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)"},{"key":"15_CR49","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Zhuge, M., et al.: Kaleido-BERT: vision-language pre-training on fashion domain. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12647\u201312657 (2021)","DOI":"10.1109\/CVPR46437.2021.01246"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73397-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T18:18:14Z","timestamp":1732990694000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73397-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9783031733963","9783031733970"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73397-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}