{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:30:54Z","timestamp":1791567054722,"version":"4.3.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732317","type":"print"},{"value":"9783031732324","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73232-4_3","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"39-57","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["FunQA: Towards Surprising Video Comprehension"],"prefix":"10.1007","author":[{"given":"Binzhu","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zitang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Hessel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingkang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Attardo, S.: A primer for the linguistics of humor. In: The Primer of Humor Research, vol. 8, pp. 101\u2013156 (2008)","DOI":"10.1515\/9783110198492.101"},{"key":"3_CR2","doi-asserted-by":"publisher","DOI":"10.4135\/9781446211779","volume-title":"Laughter and Ridicule: Towards a Social Critique of Humour","author":"M Billig","year":"2005","unstructured":"Billig, M.: Laughter and Ridicule: Towards a Social Critique of Humour. Sage, Thousand Oaks (2005)"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Bitton-Guetta, N., et al.: Breaking common sense: whoops! a vision-and-language benchmark of synthetic and compositional images (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.07274. https:\/\/arxiv.org\/abs\/2303.07274","DOI":"10.48550\/ARXIV.2303.07274"},{"issue":"1","key":"3_CR4","first-page":"1","volume":"28","author":"B Boyd","year":"2004","unstructured":"Boyd, B.: Laughter and literature: a play theory of humor. Philos. Lit. 28(1), 1\u201322 (2004)","journal-title":"Philos. Lit."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Castro, S., Hazarika, D., P\u00e9rez-Rosas, V., Zimmermann, R., Mihalcea, R., Poria, S.: Towards multimodal sarcasm detection. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Florence, Italy. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1455"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Castro, S., et al.: Fiber: fill-in-the-blanks as a challenging video understanding evaluation framework (2022)","DOI":"10.18653\/v1\/2022.acl-long.209"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Chiang, C.H., Lee, H.Y.: Can large language models be an alternative to human evaluations? arXiv preprint arXiv:2305.01937 (2023)","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"3_CR8","unstructured":"Nippon\u2002Television\u2002Network\u2002Corporation: Kasou taishou. https:\/\/www.ntv.co.jp\/kasoh\/index.html. Accessed 23 Apr 2023"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Epstein, D., Chen, B., Vondrick, C.: Oops! predicting unintentional action in video. In: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Fu, J., Ng, S.K., Jiang, Z., Liu, P.: Gptscore: evaluate as you desire. arXiv preprint arXiv:2302.04166 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"3_CR11","unstructured":"Fu, T.J., et al.: Violet: end-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681 (2021)"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Gao, D., Wang, R., Bai, Z., Chen, X.: Env-QA: a video question answering benchmark for comprehensive understanding of dynamic environments, pp. 1675\u20131685 (2021)","DOI":"10.1109\/ICCV48922.2021.00170"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Gao, D., Zhou, L., Ji, L., Zhu, L., Yang, Y., Shou, M.Z.: MIST: multi-modal iterative spatial-temporal transformer for long-form video question answering. arXiv preprint arXiv:2212.09522 (2022)","DOI":"10.1109\/CVPR52729.2023.01419"},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Garcia, N., Otani, M., Chu, C., Nakashima, Y.: Knowit VQA: answering knowledge-based questions about videos. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6713"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Grunde-McLaughlin, M., Krishna, R., Agrawala, M.: AGQA: a benchmark for compositional spatio-temporal reasoning (2021)","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"3_CR17","unstructured":"Gruner, C.R.: Understanding Laughter: The Workings of Wit & Humor. Burnham Incorporated Pub (1978)"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Hasan, M.K., et al.: UR-FUNNY: a multimodal language dataset for understanding humor. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 2046\u20132056. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1211. https:\/\/aclanthology.org\/D19-1211","DOI":"10.18653\/v1\/D19-1211"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Hessel, J., et al.: Do androids laugh at electric sheep? humor \u201cunderstanding\u201d benchmarks from the New Yorker caption contest (2022)","DOI":"10.18653\/v1\/2023.acl-long.41"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1007\/s11263-019-01189-x","volume":"127","author":"Y Jang","year":"2019","unstructured":"Jang, Y., Song, Y., Kim, C.D., Yu, Y., Kim, Y., Kim, G.: Video question answering with spatio-temporal reasoning. IJCV 127, 1385\u20131412 (2019)","journal-title":"IJCV"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, P., Han, Y.: Reasoning with heterogeneous graph alignment for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Kamalloo, E., Dziri, N., Clarke, C.L., Rafiei, D.: Evaluating open-domain question answering in the era of large language models. arXiv preprint arXiv:2305.06984 (2023)","DOI":"10.18653\/v1\/2023.acl-long.307"},{"key":"3_CR23","unstructured":"Kant, I.: Critique of Judgment. Hackett Publishing (1987)"},{"key":"3_CR24","unstructured":"Kay, W., et al.: The kinetics human action video dataset (2017)"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Koestler, A.: The act of creation. In: Brain Function, Volume IV: Brain Function and Learning, pp. 327\u2013346. University of California Press (2020)","DOI":"10.1525\/9780520340176-014"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Kougia, V., et al.: Memegraphs: linking memes to knowledge graphs (2023)","DOI":"10.1007\/978-3-031-41676-7_31"},{"key":"3_CR27","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"3_CR28","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations (2016)"},{"key":"3_CR29","unstructured":"Lamont, P., Wiseman, R.: Magic in Theory: An Introduction to the Theoretical and Psychological Elements of Conjuring. University of Hertfordshire Press (2005)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Latta, R.L.: The Basic Humor Process: A Cognitive-Shift Theory and the Case Against Incongruity. De Gruyter Mouton (1999)","DOI":"10.1515\/9783110806137"},{"key":"3_CR31","unstructured":"Lei, J., et al.: Less is more: CLIPBERT for video-and-language learning via sparse sampling\u2013supplementary file"},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVQA+: spatio-temporal grounding for video question answering. Tech Report, arXiv (2019)","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"3_CR34","unstructured":"Li, B., et al.: Lmms-eval: accelerating the development of large multimoal models (2024). https:\/\/github.com\/EvolvingLMMs-Lab\/lmms-eval"},{"key":"3_CR35","unstructured":"Li, B., Zhang, Y., Chen, L., Wang, J., Yang, J., Liu, Z.: Otter: a multi-modal model with in-context instruction tuning. arXiv preprint arXiv:2305.03726 (2023)"},{"key":"3_CR36","doi-asserted-by":"crossref","unstructured":"Li, C., et al.: mPLUG: effective and efficient vision-language learning by cross-modal skip-connections (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.488"},{"key":"3_CR37","unstructured":"Li, K., et al.: Videochat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Li, X., et al.: Beyond RNNs: positional self-attention with co-attention for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8658\u20138665 (2019)","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"3_CR39","unstructured":"Lin, B., et al.: Video-llava: learning united visual representation by alignment before projection (2023). https:\/\/arxiv.org\/abs\/2311.10122"},{"key":"3_CR40","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"3_CR41","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: Univtg: towards unified video-language temporal grounding (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"3_CR42","unstructured":"Liu, H., et al.: Llava-next: improved reasoning, OCR, and world knowledge (2024). https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next\/"},{"key":"3_CR43","unstructured":"Malinowski, M., Fritz, M.: A multi-world approach to question answering about real-world scenes based on uncertain input. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"issue":"1","key":"3_CR44","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1093\/bjaesthetics\/23.1.74","volume":"23","author":"MW Martin","year":"1983","unstructured":"Martin, M.W.: Humour and aesthetic enjoyment of incongruities. Br. J. Aesthet. 23(1), 74\u201385 (1983)","journal-title":"Br. J. Aesthet."},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"3_CR46","unstructured":"Morreall, J.: Philosophy of Humor. In: Zalta, E.N., Nodelman, U. (eds.) The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, Summer 2023 edn. (2023)"},{"key":"3_CR47","unstructured":"Maaz, M., Hanoona\u00a0Rasheed, S.K., Khan, F.: Video-chatgpt (2023). https:\/\/github.com\/mbzuai-oryx\/Video-ChatGPT"},{"key":"3_CR48","doi-asserted-by":"crossref","unstructured":"Mun, J., Hongsuck\u00a0Seo, P., Jung, I., Han, B.: Marioqa: answering questions by watching gameplay videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2867\u20132875 (2017)","DOI":"10.1109\/ICCV.2017.312"},{"key":"3_CR49","unstructured":"Nelms, H.: Magic and Showmanship: A Handbook for Conjurers. Courier Corporation (2012)"},{"issue":"7","key":"3_CR50","doi-asserted-by":"publisher","first-page":"1326","DOI":"10.1080\/02699931.2013.777660","volume":"27","author":"MK Noordewier","year":"2013","unstructured":"Noordewier, M.K., Breugelmans, S.M.: On the valence of surprise. Cogn. Emot. 27(7), 1326\u20131334 (2013)","journal-title":"Cogn. Emot."},{"key":"3_CR51","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"3_CR52","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"3_CR53","doi-asserted-by":"crossref","unstructured":"Patro, B.N., Lunayach, M., Srivastava, D., Sarvesh, Singh, H., Namboodiri, V.P.: Multimodal humor dataset: predicting laughter tracks for sitcoms. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 576\u2013585 (2021)","DOI":"10.1109\/WACV48630.2021.00062"},{"key":"3_CR54","doi-asserted-by":"crossref","unstructured":"Pu, A., Chung, H.W., Parikh, A.P., Gehrmann, S., Sellam, T.: Learning compact metrics for MT. In: Proceedings of EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.58"},{"key":"3_CR55","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: Timechat: a time-sensitive multimodal large language model for long video understanding. arXiv abs\/2312.02051 (2023)"},{"issue":"1","key":"3_CR56","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1080\/10400419.2012.650092","volume":"24","author":"MA Runco","year":"2012","unstructured":"Runco, M.A., Jaeger, G.J.: The standard definition of creativity. Creat. Res. J. 24(1), 92\u201396 (2012)","journal-title":"Creat. Res. J."},{"key":"3_CR57","unstructured":"Seo, P.H., Nagrani, A., Schmid, C.: Look before you speak: visually contextualized utterances. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16877\u201316887 (2021)"},{"key":"3_CR58","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":"3_CR59","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence\u00a0Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"3_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Is chatgpt a good NLG evaluator? A preliminary study. arXiv preprint arXiv:2303.04048 (2023)","DOI":"10.18653\/v1\/2023.newsum-1.1"},{"key":"3_CR61","unstructured":"Wang, J., et al.: GIT: a generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)"},{"key":"3_CR62","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: STAR: a benchmark for situated reasoning in real-world videos. In: Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) (2021). https:\/\/openreview.net\/forum?id=EfgNF5-ZAjM"},{"key":"3_CR63","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: NExT-QA: next phase of question-answering to explaining temporal actions (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"3_CR64","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":"3_CR65","doi-asserted-by":"crossref","unstructured":"Xu, L., Huang, H., Liu, J.: Sutd-trafficqa: a question answering benchmark and an efficient network for video reasoning over traffic events. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9878\u20139888 (2021)","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"3_CR66","doi-asserted-by":"crossref","unstructured":"Xue, H., et al.: Advancing high-resolution video-language representation with large-scale video transcriptions. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"3_CR67","doi-asserted-by":"crossref","unstructured":"Yang, J., et\u00a0al.: Panoptic video scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18675\u201318685 (2023)","DOI":"10.1109\/CVPR52729.2023.01791"},{"key":"3_CR68","doi-asserted-by":"crossref","unstructured":"Yang, P., et al.: AVQA: a dataset for audio-visual question answering on videos. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3480\u20133491 (2022)","DOI":"10.1145\/3503161.3548291"},{"key":"3_CR69","unstructured":"Ye, Q., et al.: mPLUG-Owl: modularization empowers large language models with multimodality (2023)"},{"key":"3_CR70","doi-asserted-by":"publisher","unstructured":"Ye, Y., Zhao, Z., Li, Y., Chen, L., Xiao, J., Zhuang, Y.: Video question answering via attribute-augmented attention network learning. In: Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR 2017. ACM (2017). https:\/\/doi.org\/10.1145\/3077136.3080655","DOI":"10.1145\/3077136.3080655"},{"key":"3_CR71","unstructured":"Yi, K., et al.: Clevrer: collision events for video representation and reasoning (2020)"},{"key":"3_CR72","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Activitynet-QA: a dataset for understanding complex web videos via question answering. In: AAAI, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"3_CR73","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chan, M., Liang, P.P., Tong, E., Morency, L.P.: Social-IQ: a question answering benchmark for artificial social intelligence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8807\u20138817 (2019)","DOI":"10.1109\/CVPR.2019.00901"},{"key":"3_CR74","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). https:\/\/arxiv.org\/abs\/2306.02858","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"3_CR75","doi-asserted-by":"crossref","unstructured":"Zhao, Z., et al.: Open-ended long-form video question answering via adaptive hierarchical reinforced networks. In: IJCAI, vol.\u00a02, p.\u00a08 (2018)","DOI":"10.24963\/ijcai.2018\/512"},{"key":"3_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.: Towards automatic learning of procedures from web instructional videos. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"3_CR77","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Groth, O., Bernstein, M., Fei-Fei, L.: Visual7w: grounded question answering in images (2016)","DOI":"10.1109\/CVPR.2016.540"}],"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\/978-3-031-73232-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:02:38Z","timestamp":1727589758000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73232-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732317","9783031732324"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73232-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}