{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T04:12:13Z","timestamp":1743221533262,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031552441"},{"type":"electronic","value":"9783031552458"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-55245-8_3","type":"book-chapter","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T09:09:41Z","timestamp":1710407381000},"page":"39-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Can Machines and\u00a0Humans Use Negation When Describing Images?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4095-7451","authenticated-orcid":false,"given":"Yuri","family":"Sato","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2801-9171","authenticated-orcid":false,"given":"Koji","family":"Mineshima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,15]]},"reference":[{"key":"3_CR1","unstructured":"Ahn, M., et al.: Do as I can, not as I say: grounding language in robotic affordances. In: CoRL 2023, PMLR, vol. 205, pp. 287\u2013318 (2023)"},{"key":"3_CR2","first-page":"325","volume-title":"Social Communication Among Primates","author":"S Altman","year":"1967","unstructured":"Altman, S.: The structure of primate social communication. In: Altman, S. (ed.) Social Communication Among Primates, pp. 325\u2013362. University of Chicago Press, Chicago (1967)"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Vision-and-language navigation: interpreting visually-grounded navigation instructions in real environments. In: CVPR 2018, pp. 3674\u20133683. IEEE (2018)","DOI":"10.1109\/CVPR.2018.00387"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Bender, E. M., Koller, A.: Climbing towards NLU: on meaning, form, and understanding in the age of data. In: ACL 2020, pp. 5185\u20135198 (2020)","DOI":"10.18653\/v1\/2020.acl-main.463"},{"key":"3_CR5","doi-asserted-by":"publisher","unstructured":"Bernardi, R., Pezzelle, S.: Linguistic issues behind visual question answering. Lang. Linguist. Compass 15(6), elnc3.12417 (2021). https:\/\/doi.org\/10.1111\/lnc3.12417","DOI":"10.1111\/lnc3.12417"},{"key":"3_CR6","volume-title":"The Visual Language of Comics: Introduction to the Structure and Cognition of Sequential Images","author":"N Cohn","year":"2013","unstructured":"Cohn, N.: The Visual Language of Comics: Introduction to the Structure and Cognition of Sequential Images. Bloomsbury Academic, London (2013)"},{"key":"3_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/978-3-030-58589-1_23","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Gokhale","year":"2020","unstructured":"Gokhale, T., Banerjee, P., Baral, C., Yang, Y.: VQA-LOL: visual question answering under the lens of logic. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 379\u2013396. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_23"},{"key":"3_CR8","volume-title":"A Natural History of Negation","author":"LR Horn","year":"1989","unstructured":"Horn, L.R.: A Natural History of Negation. University of Chicago Press, Chicago (1989)"},{"key":"3_CR9","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: ICML 2021. PMLR, vol. 139, pp. 5583\u20135594 (2021)"},{"key":"3_CR10","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML 2022. PMLR vol. 162, pp. 12888\u201312900 (2022)"},{"key":"3_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","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.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"3_CR12","doi-asserted-by":"publisher","first-page":"5705","DOI":"10.1007\/s10462-020-09832-7","volume":"53","author":"S Manmadhan","year":"2020","unstructured":"Manmadhan, S., Kovoor, B.C.: Visual question answering: a state-of-the-art review. Artif. Intell. Rev. 53, 5705\u20135745 (2020). https:\/\/doi.org\/10.1007\/s10462-020-09832-7","journal-title":"Artif. Intell. Rev."},{"issue":"20","key":"3_CR13","doi-asserted-by":"publisher","first-page":"21811","DOI":"10.1007\/s11042-016-4020-z","volume":"76","author":"Y Matsui","year":"2017","unstructured":"Matsui, Y., et al.: Sketch-based manga retrieval using manga109 dataset. Multimed. Tools Appl. 76(20), 21811\u201321838 (2017). https:\/\/doi.org\/10.1007\/s11042-016-4020-z","journal-title":"Multimed. Tools Appl."},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"van Miltenburg, E., Morante, R., Elliott, D.: Pragmatic factors in image description: the case of negations. In: VL 2016, pp. 54\u201359. ACL (2016)","DOI":"10.18653\/v1\/W16-3207"},{"key":"3_CR15","doi-asserted-by":"crossref","unstructured":"Park, D. H., Darrell, T., Rohrbach, A.: Robust change captioning. In: ICCV 2019, pp. 4624\u20134633, IEEE (2019)","DOI":"10.1109\/ICCV.2019.00472"},{"issue":"17","key":"3_CR16","doi-asserted-by":"publisher","first-page":"4761","DOI":"10.3390\/s20174761","volume":"20","author":"Y Qiu","year":"2020","unstructured":"Qiu, Y., Satoh, Y., Suzuki, R., Iwata, K., Kataoka, H.: Indoor scene change captioning based on multimodality data. Sensors 20(17), 4761 (2020). https:\/\/doi.org\/10.3390\/s20174761","journal-title":"Sensors"},{"key":"3_CR17","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021. PMLR vol. 139, pp. 8748\u20138763 (2021)"},{"key":"3_CR18","volume-title":"The Problems of Philosophy","author":"B Russell","year":"1912","unstructured":"Russell, B.: The Problems of Philosophy. Oxford University Press, Oxford (1912)"},{"key":"3_CR19","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s10849-015-9225-4","volume":"24","author":"Y Sato","year":"2015","unstructured":"Sato, Y., Mineshima, K.: How diagrams can support syllogistic reasoning: an experimental study. J. Log. Lang. Inf. 24, 409\u2013455 (2015). https:\/\/doi.org\/10.1007\/s10849-015-9225-4","journal-title":"J. Log. Lang. Inf."},{"key":"3_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1007\/978-3-031-15146-0_34","volume-title":"Diagrammatic Representation and Inference","author":"Y Sato","year":"2022","unstructured":"Sato, Y., Mineshima, K.: Visually analyzing universal quantifiers in photograph captions. In: Giardino, V., Linker, S., Burns, R., Bellucci, F., Boucheix, J.M., Viana, P. (eds.) Diagrams 2022. LNCS, vol. 13462, pp. 373\u2013377. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-15146-0_34"},{"issue":"3","key":"3_CR21","doi-asserted-by":"publisher","first-page":"e13258","DOI":"10.1111\/cogs.13258","volume":"47","author":"Y Sato","year":"2023","unstructured":"Sato, Y., Mineshima, K., Ueda, K.: Can negation be depicted? Comparing human and machine understanding of visual representations. Cogn. Sci. 47(3), e13258 (2023). https:\/\/doi.org\/10.1111\/cogs.13258","journal-title":"Cogn. Sci."},{"issue":"1","key":"3_CR22","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11023-023-09622-4","volume":"33","author":"A S\u00f8gaard","year":"2023","unstructured":"S\u00f8gaard, A.: Grounding the vector space of an octopus: word meaning from raw text. Minds Mach. 33(1), 33\u201354 (2023). https:\/\/doi.org\/10.1007\/s11023-023-09622-4","journal-title":"Minds Mach."},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Yoshikawa, Y., Shigeto, Y., Takeuchi, A.: STAIR captions: constructing a large-scale Japanese image caption dataset. In: ACL 2017, pp. 417\u2013421 (2017)","DOI":"10.18653\/v1\/P17-2066"},{"key":"3_CR24","unstructured":"Wittgenstein, L.: Notebooks 1914-1916. In: Anscombe, G.E.M., von Wright, G.H. (eds.) University of Chicago Press, Chicago (1984). (Original Work Published 1914)"}],"container-title":["Lecture Notes in Computer Science","Human and Artificial Rationalities"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-55245-8_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T13:57:02Z","timestamp":1743170222000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-55245-8_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031552441","9783031552458"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-55245-8_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"HAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Human and Artificial Rationalities","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"19 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"har2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/har-conf.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}