{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T02:16:07Z","timestamp":1784513767766,"version":"3.55.0"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585570","type":"print"},{"value":"9783030585587","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58558-7_30","type":"book-chapter","created":{"date-parts":[[2020,10,28]],"date-time":"2020-10-28T09:03:08Z","timestamp":1603875788000},"page":"508-524","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":46,"title":["VisualCOMET: Reasoning About the Dynamic Context of a Still Image"],"prefix":"10.1007","author":[{"given":"Jae Sung","family":"Park","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chandra","family":"Bhagavatula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roozbeh","family":"Mottaghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Farhadi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yejin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"30_CR1","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s11263-016-0966-6","volume":"123","author":"A Agrawal","year":"2015","unstructured":"Agrawal, A., et al.: VQA: visual question answering. Int. J. Comput. Vision 123, 4\u201331 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L., Savarese, S.: Social LSTM: human trajectory prediction in crowded spaces. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.110"},{"key":"30_CR3","unstructured":"Bhagavatula, C., et al.: Abductive commonsense reasoning. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=Byg1v1HKDB"},{"key":"30_CR4","doi-asserted-by":"publisher","unstructured":"Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., Choi, Y.: COMET: commonsense transformers for automatic knowledge graph construction. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 4762\u20134779. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1470. https:\/\/www.aclweb.org\/anthology\/P19-1470","DOI":"10.18653\/v1\/P19-1470"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Castrej\u00f3n, L., Ballas, N., Courville, A.C.: Improved VRNNs for video prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00770"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Yang, J., Price, B.L., Cohen, S., Deng, J.: Forecasting human dynamics from static images. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.388"},{"key":"30_CR7","unstructured":"Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv (2015)"},{"key":"30_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: Uniter: learning universal image-text representations. arXiv (2019)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Das, A., et al.: Visual dialog. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.121"},{"key":"30_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"30_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv (2018)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"30_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"30_CR15","unstructured":"Holtzman, A., Buys, J., Forbes, M., Choi, Y.: The curious case of neural text degeneration. arXiv (2019)"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, J.E., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C.L., Girshick, R.B.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: referring to objects in photographs of natural scenes. In: EMNLP (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"30_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv (2014)"},{"key":"30_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-319-10578-9_45","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T Lan","year":"2014","unstructured":"Lan, T., Chen, T.-C., Savarese, S.: A hierarchical representation for future action prediction. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 689\u2013704. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_45"},{"key":"30_CR20","unstructured":"Lavie, M.D.A.: Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2014)"},{"key":"30_CR21","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00331"},{"key":"30_CR24","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: Bengio, Y., LeCun, Y. (eds.) ICLR (2016)"},{"key":"30_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/978-3-319-46493-0_17","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Mottaghi","year":"2016","unstructured":"Mottaghi, R., Rastegari, M., Gupta, A., Farhadi, A.: \u201cWhat happens if...\u201d learning to predict the effect of forces in images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 269\u2013285. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_17"},{"key":"30_CR26","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 Annual Meeting of the Association for Computational Linguistics (ACL) (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"30_CR27","doi-asserted-by":"crossref","unstructured":"Pirsiavash, H., Vondrick, C., Torralba, A.: Inferring the why in images. arXiv (2014)","DOI":"10.21236\/ADA612444"},{"key":"30_CR28","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: collecting region-to-phrase correspondences for richer image-to-sentence models. In: IJCV (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"30_CR29","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. OpenAI Blog 1(8) (2019)"},{"key":"30_CR30","unstructured":"Ranzato, M., Szlam, A., Bruna, J., Mathieu, M., Collobert, R., Chopra, S.: Video (language) modeling: a baseline for generative models of natural videos. arXiv (2014)"},{"key":"30_CR31","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS) (2015)"},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Sap, M., et al.: Atomic: an atlas of machine commonsense for if-then reasoning. In: Proceedings of the Conference on Artificial Intelligence (AAAI) (2019)","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"30_CR33","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 Annual Meeting of the Association for Computational Linguistics (ACL) (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"30_CR34","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMS. In: ICML (2015)"},{"key":"30_CR35","unstructured":"Su, W., et al.: Vl-bert: pre-training of generic visual-linguistic representations. In: ICLR (2020)"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Sukthankar, R., Murphy, K., Schmid, C.: Relational action forecasting. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00036"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: Lxmert: learning cross-modality encoder representations from transformers. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"30_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS) (2017)"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lin, X., Batra, T., Zitnick, C.L., Parikh, D.: Learning common sense through visual abstraction. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.292"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"30_CR41","unstructured":"Villegas, R., Pathak, A., Kannan, H., Erhan, D., Le, Q.V., Lee, H.: High fidelity video prediction with large stochastic recurrent neural networks. In: NeurIPS (2019)"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"30_CR43","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: NeurIPS (2016)"},{"key":"30_CR44","doi-asserted-by":"crossref","unstructured":"Walker, J., Gupta, A., Hebert, M.: Patch to the future: unsupervised visual prediction. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.416"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.361"},{"key":"30_CR46","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: NeurIPS (2016)"},{"key":"30_CR47","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"30_CR48","unstructured":"Zellers, R., et al.: Defending against neural fake news. In: Advances in Neural Information Processing Systems (NIPS) (2019)"},{"key":"30_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, L., Hamid, P., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and question answering. In: Proceedings of the Conference on Artificial Intelligence (AAAI) (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"30_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Berg, T.L.: Temporal perception and prediction in ego-centric video. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.511"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58558-7_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T08:55:47Z","timestamp":1730105747000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58558-7_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585570","9783030585587"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58558-7_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 October 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}