{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:58:33Z","timestamp":1780765113938,"version":"3.54.1"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198359","type":"print"},{"value":"9783031198366","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19836-6_17","type":"book-chapter","created":{"date-parts":[[2022,10,21]],"date-time":"2022-10-21T09:04:58Z","timestamp":1666343098000},"page":"292-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["PACS: A Dataset for\u00a0Physical Audiovisual CommonSense Reasoning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9734-9265","authenticated-orcid":false,"given":"Samuel","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruslan","family":"Salakhutdinov","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,22]]},"reference":[{"key":"17_CR1","unstructured":"Standard list of material categories and types (2018). https:\/\/www.calrecycle.ca.gov\/lgcentral\/basics\/standlst"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D.: Analyzing the behavior of visual question answering models. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 1955\u20131960 (2016)","DOI":"10.18653\/v1\/D16-1203"},{"key":"17_CR3","unstructured":"Agrawal, P., Nair, A.V., Abbeel, P., Malik, J., Levine, S.: Learning to poke by poking: experiential learning of intuitive physics. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"17_CR4","unstructured":"Anand, A., Belilovsky, E., Kastner, K., Larochelle, H., Courville, A.: Blindfold baselines for embodied QA. arXiv preprint arXiv:1811.05013 (2018)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Bisk, Y., Zellers, R., Gao, J., Choi, Y., et al.: PIQA: reasoning about physical commonsense in natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7432\u20137439 (2020)","DOI":"10.1609\/aaai.v34i05.6239"},{"issue":"2","key":"17_CR7","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1080\/03057260802264149","volume":"44","author":"J Bliss","year":"2008","unstructured":"Bliss, J.: Commonsense reasoning about the physical world. Stud. Sci. Educ. 44(2), 123\u2013155 (2008)","journal-title":"Stud. Sci. Educ."},{"issue":"1\u20133","key":"17_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0004-3702(84)90036-5","volume":"24","author":"DG Bobrow","year":"1984","unstructured":"Bobrow, D.G.: Qualitative reasoning about physical systems: an introduction. Artif. Intell. 24(1\u20133), 1\u20135 (1984)","journal-title":"Artif. Intell."},{"key":"17_CR9","first-page":"841","volume":"32","author":"R Cadene","year":"2019","unstructured":"Cadene, R., Dancette, C., Cord, M., Parikh, D., et al.: Rubi: reducing unimodal biases for visual question answering. Adv. Neural. Inf. Process. Syst. 32, 841\u2013852 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"17_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-030-58539-6_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Chen","year":"2020","unstructured":"Chen, C., et al.: SoundSpaces: audio-visual navigation in\u00a03D\u00a0environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 17\u201336. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_2"},{"key":"17_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, S., Yuan, T., Qi, S., Zhu, Y., Zhu, S.C.: Holistic++ scene understanding: single-view 3D holistic scene parsing and human pose estimation with human-object interaction and physical commonsense. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00874"},{"issue":"3","key":"17_CR13","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1002\/wps.20557","volume":"17","author":"PR Corlett","year":"2018","unstructured":"Corlett, P.R., Powers, A.R.: Conditioned hallucinations: historic insights and future directions. World Psychiatry 17(3), 361 (2018)","journal-title":"World Psychiatry"},{"key":"17_CR14","unstructured":"Coumans, E., Bai, Y.: PyBullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning (2016-2021). http:\/\/pybullet.org"},{"key":"17_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"17_CR16","unstructured":"Forbes, M., Holtzman, A., Choi, Y.: Do neural language representations learn physical commonsense? CogSci (2019)"},{"issue":"1\u20133","key":"17_CR17","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/0004-3702(84)90038-9","volume":"24","author":"KD Forbus","year":"1984","unstructured":"Forbus, K.D.: Qualitative process theory. Artif. Intell. 24(1\u20133), 85\u2013168 (1984)","journal-title":"Artif. Intell."},{"key":"17_CR18","unstructured":"Gao, R., Chang, Y.Y., Mall, S., Fei-Fei, L., Wu, J.: Objectfolder: a dataset of objects with implicit visual, auditory, and tactile representations. CoRL (2021)"},{"key":"17_CR19","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T.: pyAudioAnalysis: an open-source python library for audio signal analysis. PLoS ONE 10(12), e0144610 (2015)","DOI":"10.1371\/journal.pone.0144610"},{"key":"17_CR21","doi-asserted-by":"publisher","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: audio spectrogram transformer. In: Proceedings of Interspeech 2021, pp. 571\u2013575 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-698","DOI":"10.21437\/Interspeech.2021-698"},{"key":"17_CR22","doi-asserted-by":"publisher","unstructured":"Goyal, R., et al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense, pp. 5843\u20135851 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.622","DOI":"10.1109\/ICCV.2017.622"},{"key":"17_CR23","unstructured":"Guzhov, A., Raue, F., Hees, J., Dengel, A.: Audioclip: extending clip to image, text and audio. arXiv preprint arXiv:2008.04838 (2020)"},{"key":"17_CR24","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/B978-012505626-7\/50014-5","volume":"2","author":"S Handel","year":"1995","unstructured":"Handel, S.: Timbre perception and auditory object identification. Hearing 2, 425\u2013461 (1995)","journal-title":"Hearing"},{"key":"17_CR25","volume-title":"Knowledge Representation","author":"P Hayes","year":"1987","unstructured":"Hayes, P., Nilsson, N.J.: Knowledge Representation. Morgan Kaufman, Burlington (1987)"},{"key":"17_CR26","unstructured":"He, P., Gao, J., Chen, W.: DeBERTaV3: improving DeBERTa using ELECTRA-Style pre-training with gradient-disentangled embedding sharing (2021)"},{"key":"17_CR27","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: DeBERTa: decoding-enhanced BERT with disentangled attention. In: International Conference on Learning Representations (2021). https:\/\/openreview.net\/forum?id=XPZIaotutsD"},{"key":"17_CR28","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1177\/0956797615617897","volume":"27","author":"SJ Hespos","year":"2016","unstructured":"Hespos, S.J., Ferry, A., Anderson, E., Hollenbeck, E., Rips, L.J.: Five-month-old infants have general knowledge of how nonsolid substances behave and interact. Psychol. Sci. 27, 244\u2013256 (2016)","journal-title":"Psychol. Sci."},{"issue":"6998","key":"17_CR29","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1038\/nature02634","volume":"430","author":"SJ Hespos","year":"2004","unstructured":"Hespos, S.J., Spelke, E.S.: Conceptual precursors to language. Nature 430(6998), 453\u2013456 (2004)","journal-title":"Nature"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Hessel, J., Mimno, D., Lee, L.: Quantifying the visual concreteness of words and topics in multimodal datasets. In: Proceedings of NAACL-HLT, pp. 2194\u20132205 (2018)","DOI":"10.18653\/v1\/N18-1199"},{"key":"17_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1007\/978-3-319-46484-8_44","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Jabri","year":"2016","unstructured":"Jabri, A., Joulin, A., van der Maaten, L.: Revisiting visual question answering baselines. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 727\u2013739. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_44"},{"key":"17_CR32","unstructured":"Jimenez, C.E.: Learning physical commonsense knowledge (2020)"},{"key":"17_CR33","doi-asserted-by":"publisher","first-page":"308","DOI":"10.3758\/BF03202508","volume":"14","author":"M Kaiser","year":"1986","unstructured":"Kaiser, M., Jonides, J., Alexander, J.: Intuitive reasoning about abstract and familiar physics problems. Mem. Cogn. 14, 308\u201312 (1986). https:\/\/doi.org\/10.3758\/BF03202508","journal-title":"Mem. Cogn."},{"key":"17_CR34","doi-asserted-by":"publisher","unstructured":"Kim, I.K., Spelke, E.S.: Perception and understanding of effects of gravity and inertia on object motion. Dev. Sci. 2(3), 339\u2013362 (1999). https:\/\/doi.org\/10.1111\/1467-7687.00080. https:\/\/onlinelibrary.wiley.com\/doi\/abs\/10.1111\/1467-7687.00080","DOI":"10.1111\/1467-7687.00080"},{"issue":"1","key":"17_CR35","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.: TVQA: localized, compositional video question answering. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1369\u20131379 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Li, Y.L., et al.: Hake: a knowledge engine foundation for human activity understanding (2022)","DOI":"10.1109\/TPAMI.2022.3232797"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Maharaj, T., Ballas, N., Rohrbach, A., Courville, A., Pal, C.: A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6884\u20136893 (2017)","DOI":"10.1109\/CVPR.2017.778"},{"issue":"4","key":"17_CR39","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1038\/scientificamerican0483-122","volume":"248","author":"M McCloskey","year":"1983","unstructured":"McCloskey, M.: Intuitive physics. Sci. Am. 248(4), 122\u2013131 (1983)","journal-title":"Sci. Am."},{"issue":"8","key":"17_CR40","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1145\/345124.345145","volume":"43","author":"M Minsky","year":"2000","unstructured":"Minsky, M.: Commonsense-based interfaces. Commun. ACM 43(8), 66\u201373 (2000)","journal-title":"Commun. ACM"},{"issue":"4","key":"17_CR41","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/S0163-6383(98)90028-5","volume":"21","author":"BA Morrongiello","year":"1998","unstructured":"Morrongiello, B.A., Fenwick, K.D., Chance, G.: Crossmodal learning in newborn infants: inferences about properties of auditory-visual events. Infant Behav. Dev. 21(4), 543\u2013553 (1998)","journal-title":"Infant Behav. Dev."},{"key":"17_CR42","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...\u2019\u2019 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":"17_CR43","doi-asserted-by":"crossref","unstructured":"Nair, L., Balloch, J., Chernova, S.: Tool macgyvering: tool construction using geometric reasoning. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 5837\u20135843. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793257"},{"issue":"2","key":"17_CR44","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1007\/s11042-020-08836-3","volume":"80","author":"YR Pandeya","year":"2020","unstructured":"Pandeya, Y.R., Lee, J.: Deep learning-based late fusion of multimodal information for emotion classification of music video. Multimedia Tools Appl. 80(2), 2887\u20132905 (2020). https:\/\/doi.org\/10.1007\/s11042-020-08836-3","journal-title":"Multimedia Tools Appl."},{"key":"17_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1007\/978-3-030-58558-7_30","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JS Park","year":"2020","unstructured":"Park, J.S., Bhagavatula, C., Mottaghi, R., Farhadi, A., Choi, Y.: VisualCOMET: reasoning about the dynamic context of a still image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 508\u2013524. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_30"},{"key":"17_CR46","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"17_CR47","unstructured":"Ridnik, T., Ben-Baruch, E., Noy, A., Zelnik-Manor, L.: ImageNet-21K pretraining for the masses (2021)"},{"key":"17_CR48","unstructured":"Smith, K.A., Battaglia, P.W., Vul, E.: Consistent physics underlying ballistic motion prediction. Cogn. Sci. 35 (2013)"},{"key":"17_CR49","unstructured":"Sou\u010dek, T., Loko\u010d, J.: TransNet V2: an effective deep network architecture for fast shot transition detection. arXiv preprint arXiv:2008.04838 (2020)"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Storks, S., Gao, Q., Zhang, Y., Chai, J.Y.: Tiered reasoning for intuitive physics: toward verifiable commonsense language understanding. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.422"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Suhr, A., Lewis, M., Yeh, J., Artzi, Y.: A corpus of natural language for visual reasoning. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 217\u2013223 (2017)","DOI":"10.18653\/v1\/P17-2034"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6418\u20136428 (2019)","DOI":"10.18653\/v1\/P19-1644"},{"key":"17_CR53","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":"17_CR54","doi-asserted-by":"crossref","unstructured":"Toussaint, M.A., Allen, K.R., Smith, K.A., Tenenbaum, J.B.: Differentiable physics and stable modes for tool-use and manipulation planning (2018)","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Tuli, S., Bansal, R., Paul, R., et al.: Tango: commonsense generalization in predicting tool interactions for mobile manipulators. arXiv preprint arXiv:2105.04556 (2021)","DOI":"10.24963\/ijcai.2021\/577"},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Wang, L., Tong, Z., Ji, B., Wu, G.: TDN: temporal difference networks for efficient action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1895\u20131904, June 2021","DOI":"10.1109\/CVPR46437.2021.00193"},{"key":"17_CR57","doi-asserted-by":"crossref","unstructured":"Wilcox, T., Woods, R., Tuggy, L., Napoli, R.: Shake, rattle, and... one or two objects? Young infants\u2019 use of auditory information to individuate objects. Infancy 9(1), 97\u2013123 (2006)","DOI":"10.1207\/s15327078in0901_5"},{"key":"17_CR58","unstructured":"Wu, J., Lu, E., Kohli, P., Freeman, B., Tenenbaum, J.: Learning to see physics via visual de-animation. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems. Curran Associates Inc. (2017)"},{"key":"17_CR59","unstructured":"Wu, J., Yildirim, I., Lim, J.J., Freeman, B., Tenenbaum, J.: Galileo: perceiving physical object properties by integrating a physics engine with deep learning. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28. Curran Associates, Inc. (2015). https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/d09bf41544a3365a46c9077ebb5e35c3-Paper.pdf"},{"key":"17_CR60","unstructured":"Yang, J., Zhu, Y., Wang, Y., Yi, R., Zadeh, A., Morency, L.P.: What gives the answer away? Question answering bias analysis on video QA datasets (2020)"},{"key":"17_CR61","doi-asserted-by":"crossref","unstructured":"Yatskar, M., Ordonez, V., Zettlemoyer, L., Farhadi, A.: Commonly uncommon: semantic sparsity in situation recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7196\u20137205 (2017)","DOI":"10.1109\/CVPR.2017.671"},{"key":"17_CR62","doi-asserted-by":"publisher","unstructured":"Zadeh, A., Chan, M., Liang, P.P., Tong, E., Morency, L.P.: Social-IQ: a question answering benchmark for artificial social intelligence. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8799\u20138809 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00901","DOI":"10.1109\/CVPR.2019.00901"},{"key":"17_CR63","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00688"},{"key":"17_CR64","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: Merlot reserve: multimodal neural script knowledge through vision and language and sound. arxiv (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"17_CR65","unstructured":"Zhang, Z., Li, Q., Huang, Z., Wu, J., Tenenbaum, J., Freeman, B.: Shape and material from sound. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/f4552671f8909587cf485ea990207f3b-Paper.pdf"},{"key":"17_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Generative modeling of audible shapes for object perception. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.141"},{"key":"17_CR67","doi-asserted-by":"publisher","unstructured":"Zhao, Z., Papalexakis, E., Ma, X.: Learning physical common sense as knowledge graph completion via BERT data augmentation and constrained tucker factorization. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3293\u20133298. Association for Computational Linguistics, November 2020. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.266. https:\/\/aclanthology.org\/2020.emnlp-main.266","DOI":"10.18653\/v1\/2020.emnlp-main.266"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19836-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T11:32:43Z","timestamp":1678361563000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19836-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198359","9783031198366"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19836-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}