{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:28:12Z","timestamp":1742981292004,"version":"3.40.3"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726422"},{"type":"electronic","value":"9783031726439"}],"license":[{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T00:00:00Z","timestamp":1732233600000},"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\/978-3-031-72643-9_11","type":"book-chapter","created":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T20:48:25Z","timestamp":1732222105000},"page":"176-194","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GRACE: Graph-Based Contextual Debiasing for\u00a0Fair Visual Question Answering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1205-9475","authenticated-orcid":false,"given":"Yifeng","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6439-5476","authenticated-orcid":false,"given":"Ming","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3054-8934","authenticated-orcid":false,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Agrawal, A., Batra, D., Parikh, D., Kembhavi, A.: Don\u2019t just assume; look and answer: overcoming priors for visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4971\u20134980 (2018)","key":"11_CR1","DOI":"10.1109\/CVPR.2018.00522"},{"doi-asserted-by":"crossref","unstructured":"Alvi, M., Zisserman, A., Nell\u00e5ker, C.: Turning a blind eye: explicit removal of biases and variation from deep neural network embeddings. In: Proceedings of the European Conference on Computer Vision Workshops (2018)","key":"11_CR2","DOI":"10.1007\/978-3-030-11009-3_34"},{"doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","key":"11_CR3","DOI":"10.1109\/CVPR.2018.00636"},{"doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 39\u201348 (2016)","key":"11_CR4","DOI":"10.1109\/CVPR.2016.12"},{"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)","key":"11_CR5","DOI":"10.1109\/ICCV.2015.279"},{"key":"11_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"6334","key":"11_CR7","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1126\/science.aal4230","volume":"356","author":"A Caliskan","year":"2017","unstructured":"Caliskan, A., Bryson, J.J., Narayanan, A.: Semantics derived automatically from language corpora contain human-like biases. Science 356(6334), 183\u2013186 (2017)","journal-title":"Science"},{"unstructured":"Caton, S., Haas, C.: Fairness in machine learning: a survey. ACM Comput. Surv. (2020)","key":"11_CR8"},{"doi-asserted-by":"crossref","unstructured":"Chen, L., Yan, X., Xiao, J., Zhang, H., Pu, S., Zhuang, Y.: Counterfactual samples synthesizing for robust visual question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","key":"11_CR9","DOI":"10.1109\/CVPR42600.2020.01081"},{"doi-asserted-by":"crossref","unstructured":"Chen, S., Jin, Q., Wang, P., Wu, Q.: Say as you wish: fine-grained control of image caption generation with abstract scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9962\u20139971 (2020)","key":"11_CR10","DOI":"10.1109\/CVPR42600.2020.00998"},{"doi-asserted-by":"crossref","unstructured":"Chen, W., Gan, Z., Li, L., Cheng, Y., Wang, W., Liu, J.: Meta module network for compositional visual reasoning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 655\u2013664 (2021)","key":"11_CR11","DOI":"10.1109\/WACV48630.2021.00070"},{"doi-asserted-by":"crossref","unstructured":"Clark, C., Yatskar, M., Zettlemoyer, L.: Don\u2019t take the easy way out: ensemble based methods for avoiding known dataset biases. arXiv preprint arXiv:1909.03683 (2019)","key":"11_CR12","DOI":"10.18653\/v1\/D19-1418"},{"doi-asserted-by":"crossref","unstructured":"Dong, Y., Ma, J., Wang, S., Chen, C., Li, J.: Fairness in graph mining: a survey. IEEE Trans. Knowl. Data Eng. (2023)","key":"11_CR13","DOI":"10.1109\/TKDE.2023.3265598"},{"unstructured":"Elkan, C.: The foundations of cost-sensitive learning. In: International Joint Conference on Artificial Intelligence, vol.\u00a017, pp. 973\u2013978. Lawrence Erlbaum Associates Ltd. (2001)","key":"11_CR14"},{"doi-asserted-by":"crossref","unstructured":"Fu, X., Zhang, J., Meng, Z., King, I.: MAGNN: metapath aggregated graph neural network for heterogeneous graph embedding. In: Proceedings of The Web Conference 2020, pp. 2331\u20132341 (2020)","key":"11_CR15","DOI":"10.1145\/3366423.3380297"},{"doi-asserted-by":"crossref","unstructured":"Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T., Rohrbach, M.: Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847 (2016)","key":"11_CR16","DOI":"10.18653\/v1\/D16-1044"},{"doi-asserted-by":"crossref","unstructured":"Gard\u00e8res, F., Ziaeefard, M., Abeloos, B., Lecue, F.: ConceptBERT: concept-aware representation for visual question answering. In: Proceedings of the Empirical Methods in Natural Language Processing, pp. 489\u2013498 (2020)","key":"11_CR17","DOI":"10.18653\/v1\/2020.findings-emnlp.44"},{"issue":"12","key":"11_CR18","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1145\/3458723","volume":"64","author":"T Gebru","year":"2021","unstructured":"Gebru, T., et al.: Datasheets for datasets. Commun. ACM 64(12), 86\u201392 (2021)","journal-title":"Commun. ACM"},{"issue":"2","key":"11_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1307\/mmj\/1029003026","volume":"31","author":"CR Givens","year":"1984","unstructured":"Givens, C.R., Shortt, R.M.: A class of Wasserstein metrics for probability distributions. Mich. Math. J. 31(2), 231\u2013240 (1984)","journal-title":"Mich. Math. J."},{"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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","key":"11_CR20","DOI":"10.1109\/CVPR.2017.670"},{"doi-asserted-by":"crossref","unstructured":"Gu, J., Zhao, H., Lin, Z., Li, S., Cai, J., Ling, M.: Scene graph generation with external knowledge and image reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1969\u20131978 (2019)","key":"11_CR21","DOI":"10.1109\/CVPR.2019.00207"},{"doi-asserted-by":"crossref","unstructured":"Gui, L., Wang, B., Huang, Q., Hauptmann, A., Bisk, Y., Gao, J.: Kat: A knowledge augmented transformer for vision-and-language. arXiv preprint arXiv:2112.08614 (2021)","key":"11_CR22","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"unstructured":"Gupta, N., Lin, K., Roth, D., Singh, S., Gardner, M.: Neural module networks for reasoning over text. arXiv preprint arXiv:1912.04971 (2019)","key":"11_CR23"},{"issue":"8","key":"11_CR24","doi-asserted-by":"publisher","first-page":"9789","DOI":"10.1109\/TPAMI.2023.3240337","volume":"45","author":"X Han","year":"2023","unstructured":"Han, X., Wang, S., Su, C., Huang, Q., Tian, Q.: General greedy de-bias learning. IEEE Trans. Pattern Anal. Mach. Intell. 45(8), 9789\u20139805 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Burns, K., Saenko, K., Darrell, T., Rohrbach, A.: Women also Snowboard: overcoming bias in captioning models. In: Proceedings of the European Conference on Computer Vision, pp. 771\u2013787 (2018)","key":"11_CR25","DOI":"10.1007\/978-3-030-01219-9_47"},{"doi-asserted-by":"publisher","unstructured":"Hessel, J., et al.: The abduction of sherlock Holmes: a dataset for visual abductive reasoning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds) European Conference on Computer Vision, pp. 558\u2013575. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_32","key":"11_CR26","DOI":"10.1007\/978-3-031-20059-5_32"},{"doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. IEEE Trans., 53\u201369 (2018)","key":"11_CR27","DOI":"10.1007\/978-3-030-01234-2_4"},{"unstructured":"Hu, X., et al.: Discovering biases in image datasets with the crowd. In: Proceedings of HCOMP (2019)","key":"11_CR28"},{"doi-asserted-by":"crossref","unstructured":"Hu, Y., Hua, H., Yang, Z., Shi, W., Smith, N.A., Luo, J.: PromptCap: prompt-guided task-aware image captioning. arXiv preprint arXiv:2211.09699 (2022)","key":"11_CR29","DOI":"10.1109\/ICCV51070.2023.00277"},{"unstructured":"Hudson, D., Manning, C.D.: Learning by abstraction: the neural state machine. In: Advances in Neural Information Processing Systems, vol. 32 (2019)","key":"11_CR30"},{"unstructured":"Hudson, D.A., Manning, C.D.: Compositional attention networks for machine reasoning. arXiv preprint arXiv:1803.03067 (2018)","key":"11_CR31"},{"doi-asserted-by":"crossref","unstructured":"Hudson, D.A., Manning, C.D.: GQA: a new dataset for real-world visual reasoning and compositional question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6700\u20136709 (2019)","key":"11_CR32","DOI":"10.1109\/CVPR.2019.00686"},{"doi-asserted-by":"crossref","unstructured":"Jeh, G., Widom, J.: SimRank: a measure of structural-context similarity. In: Proceedings of the eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 538\u2013543 (2002)","key":"11_CR33","DOI":"10.1145\/775047.775126"},{"doi-asserted-by":"crossref","unstructured":"Kervadec, C., Antipov, G., Baccouche, M., Wolf, C.: Roses are red, violets are blue... but should VQA expect them to? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2776\u20132785 (2021)","key":"11_CR34","DOI":"10.1109\/CVPR46437.2021.00280"},{"unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017)","key":"11_CR35"},{"unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)","key":"11_CR36"},{"key":"11_CR37","first-page":"22199","volume":"35","author":"T Kojima","year":"2022","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. Adv. Neural. Inf. Process. Syst. 35, 22199\u201322213 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"unstructured":"Lin, Y., Xie, Y., Chen, D., Xu, Y., Zhu, C., Yuan, L.: REVIVE: regional visual representation matters in knowledge-based visual question answering. arXiv preprint arXiv:2206.01201 (2022)","key":"11_CR38"},{"unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning (2023)","key":"11_CR39"},{"unstructured":"Locatello, F., Abbati, G., Rainforth, T., Bauer, S., Sch\u00f6lkopf, B., Bachem, O.: On the fairness of disentangled representations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)","key":"11_CR40"},{"doi-asserted-by":"crossref","unstructured":"Marino, K., Rastegari, M., Farhadi, A., Mottaghi, R.: OK-VQA: a visual question answering benchmark requiring external knowledge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3195\u20133204 (2019)","key":"11_CR41","DOI":"10.1109\/CVPR.2019.00331"},{"unstructured":"Merity, S., Xiong, C., Bradbury, J., Socher, R.: Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843 (2016)","key":"11_CR42"},{"key":"11_CR43","doi-asserted-by":"publisher","first-page":"215091","DOI":"10.1109\/ACCESS.2020.3041503","volume":"8","author":"S Park","year":"2020","unstructured":"Park, S., Hwang, S., Hong, J., Byun, H.: Fair-VQA: fairness-aware visual question answering through sensitive attribute prediction. IEEE Access 8, 215091\u2013215099 (2020)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., De\u00a0Vries, H., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","key":"11_CR44","DOI":"10.1609\/aaai.v32i1.11671"},{"unstructured":"Pu, Y., Gan, Z., Henao, R., Yuan, X., Li, C., Stevens, A., Carin, L.: Variational autoencoder for deep learning of images, labels and captions. In: Advances in Neural Information Processing Systems, vol. 29 (2016)","key":"11_CR45"},{"unstructured":"Ryu, H.J., Adam, H., Mitchell, M.: InclusiveFaceNet: improving face attribute detection with race and gender diversity. arXiv preprint arXiv:1712.00193 (2017)","key":"11_CR46"},{"unstructured":"Santoro, A., et al.: A simple neural network module for relational reasoning. In: Proceedings of the Conference and Workshop on Neural Information Processing Systems, pp. 4967\u20134976 (2017)","key":"11_CR47"},{"doi-asserted-by":"crossref","unstructured":"Shao, Z., Yu, Z., Wang, M., Yu, J.: Prompting large language models with answer heuristics for knowledge-based visual question answering. In: Computer Vision and Pattern Recognition (CVPR), pp. 14974\u201314983 (2023)","key":"11_CR48","DOI":"10.1109\/CVPR52729.2023.01438"},{"doi-asserted-by":"crossref","unstructured":"Shi, J., Zhang, H., Li, J.: Explainable and explicit visual reasoning over scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8376\u20138384 (2019)","key":"11_CR49","DOI":"10.1109\/CVPR.2019.00857"},{"issue":"4148","key":"11_CR50","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1038\/163688a0","volume":"163","author":"EH Simpson","year":"1949","unstructured":"Simpson, E.H.: Measurement of diversity. Nature 163(4148), 688\u2013688 (1949)","journal-title":"Nature"},{"unstructured":"Su, W., et al.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)","key":"11_CR51"},{"doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. arXiv preprint arXiv:1908.07490 (2019)","key":"11_CR52","DOI":"10.18653\/v1\/D19-1514"},{"unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models (2023)","key":"11_CR53"},{"doi-asserted-by":"crossref","unstructured":"Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4068\u20134076 (2015)","key":"11_CR54","DOI":"10.1109\/ICCV.2015.463"},{"unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)","key":"11_CR55"},{"doi-asserted-by":"crossref","unstructured":"Verma, S., Rubin, J.: Fairness definitions explained. In: Proceedings of the International Workshop on Software Fairness, pp.\u00a01\u20137 (2018)","key":"11_CR56","DOI":"10.1145\/3194770.3194776"},{"issue":"7","key":"11_CR57","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1007\/s11263-022-01625-5","volume":"130","author":"A Wang","year":"2022","unstructured":"Wang, A., et al.: REVISE: a tool for measuring and mitigating bias in visual datasets. Int. J. Comput. Vis. 130(7), 1790\u20131810 (2022). https:\/\/doi.org\/10.1007\/s11263-022-01625-5","journal-title":"Int. J. Comput. Vis."},{"issue":"10","key":"11_CR58","doi-asserted-by":"publisher","first-page":"2413","DOI":"10.1109\/TPAMI.2017.2754246","volume":"40","author":"P Wang","year":"2017","unstructured":"Wang, P., Wu, Q., Shen, C., Dick, A., Van Den Hengel, A.: FVQA: fact-based visual question answering. IEEE Trans. Pattern Anal. Mach. Intell. 40(10), 2413\u20132427 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"doi-asserted-by":"crossref","unstructured":"Wu, J., Lu, J., Sabharwal, A., Mottaghi, R.: Multi-modal answer validation for knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2712\u20132721 (2022)","key":"11_CR59","DOI":"10.1609\/aaai.v36i3.20174"},{"unstructured":"Xiong, C., Merity, S., Socher, R.: Dynamic memory networks for visual and textual question answering. In: International Conference on Machine Learning, pp. 2397\u20132406. PMLR (2016)","key":"11_CR60"},{"key":"11_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-319-46478-7_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"H Xu","year":"2016","unstructured":"Xu, H., Saenko, K.: Ask, Attend and Answer: exploring question-guided spatial attention for visual question answering. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 451\u2013466. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_28"},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3081\u20133089 (2022)","key":"11_CR62","DOI":"10.1609\/aaai.v36i3.20215"},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., He, X., Gao, J., Deng, L., Smola, A.: Stacked attention networks for image question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21\u201329 (2016)","key":"11_CR63","DOI":"10.1109\/CVPR.2016.10"},{"doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR, pp. 6713\u20136724 (2019)","key":"11_CR64","DOI":"10.1109\/CVPR.2019.00688"},{"doi-asserted-by":"crossref","unstructured":"Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI\/ACM Conference on AI, Ethics, and Society, pp. 335\u2013340 (2018)","key":"11_CR65","DOI":"10.1145\/3278721.3278779"},{"doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","key":"11_CR66","DOI":"10.1109\/CVPR46437.2021.00553"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jiang, M., Zhao, Q.: Explicit knowledge incorporation for visual reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1356\u20131365 (2021)","key":"11_CR67","DOI":"10.1109\/CVPR46437.2021.00141"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Jiang, M., Zhao, Q.: Query and attention augmentation for knowledge-based explainable reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15576\u201315585 (2022)","key":"11_CR68","DOI":"10.1109\/CVPR52688.2022.01513"},{"doi-asserted-by":"crossref","unstructured":"Zhu, B., Niu, Y., Lee, S., Hur, M., Zhang, H.: Debiased fine-tuning for vision-language models by prompt regularization. arXiv preprint arXiv:2301.12429 (2023)","key":"11_CR69","DOI":"10.1609\/aaai.v37i3.25496"}],"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\/978-3-031-72643-9_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T21:26:17Z","timestamp":1732224377000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72643-9_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,22]]},"ISBN":["9783031726422","9783031726439"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72643-9_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,22]]},"assertion":[{"value":"22 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"}}]}}