{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:21:21Z","timestamp":1777656081565,"version":"3.51.4"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728891","type":"print"},{"value":"9783031728907","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-3-031-72890-7_11","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:46:24Z","timestamp":1733514384000},"page":"174-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving Vision and\u00a0Language Concepts Understanding with\u00a0Multimodal Counterfactual Samples"],"prefix":"10.1007","author":[{"given":"Chengen","family":"Lai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengli","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sitong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangneng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C.L., Parikh, D.: 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":"11_CR2","doi-asserted-by":"crossref","unstructured":"Basu, A., Addepalli, S., Babu, R.V.: Rmlvqa: a margin loss approach for visual question answering with language biases. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11671\u201311680 (2023)","DOI":"10.1109\/CVPR52729.2023.01123"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Cascante-Bonilla, P., et\u00a0al.: Going beyond nouns with vision & language models using synthetic data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20155\u201320165 (2023)","DOI":"10.1109\/ICCV51070.2023.01844"},{"key":"11_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Revisiting multimodal representation in contrastive learning: from patch and token embeddings to finite discrete tokens. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15095\u201315104 (2023)","DOI":"10.1109\/CVPR52729.2023.01449"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Vilem: visual-language error modeling for image-text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11018\u201311027 (2023)","DOI":"10.1109\/CVPR52729.2023.01060"},{"key":"11_CR7","first-page":"8765","volume":"33","author":"CY Chuang","year":"2020","unstructured":"Chuang, C.Y., Robinson, J., Lin, Y.C., Torralba, A., Jegelka, S.: Debiased contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 8765\u20138775 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 4171\u20134186 (2019)"},{"key":"11_CR9","unstructured":"Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., Brox, T.: Discriminative unsupervised feature learning with convolutional neural networks. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"11_CR10","unstructured":"Doveh, S., et\u00a0al.: Dense and aligned captions (dac) promote compositional reasoning in vl models. In: NeurIPS (2023)"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Doveh, S., et al.: Teaching structured vision & language concepts to vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2657\u20132668 (2023)","DOI":"10.1109\/CVPR52729.2023.00261"},{"issue":"11","key":"11_CR12","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R., et al.: Shortcut learning in deep neural networks. Nat. Mach. Intell. 2(11), 665\u2013673 (2020)","journal-title":"Nat. Mach. Intell."},{"key":"11_CR13","first-page":"6704","volume":"35","author":"S Goel","year":"2022","unstructured":"Goel, S., Bansal, H., Bhatia, S., Rossi, R., Vinay, V., Grover, A.: Cyclip: cyclic contrastive language-image pretraining. Adv. Neural. Inf. Process. Syst. 35, 6704\u20136719 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol.\u00a02, pp. 1735\u20131742. IEEE (2006)","DOI":"10.1109\/CVPR.2006.100"},{"key":"11_CR15","unstructured":"He, R., et al.: Is synthetic data from generative models ready for image recognition? In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"11_CR16","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"11_CR17","first-page":"21798","volume":"33","author":"Y Kalantidis","year":"2020","unstructured":"Kalantidis, Y., Sariyildiz, M.B., Pion, N., Weinzaepfel, P., Larlus, D.: Hard negative mixing for contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 21798\u201321809 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR18","first-page":"18661","volume":"33","author":"P Khosla","year":"2020","unstructured":"Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., Krishnan, D.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR19","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, 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"11_CR20","unstructured":"Le, T., Lal, V., Howard, P.: Coco-counterfactuals: automatically constructed counterfactual examples for image-text pairs. arXiv preprint arXiv:2309.14356 (2023)"},{"key":"11_CR21","first-page":"9287","volume":"35","author":"C Li","year":"2022","unstructured":"Li, C., et al.: Elevater: a benchmark and toolkit for evaluating language-augmented visual models. Adv. Neural. Inf. Process. Syst. 35, 9287\u20139301 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR22","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: ICML (2023)"},{"key":"11_CR23","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"11_CR24","unstructured":"Li, Y.L., et al.: Hake: human activity knowledge engine. arXiv preprint arXiv:1904.06539 (2019)"},{"key":"11_CR25","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"},{"issue":"11","key":"11_CR26","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1145\/219717.219748","volume":"38","author":"GA Miller","year":"1995","unstructured":"Miller, G.A.: Wordnet: a lexical database for english. Commun. ACM 38(11), 39\u201341 (1995)","journal-title":"Commun. ACM"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Moltisanti, D., Keller, F., Bilen, H., Sevilla-Lara, L.: Learning action changes by measuring verb-adverb textual relationships. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 23110\u201323118 (2023)","DOI":"10.1109\/CVPR52729.2023.02213"},{"key":"11_CR28","doi-asserted-by":"crossref","unstructured":"Momeni, L., Caron, M., Nagrani, A., Zisserman, A., Schmid, C.: Verbs in action: improving verb understanding in video-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15579\u201315591 (2023)","DOI":"10.1109\/ICCV51070.2023.01428"},{"key":"11_CR29","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Pham, K., Kafle, K., Lin, Z., Ding, Z., Cohen, S., Tran, Q., Shrivastava, A.: Learning to predict visual attributes in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13018\u201313028 (2021)","DOI":"10.1109\/CVPR46437.2021.01282"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Pratt, S., Yatskar, M., Weihs, L., Farhadi, A., Kembhavi, A.: Grounded situation recognition. In: European Conference on Computer Vision, pp. 314\u2013332 (2020)","DOI":"10.1007\/978-3-030-58548-8_19"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Radenovic, F., et al.: Filtering, distillation, and hard negatives for vision-language pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6967\u20136977 (2023)","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"11_CR33","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"11_CR34","unstructured":"Robinson, J.D., Chuang, C.Y., Sra, S., Jegelka, S.: Contrastive learning with hard negative samples. In: International Conference on Learning Representations (2020)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Roth, K., Kim, J.M., Koepke, A.S., Vinyals, O., Schmid, C., Akata, Z.: Waffling around for performance: Visual classification with random words and broad concepts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15746\u201315757 (2023)","DOI":"10.1109\/ICCV51070.2023.01443"},{"key":"11_CR37","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Shi, C., Yang, S.: Logoprompt: Synthetic text images can be good visual prompts for vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2932\u20132941 (2023)","DOI":"10.1109\/ICCV51070.2023.00274"},{"key":"11_CR39","unstructured":"Shi, H., Mao, J., Xiao, T., Jiang, Y., Sun, J.: Learning visually-grounded semantics from contrastive adversarial samples. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 3715\u20133727 (2018)"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Smith, J.S., et al.: Construct-vl: data-free continual structured vl concepts learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14994\u201315004 (2023)","DOI":"10.1109\/CVPR52729.2023.01440"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"11_CR42","first-page":"6827","volume":"33","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Sun, C., Poole, B., Krishnan, D., Schmid, C., Isola, P.: What makes for good views for contrastive learning? Adv. Neural. Inf. Process. Syst. 33, 6827\u20136839 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR43","unstructured":"Trabucco, B., Doherty, K., Gurinas, M., Salakhutdinov, R.: Effective data augmentation with diffusion models. In: ICLR 2023 Workshop on Mathematical and Empirical Understanding of Foundation Models (2023)"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Wang, W., Yang, Z., Xu, B., Li, J., Sun, Y.: Vilta: enhancing vision-language pre-training through textual augmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3158\u20133169 (2023)","DOI":"10.1109\/ICCV51070.2023.00293"},{"key":"11_CR45","doi-asserted-by":"crossref","unstructured":"Wang, Z., Gao, Z., Guo, K., Yang, Y., Wang, X., Shen, H.T.: Multilateral semantic relations modeling for image text retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2830\u20132839 (2023)","DOI":"10.1109\/CVPR52729.2023.00277"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Wei, J., Zou, K.: Eda: easy data augmentation techniques for boosting performance on text classification tasks. 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), pp. 6382\u20136388 (2019)","DOI":"10.18653\/v1\/D19-1670"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhang, Y., Ji, Z., Bai, J., Zhang, L., Zuo, W.: Elite: encoding visual concepts into textual embeddings for customized text-to-image generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15943\u201315953 (2023)","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Unified visual-semantic embeddings: bridging vision and language with structured meaning representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6609\u20136618 (2019)","DOI":"10.1109\/CVPR.2019.00677"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Y., Wei, Y., Wang, H., Liu, Y., Yang, S., He, X.: Grounded image text matching with mismatched relation reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2976\u20132987 (2023)","DOI":"10.1109\/ICCV51070.2023.00278"},{"key":"11_CR50","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Sun, S., Xiong, X., Zheng, Y., Zhao, D., Zhou, J.: Ra-clip: retrieval augmented contrastive language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19265\u201319274 (2023)","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"11_CR52","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: Alip: adaptive language-image pre-training with synthetic caption. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2922\u20132931 (2023)","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"11_CR53","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, F., Xu, C.: Vqacl: a novel visual question answering continual learning setting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19102\u201319112 (2023)","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"11_CR55","unstructured":"Zhang, X., Zhao, J., LeCun, Y.: Character-level convolutional networks for text classification. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"11_CR56","unstructured":"Zhao, T., et al.: Vl-checklist: evaluating pre-trained vision-language models with objects, attributes and relations. arXiv preprint arXiv:2207.00221 (2022)"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Zhen, L., Hu, P., Wang, X., Peng, D.: Deep supervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10394\u201310403 (2019)","DOI":"10.1109\/CVPR.2019.01064"},{"key":"11_CR58","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et\u00a0al.: Regionclip: region-based language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16793\u201316803 (2022)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Zheng, L., Kang, G., Li, S., Yang, Y.: Random erasing data augmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 13001\u201313008 (2020)","DOI":"10.1609\/aaai.v34i07.7000"}],"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\/978-3-031-72890-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:04:52Z","timestamp":1733515492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72890-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9783031728891","9783031728907"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72890-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 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"}}]}}