{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T02:11:26Z","timestamp":1784513486680,"version":"3.55.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729195","type":"print"},{"value":"9783031729201","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-72920-1_18","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T08:02:57Z","timestamp":1727683377000},"page":"315-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Video Question Answering with\u00a0Procedural Programs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8307-8395","authenticated-orcid":false,"given":"Rohan","family":"Choudhury","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8367-3988","authenticated-orcid":false,"given":"Koichiro","family":"Niinuma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9389-4060","authenticated-orcid":false,"given":"Kris M.","family":"Kitani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2830-700X","authenticated-orcid":false,"given":"L\u00e1szl\u00f3 A.","family":"Jeni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"18_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"18_CR2","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Andreas, J., Rohrbach, M., Darrell, T., Klein, D.: Neural module networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.12"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"18_CR5","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."},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"18_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhang, X., Zhang, S., Wang, W., Zhang, C., Huang, H.: Heterogeneous memory enhanced multimodal attention model for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1999\u20132007 (2019)","DOI":"10.1109\/CVPR.2019.00210"},{"key":"18_CR9","unstructured":"Fu, T.J., et al.: Violet: end-to-end video-language transformers with masked visual-token modeling. arXiv preprint arXiv:2111.12681 (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., Ge, R., Chen, K., Nevatia, R.: Motion-appearance co-memory networks for video question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6576\u20136585 (2018)","DOI":"10.1109\/CVPR.2018.00688"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: Imagebind: one embedding space to bind them all. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"18_CR12","unstructured":"Grauman, K., et\u00a0al.: Ego4d: around the world in 3,000 hours of egocentric video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18995\u201319012 (2022)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, T., Kembhavi, A.: Visual programming: compositional visual reasoning without training. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Darrell, T., Saenko, K.: Explainable neural computation via stack neural module networks. In: Proceedings of the European conference on computer vision (ECCV), pp. 53\u201369 (2018)","DOI":"10.1007\/978-3-030-01234-2_4"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Hu, R., Andreas, J., Rohrbach, M., Darrell, T., Saenko, K.: Learning to reason: end-to-end module networks for visual question answering. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.93"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Huang, D., Chen, P., Zeng, R., Du, Q., Tan, M., Gan, C.: Location-aware graph convolutional networks for video question answering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 11021\u201311028 (2020)","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: Tgif-qa: toward spatio-temporal reasoning in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2758\u20132766 (2017)","DOI":"10.1109\/CVPR.2017.149"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Joulin, A., Grave, E., Bojanowski, P., Mikolov, T.: Bag of tricks for efficient text classification. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: vol. 2, Short Papers, pp. 427\u2013431. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/E17-2068"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Kim, J., Ma, M., Pham, T., Kim, K., Yoo, C.D.: Modality shifting attention network for multi-modal video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310115 (2020)","DOI":"10.1109\/CVPR42600.2020.01012"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9972\u20139981 (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: Tvqa: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"18_CR22","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR23","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"18_CR24","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":"18_CR25","unstructured":"Li, K., et al.: Videochat: chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: TGIF: a new dataset and benchmark on animated GIF description. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.502"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., Ning, M., Jin, P., Yuan, L.: Video-llava: learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Lin, X., Bertasius, G., Wang, J., Chang, S.F., Parikh, D., Torresani, L.: Vx2text: end-to-end learning of video-based text generation from multimodal inputs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7005\u20137015 (2021)","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR30","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"18_CR32","unstructured":"Maaz, M., Rasheed, H., Khan, S., Khan, F.: Video-chatgpt: towards detailed video understanding via large vision and language models. ArXiv 2306.05424 (2023)"},{"key":"18_CR33","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: Egoschema: a diagnostic benchmark for very long-form video language understanding. arXiv preprint arXiv:2308.09126 (2023)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: Howto100m: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"18_CR35","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"18_CR36","unstructured":"OpenAI, R.: Gpt-4 technical report. arXiv, pp. 2303\u201308774 (2023)"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Sohn, K.: Bridge to answer: structure-aware graph interaction network for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15526\u201315535 (2021)","DOI":"10.1109\/CVPR46437.2021.01527"},{"key":"18_CR38","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR39","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Reddy, R.G., et\u00a0al.: Mumuqa: multimedia multi-hop news question answering via cross-media knowledge extraction and grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 11200\u201311208 (2022)","DOI":"10.1609\/aaai.v36i10.21370"},{"key":"18_CR41","first-page":"3070","volume":"33","author":"R Saqur","year":"2020","unstructured":"Saqur, R., Narasimhan, K.: Multimodal graph networks for compositional generalization in visual question answering. Adv. Neural. Inf. Process. Syst. 33, 3070\u20133081 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR42","unstructured":"Schick, T., et al.: Toolformer: language models can teach themselves to use tools. arXiv preprint arXiv:2302.04761 (2023)"},{"key":"18_CR43","unstructured":"Seo, P.H., Nagrani, A., Schmid, C.: Look before you speak: visually contextualized utterances. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16877\u201316887 (2021)"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: Moviechat: from dense token to sparse memory for long video understanding. arXiv preprint arXiv:2307.16449 (2023)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"18_CR45","doi-asserted-by":"publisher","unstructured":"Subramanian, S., et al.: Modular visual question answering via code generation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (vol. 2: Short Papers), pp. 747\u2013761. Association for Computational Linguistics, Toronto, Canada (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-short.65, https:\/\/aclanthology.org\/2023.acl-short.65","DOI":"10.18653\/v1\/2023.acl-short.65"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Sur\u00eds, D., Menon, S., Vondrick, C.: Vipergpt: visual inference via python execution for reasoning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11888\u201311898 (2023)","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"18_CR47","unstructured":"Team, G., et\u00a0al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"18_CR48","unstructured":"Wang, Y., et\u00a0al.: Internvid: a large-scale video-text dataset for multimodal understanding and generation. arXiv preprint arXiv:2307.06942 (2023)"},{"key":"18_CR49","unstructured":"Wang, Y., et\u00a0al.: Internvideo: general video foundation models via generative and discriminative learning. arXiv preprint arXiv:2212.03191 (2022)"},{"key":"18_CR50","first-page":"8483","volume":"35","author":"Z Wang","year":"2022","unstructured":"Wang, Z., et al.: Language models with image descriptors are strong few-shot video-language learners. Adv. Neural. Inf. Process. Syst. 35, 8483\u20138497 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR51","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural. Inf. Process. Syst. 35, 24824\u201324837 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Xiao, J., Shang, X., Yao, A., Chua, T.S.: Next-qa: next phase of question-answering to explaining temporal actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9777\u20139786 (2021)","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACM Multimedia (2017)","DOI":"10.1145\/3123266.3123427"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Just ask: learning to answer questions from millions of narrated videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"18_CR55","unstructured":"Yang, A., Miech, A., Sivic, J., Laptev, I., Schmid, C.: Zero-shot video question answering via frozen bidirectional language models. In: NeurIPS (2022)"},{"key":"18_CR56","unstructured":"Yang, R., et al.: Gpt4tools: teaching large language model to use tools via self-instruction. arXiv preprint arXiv:2305.18752 (2023)"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: An empirical study of GPT-3 for few-shot knowledge-based VQA. In: AAAI (2022)","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Ye, Q., et al.: Hitea: hierarchical temporal-aware video-language pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15405\u201315416 (2023)","DOI":"10.1109\/ICCV51070.2023.01413"},{"key":"18_CR59","unstructured":"Ye, Q., et\u00a0al.: mplug-owl: modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)"},{"key":"18_CR60","unstructured":"Yu, S., Cho, J., Yadav, P., Bansal, M.: Self-chained image-language model for video localization and question answering. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Activitynet-qa: a dataset for understanding complex web videos via question answering. In: AAAI, pp. 9127\u20139134 (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"18_CR62","doi-asserted-by":"crossref","unstructured":"Zellers, R., et al.: Merlot reserve: neural script knowledge through vision and language and sound. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16375\u201316387 (2022)","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"18_CR63","first-page":"23634","volume":"34","author":"R Zellers","year":"2021","unstructured":"Zellers, R., et al.: Merlot: multimodal neural script knowledge models. Adv. Neural. Inf. Process. Syst. 34, 23634\u201323651 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR64","unstructured":"Zeng, A., et\u00a0al.: Socratic models: Composing zero-shot multimodal reasoning with language. arXiv preprint arXiv:2204.00598 (2022)"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A simple llm framework for long-range video question-answering (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Bytetrack: multi-object tracking by associating every detection box (2022)","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"18_CR68","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"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\/978-3-031-72920-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:54:42Z","timestamp":1732830882000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72920-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031729195","9783031729201"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72920-1_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 October 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"}}]}}