{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:46:05Z","timestamp":1778082365652,"version":"3.51.4"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727535","type":"print"},{"value":"9783031727542","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-72754-2_18","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"313-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["KDProR: A Knowledge-Decoupling Probabilistic Framework for\u00a0Video-Text Retrieval"],"prefix":"10.1007","author":[{"given":"Xianwei","family":"Zhuang","sequence":"first","affiliation":[]},{"given":"Hongxiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xuxin","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Zhihong","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Yuxin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"18_CR1","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_CR2","doi-asserted-by":"crossref","unstructured":"Bogolin, S.V., Croitoru, I., Jin, H., Liu, Y., Albanie, S.: Cross modal retrieval with querybank normalisation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5194\u20135205 (2022)","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"18_CR3","unstructured":"Cheng, X., Lin, H., Wu, X., Yang, F., Shen, D.: Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss. arXiv preprint arXiv:2109.04290 (2021)"},{"key":"18_CR4","unstructured":"Cuturi, M.: Sinkhorn distances: lightspeed computation of optimal transport. In: Advances in Neural Information Processing Systems, vol. 26 (2013)"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper (1977)","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Deng, C., Chen, Q., Qin, P., Chen, D., Wu, Q.: Prompt switch: efficient clip adaptation for text-video retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15648\u201315658 (2023)","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"18_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics (2019)"},{"key":"18_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv abs\/2010.11929 (2020)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Elangovan, A., He, J., Verspoor, K.M.: Memorization vs. generalization: quantifying data leakage in NLP performance evaluation. In: Conference of the European Chapter of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.eacl-main.113"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Fang, B., et al.: UATVR: uncertainty-adaptive text-video retrieval. arXiv preprint arXiv:2301.06309 (2023)","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Feldman, V.: Does learning require memorization? A short tale about a long tail. In: Proceedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing (2019)","DOI":"10.1145\/3357713.3384290"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gorti, S.K., et al.: X-pool: cross-modal language-video attention for text-video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5006\u20135015 (2022)","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Heilbron, F.C., Escorcia, V., Ghanem, B., Niebles, J.C.: Activitynet: a large-scale video benchmark for human activity understanding. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Hendricks, L.A., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.C.: Localizing moments in video with natural language. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5804\u20135813 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Ibrahimi, S., Sun, X., Wang, P., Garg, A., Sanan, A., Omar, M.: Audio-enhanced text-to-video retrieval using text-conditioned feature alignment. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 12020\u201312030 (2023)","DOI":"10.1109\/ICCV51070.2023.01107"},{"key":"18_CR19","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/BF02418571","volume":"30","author":"JLWV Jensen","year":"1906","unstructured":"Jensen, J.L.W.V.: Sur les fonctions convexes et les in\u00e9galit\u00e9s entre les valeurs moyennes. Acta Math. 30, 175\u2013193 (1906)","journal-title":"Acta Math."},{"key":"18_CR20","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. arXiv abs\/2102.05918 (2021)"},{"key":"18_CR21","first-page":"30291","volume":"35","author":"P Jin","year":"2022","unstructured":"Jin, P., et al.: Expectation-maximization contrastive learning for compact video-and-language representations. Adv. Neural. Inf. Process. Syst. 35, 30291\u201330306 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Jin, P., et al.: Diffusionret: generative text-video retrieval with diffusion model. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2470\u20132481 (2023)","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"18_CR23","unstructured":"Khandelwal, U., Levy, O., Jurafsky, D., Zettlemoyer, L., Lewis, M.: Generalization through memorization: Nearest neighbor language models. arXiv preprint arXiv:1911.00172 (2019)"},{"key":"18_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., Cao, M., Cheng, X., Li, Y., Zhu, Z., Zou, Y.: G2L: semantically aligned and uniform video grounding via geodesic and game theory. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11998\u201312008 (2023). https:\/\/api.semanticscholar.org\/CorpusID:260164585","DOI":"10.1109\/ICCV51070.2023.01105"},{"key":"18_CR26","unstructured":"Li, H., Cao, M., Cheng, X., Zhu, Z., Li, Y., Zou, Y.: Exploiting auxiliary caption for video grounding. In: AAAI Conference on Artificial Intelligence (2023). https:\/\/api.semanticscholar.org\/CorpusID:257772084"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Unmasked teacher: towards training-efficient video foundation models. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 19891\u201319903 (2023)","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Liu, R., Huang, J., Li, G., Feng, J., Wu, X., Li, T.H.: Revisiting temporal modeling for clip-based image-to-video knowledge transferring. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6555\u20136564 (2023)","DOI":"10.1109\/CVPR52729.2023.00634"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: HIT: hierarchical transformer with momentum contrast for video-text retrieval. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11895\u201311905 (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: HIT: hierarchical transformer with momentum contrast for video-text retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11915\u201311925 (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"18_CR31","unstructured":"Liu, Y., Albanie, S., Nagrani, A., Zisserman, A.: Use what you have: video retrieval using representations from collaborative experts. arXiv preprint arXiv:1907.13487 (2019)"},{"key":"18_CR32","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv abs\/1907.11692 (2019)"},{"key":"18_CR33","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-031-19781-9_19","volume-title":"European Conference on Computer Vision","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Xiong, P., Xu, L., Cao, S., Jin, Q.: TS2-Net: token shift and selection transformer for text-video retrieval. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13674, pp. 319\u2013335. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19781-9_19"},{"key":"18_CR34","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv: Learning (2016)"},{"key":"18_CR35","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.neucom.2022.07.028","volume":"508","author":"H Luo","year":"2022","unstructured":"Luo, H., et al.: CLIP4Clip: an empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing 508, 293\u2013304 (2022)","journal-title":"Neurocomputing"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Ma, Y., Xu, G., Sun, X., Yan, M., Zhang, J., Ji, R.: X-clip: end-to-end multi-grained contrastive learning for video-text retrieval. In: Proceedings of the 30th ACM International Conference on Multimedia (2022)","DOI":"10.1145\/3503161.3547910"},{"key":"18_CR37","unstructured":"Meng, Y., et al.: GNN-LM: language modeling based on global contexts via GNN. arXiv abs\/2110.08743 (2021)"},{"key":"18_CR38","unstructured":"Mikolov, T., Chen, K., Corrado, G.S., Dean, J.: Efficient estimation of word representations in vector space. In: International Conference on Learning Representations (2013)"},{"key":"18_CR39","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. arXiv abs\/2203.02155 (2022)"},{"key":"18_CR40","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR41","unstructured":"Papernot, N., McDaniel, P.: Deep k-nearest neighbors: towards confident, interpretable and robust deep learning. arXiv preprint arXiv:1803.04765 (2018)"},{"key":"18_CR42","unstructured":"Patrick, M., et al.: Support-set bottlenecks for video-text representation learning. arXiv preprint arXiv:2010.02824 (2020)"},{"key":"18_CR43","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"18_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3202\u20133212 (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Su, B., Hua, G.: Order-preserving Wasserstein distance for sequence matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131057 (2017)","DOI":"10.1109\/CVPR.2017.310"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"T\u00e4nzer, M., Ruder, S., Rei, M.: Memorisation versus generalisation in pre-trained language models. In: Annual Meeting of the Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2022.acl-long.521"},{"key":"18_CR48","unstructured":"Wang, Q., Zhang, Y., Zheng, Y., Pan, P., Hua, X.: Disentangled representation learning for text-video retrieval. arXiv abs\/2203.07111 (2022)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Z., Sung, Y.L., Cheng, F., Bertasius, G., Bansal, M.: Unified coarse-to-fine alignment for video-text retrieval. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2804\u20132815 (2023)","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"18_CR50","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_CR51","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Unified visual-semantic embeddings: bridging vision and language with structured meaning representations. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6602\u20136611 (2019)","DOI":"10.1109\/CVPR.2019.00677"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Wu, W., Luo, H., Fang, B., Wang, J., Ouyang, W.: Cap4video: what can auxiliary captions do for text-video retrieval? In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10704\u201310713 (2022)","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"18_CR53","unstructured":"Wu, X., et al.: Uncertainty-aware sign language video retrieval with probability distribution modeling. arXiv abs\/2405.19689 (2024). https:\/\/api.semanticscholar.org\/CorpusID:270123137"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Xie, Y., Zhu, Z., Zhuang, X., Liang, L., Wang, Z., Zou, Y.: GPA: global and prototype alignment for audio-text retrieval. In: Interspeech (2024)","DOI":"10.21437\/Interspeech.2024-1642"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, Z., Zhang, Y., Song, Y., Wan, X., Li, G.: Bridging vision and language encoders: Parameter-efficient tuning for referring image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 17503\u201317512 (2023)","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"18_CR57","unstructured":"Xu, Z., et al.: Enhancing fine-grained multi-modal alignment via adapters: a parameter-efficient training framework for referring image segmentation. In: 2nd Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization (WANT@ ICML 2024) (2024)"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Xue, H., et al.: Advancing high-resolution video-language representation with large-scale video transcriptions. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5026\u20135035 (2021)","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"18_CR59","unstructured":"Xue, H., et al.: Clip-VIP: adapting pre-trained image-text model to video-language alignment. In: International Conference on Learning Representations (2023)"},{"key":"18_CR60","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res. 2022 (2022)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Yu, Y., Kim, J., Kim, G.: A joint sequence fusion model for video question answering and retrieval. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"18_CR62","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arXiv abs\/2111.11432 (2021)"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Graco: granularity-controllable interactive segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3501\u20133510 (2024)","DOI":"10.1109\/CVPR52733.2024.00336"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Zheng, X., Jiang, J.: An empirical study of memorization in NLP. In: Annual Meeting of the Association for Computational Linguistics (2022)","DOI":"10.18653\/v1\/2022.acl-long.434"}],"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\/978-3-031-72754-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:10:53Z","timestamp":1730301053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72754-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031727535","9783031727542"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72754-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 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"}}]}}