{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:12:30Z","timestamp":1743135150908,"version":"3.40.3"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726545"},{"type":"electronic","value":"9783031726552"}],"license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"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\/978-3-031-72655-2_23","type":"book-chapter","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T10:13:43Z","timestamp":1733393623000},"page":"398-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SHINE: Saliency-Aware Hierarchical Negative Ranking for\u00a0Compositional Temporal Grounding"],"prefix":"10.1007","author":[{"given":"Zixu","family":"Cheng","sequence":"first","affiliation":[]},{"given":"Yujiang","family":"Pu","sequence":"additional","affiliation":[]},{"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[]},{"given":"Parisa","family":"Kordjamshidi","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Kong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"23_CR1","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":"23_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"23_CR3","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":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Chen, X., Ma, L., Jie, Z., Chua, T.S.: Temporally grounding natural sentence in video. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 162\u2013171 (2018)","DOI":"10.18653\/v1\/D18-1015"},{"key":"23_CR5","unstructured":"Doveh, Set\u00a0al.: Dense and aligned captions (dac) promote compositional reasoning in vl models. Adv. Neural Inf. Process. Syst. 36 (2023)"},{"key":"23_CR6","unstructured":"Duan, X., Huang, W., Gan, C., Wang, J., Zhu, W., Huang, J.: Weakly supervised dense event captioning in videos. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Gandhi, M., Gul, M.O., Prakash, E., Grunde-McLaughlin, M., Krishna, R., Agrawala, M.: Measuring compositional consistency for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5046\u20135055 (2022)","DOI":"10.1109\/CVPR52688.2022.00499"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: Tall: temporal activity localization via language query. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"23_CR10","unstructured":"Google: Gemini-1.5 flash (2024). https:\/\/deepmind.google\/technologies\/gemini\/flash\/"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Grunde-McLaughlin, M., Krishna, R., Agrawala, M.: Agqa: a benchmark for compositional spatio-temporal reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11287\u201311297 (2021)","DOI":"10.1109\/CVPR46437.2021.01113"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"He, B., Wang, J., Qiu, J., Bui, T., Shrivastava, A., Wang, Z.: Align and attend: multimodal summarization with dual contrastive losses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14867\u201314878 (2023)","DOI":"10.1109\/CVPR52729.2023.01428"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Hou, Z., et al.: Cone: an efficient coarse-to-fine alignment framework for long video temporal grounding. arXiv preprint arXiv:2209.10918 (2022)","DOI":"10.18653\/v1\/2023.acl-long.445"},{"key":"23_CR14","unstructured":"Hsieh, C.Y., Zhang, J., Ma, Z., Kembhavi, A., Krishna, R.: Sugarcrepe: fixing hackable benchmarks for vision-language compositionality. Adv. Neural Inf. Process. Syst. 36 (2023)"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Jang, J., Park, J., Kim, J., Kwon, H., Sohn, K.: Knowing where to focus: event-aware transformer for video grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13846\u201313856 (2023)","DOI":"10.1109\/ICCV51070.2023.01273"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Clevr: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Carlos\u00a0Niebles, J.: Dense-captioning events in videos. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 706\u2013715 (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"23_CR19","first-page":"11846","volume":"34","author":"J Lei","year":"2021","unstructured":"Lei, J., Berg, T.L., Bansal, M.: Detecting moments and highlights in videos via natural language queries. Adv. Neural. Inf. Process. Syst. 34, 11846\u201311858 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Li, C., Li, Z., Jing, C., Jia, Y., Wu, Y.: Exploring the effect of primitives for compositional generalization in vision-and-language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19092\u201319101 (2023)","DOI":"10.1109\/CVPR52729.2023.01830"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Ke, Q., Gong, M., Drummond, T.: Progressive video summarization via multimodal self-supervised learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5584\u20135593 (2023)","DOI":"10.1109\/WACV56688.2023.00554"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Compositional temporal grounding with structured variational cross-graph correspondence learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3032\u20133041 (2022)","DOI":"10.1109\/CVPR52688.2022.00304"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Li, X., Yang, X., Wei, K., Deng, C., Yang, M.: Siamese contrastive embedding network for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9326\u20139335 (2022)","DOI":"10.1109\/CVPR52688.2022.00911"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Lin, K.Q., et al.: Univtg: towards unified video-language temporal grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2794\u20132804 (2023)","DOI":"10.1109\/ICCV51070.2023.00262"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Liu, B., Yeung, S., Chou, E., Huang, D.A., Fei-Fei, L., Niebles, J.C.: Temporal modular networks for retrieving complex compositional activities in videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 552\u2013568 (2018)","DOI":"10.1007\/978-3-030-01219-9_34"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Liu, M., Wang, X., Nie, L., Tian, Q., Chen, B., Chua, T.S.: Cross-modal moment localization in videos. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 843\u2013851 (2018)","DOI":"10.1145\/3240508.3240549"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, S., Wu, Y., Chen, C.W., Shan, Y., Qie, X.: Umt: unified multi-modal transformers for joint video moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3042\u20133051 (2022)","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Lu, X., Guo, S., Liu, Z., Guo, J.: Decomposed soft prompt guided fusion enhancing for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23560\u201323569 (2023)","DOI":"10.1109\/CVPR52729.2023.02256"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: Crepe: can vision-language foundation models reason compositionally? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10910\u201310921 (2023)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"23_CR30","unstructured":"Meta: Llama 3 (2024). https:\/\/llama.meta.com\/llama3\/"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Moon, W., Hyun, S., Park, S., Park, D., Heo, J.P.: Query-dependent video representation for moment retrieval and highlight detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23023\u201323033 (2023)","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Mun, J., Cho, M., Han, B.: Local-global video-text interactions for temporal grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10810\u201310819 (2020)","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Pu, Y., Wu, X.: Locality-aware attention network with discriminative dynamics learning for weakly supervised anomaly detection. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp.\u00a01\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859718"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Pu, Y., Wu, X., Yang, L., Wang, S.: Learning prompt-enhanced context features for weakly-supervised video anomaly detection. arXiv preprint arXiv:2306.14451 (2023)","DOI":"10.1109\/TIP.2024.3451935"},{"key":"23_CR35","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":"23_CR36","unstructured":"Ray, A., Radenovic, F., Dubey, A., Plummer, B., Krishna, R., Saenko, K.: cola: a benchmark for compositional text-to-image retrieval. Adv. Neural Inf. Process. Syst. 36 (2023)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Singh, H., et al.: Coarse-to-fine contrastive learning in image-text-graph space for improved vision-language compositionality. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, 6\u201310 December 2023, pp. 869\u2013893 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.56"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Trager, M., Perera, P., Zancato, L., Achille, A., Bhatia, P., Soatto, S.: Linear spaces of meanings: compositional structures in vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15395\u201315404 (2023)","DOI":"10.1109\/ICCV51070.2023.01412"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, L., Wu, T., Li, T., Wu, G.: Negative sample matters: a renaissance of metric learning for temporal grounding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2613\u20132623 (2022)","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Wu, J., Li, G., Liu, S., Lin, L.: Tree-structured policy based progressive reinforcement learning for temporally language grounding in video. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12386\u201312393 (2020)","DOI":"10.1609\/aaai.v34i07.6924"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, S., et al.: Boundary proposal network for two-stage natural language video localization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 2986\u20132994 (2021)","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Xu, G., Chai, J., Kordjamshidi, P.: Gipcol: graph-injected soft prompting for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5774\u20135783 (2024)","DOI":"10.1109\/WACV57701.2024.00567"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Xu, G., Kordjamshidi, P., Chai, J.: Metarevision: meta-learning with retrieval for visually grounded compositional concept acquisition. arXiv preprint arXiv:2311.01580 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.818"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Xu, H., He, K., Plummer, B.A., Sigal, L., Sclaroff, S., Saenko, K.: Multilevel language and vision integration for text-to-clip retrieval. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 9062\u20139069 (2019)","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Unloc: a unified framework for video localization tasks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13623\u201313633 (2023)","DOI":"10.1109\/ICCV51070.2023.01253"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Yang, L., Kong, Q., Yang, H.K., Kehl, W., Sato, Y., Kobori, N.: Deco: decomposition and reconstruction for compositional temporal grounding via coarse-to-fine contrastive ranking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23130\u201323140 (2023)","DOI":"10.1109\/CVPR52729.2023.02215"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Yao, T., Mei, T., Rui, Y.: Highlight detection with pairwise deep ranking for first-person video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 982\u2013990 (2016)","DOI":"10.1109\/CVPR.2016.112"},{"key":"23_CR48","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: Anetqa: a large-scale benchmark for fine-grained compositional reasoning over untrimmed videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23191\u201323200 (2023)","DOI":"10.1109\/CVPR52729.2023.02221"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Mei, T., Zhu, W.: To find where you talk: temporal sentence localization in video with attention based location regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 9159\u20139166 (2019)","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"23_CR50","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":"23_CR51","doi-asserted-by":"crossref","unstructured":"Zala, A., et al.: Hierarchical video-moment retrieval and step-captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23056\u201323065 (2023)","DOI":"10.1109\/CVPR52729.2023.02208"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Zeng, Y., Cao, D., Wei, X., Liu, M., Zhao, Z., Qin, Z.: Multi-modal relational graph for cross-modal video moment retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2215\u20132224 (2021)","DOI":"10.1109\/CVPR46437.2021.00225"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, X., Wang, X., Wang, Y.F., Davis, L.S.: Man: moment alignment network for natural language moment retrieval via iterative graph adjustment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1247\u20131257 (2019)","DOI":"10.1109\/CVPR.2019.00134"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, H., Sun, A., Jing, W., Zhou, J.T.: Span-based localizing network for natural language video localization. arXiv preprint arXiv:2004.13931 (2020)","DOI":"10.18653\/v1\/2020.acl-main.585"},{"issue":"12","key":"23_CR55","doi-asserted-by":"publisher","first-page":"9073","DOI":"10.1109\/TPAMI.2021.3120745","volume":"44","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Peng, H., Fu, J., Lu, Y., Luo, J.: Multi-scale 2d temporal adjacency networks for moment localization with natural language. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9073\u20139087 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Luo, J.: Learning 2d temporal adjacent networks for moment localization with natural language. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 12870\u201312877 (2020)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"23_CR57","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Zhu, H., Nevatia, R.: Caila: concept-aware intra-layer adapters for compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1721\u20131731 (2024)","DOI":"10.1109\/WACV57701.2024.00174"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Tang, W., Wang, L., Zheng, N., Hua, G.: Enriching local and global contexts for temporal action localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13516\u201313525 (2021)","DOI":"10.1109\/ICCV48922.2021.01326"}],"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\/978-3-031-72655-2_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T11:34:09Z","timestamp":1733398449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72655-2_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"ISBN":["9783031726545","9783031726552"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72655-2_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"6 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"}}]}}