{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:37:49Z","timestamp":1778081869033,"version":"3.51.4"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726231","type":"print"},{"value":"9783031726248","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72624-8_6","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"92-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["AMEGO: Active Memory from\u00a0Long EGOcentric Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3778-6460","authenticated-orcid":false,"given":"Gabriele","family":"Goletto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1627-3842","authenticated-orcid":false,"given":"Tushar","family":"Nagarajan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1212-3465","authenticated-orcid":false,"given":"Giuseppe","family":"Averta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8804-6238","authenticated-orcid":false,"given":"Dima","family":"Damen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Sun, C., Schmid, C.: Unified graph structured models for video understanding. In: Proceedings of the International Conference on Computer Vision, pp. 8117\u20138126 (2021)","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Baradel, F., Neverova, N., Wolf, C., Mille, J., Mori, G.: Object level visual reasoning in videos. In: Proceedings of the European Conference on Computer, pp. 105\u2013121 (2018)","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Brendel, W., Todorovic, S.: Learning spatiotemporal graphs of human activities. In: Proceedings of the International Conference on Computer Vision, pp. 778\u2013785 (2011)","DOI":"10.1109\/ICCV.2011.6126316"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Cong, Y., Liao, W., Ackermann, H., Rosenhahn, B., Yang, M.Y.: Spatial-temporal transformer for dynamic scene graph generation. In: Proceedings of the International Conference on Computer Vision, pp. 16372\u201316382 (2021)","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Damen","year":"2022","unstructured":"Damen, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for EPIC-KITCHENS-100. IJCV 130, 33\u201355 (2022)","journal-title":"IJCV"},{"key":"6_CR6","unstructured":"Darkhalil, A., et al.: EPIC-KITCHENS VISOR benchmark: video segmentations and object relations. In: NeurIPS (2022)"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Datta, S., et al.: Episodic memory question answering. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01853"},{"key":"6_CR8","unstructured":"Du, Y., et al.: Towards event-oriented long video understanding. arXiv preprint arXiv:2406.14129 (2024)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Y., et al.: VideoAgent: a memory-augmented multimodal agent for video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72670-5_5"},{"key":"6_CR10","unstructured":"Fang, X., et al.: MMBench-Video: a long-form multi-shot benchmark for holistic video understanding. arXiv preprint arXiv:2406.14515 (2024)"},{"key":"6_CR11","unstructured":"Grauman, K., et al.: Ego4D: around the world in 3,000 hours of egocentric video. In: CVPR (2022)"},{"key":"6_CR12","unstructured":"Grauman, K., et al.: Ego-Exo4D: understanding skilled human activity from first-and third-person perspectives. In: CVPR (2024)"},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1007\/978-3-031-19790-1_40","volume-title":"ECCV 2022","author":"Z Huang","year":"2022","unstructured":"Huang, Z., et al.: FlowFormer: a transformer architecture for optical flow. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13677, pp. 668\u2013685. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_40"},{"key":"6_CR14","unstructured":"Hussein, N., Gavves, E., Smeulders, A.W.: VideoGraph: recognizing minutes-long human activities in videos. arXiv preprint arXiv:1905.05143 (2019)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Jain, A., Zamir, A.R., Savarese, S., Saxena, A.: Structural-RNN: deep learning on spatio-temporal graphs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.573"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Jasani, B., Girdhar, R., Ramanan, D.: Are we asking the right questions in MovieQA? In: ICCV Workshop (2019)","DOI":"10.1109\/ICCVW.2019.00235"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Ji, J., Krishna, R., Fei-Fei, L., Niebles, J.C.: Action genome: actions as compositions of spatio-temporal scene graphs. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01025"},{"key":"6_CR18","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: CVPR (2012)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"6_CR20","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":"6_CR21","unstructured":"Li, Y., Chen, X., Hu, B., Zhang, M.: LLMs meet long video: advancing long video comprehension with an interactive visual adapter in LLMs. arXiv preprint arXiv:2402.13546 (2024)"},{"key":"6_CR22","unstructured":"Li, Y., Chen, X., Hu, B., Wang, L., Shi, H., Zhang, M.: VideoVista: a versatile benchmark for video understanding and reasoning. arXiv preprint arXiv:2406.11303 (2024)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Lin, Y.L., Morariu, V.I., Hsu, W.: Summarizing while recording: context-based highlight detection for egocentric videos. In: ICCV Workshop (2015)","DOI":"10.1109\/ICCVW.2015.65"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Lu, Z., Grauman, K.: Story-driven summarization for egocentric video. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.350"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Ma, C.Y., Kadav, A., Melvin, I., Kira, Z., AlRegib, G., Graf, H.P.: Attend and interact: higher-order object interactions for video understanding. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00710"},{"key":"6_CR26","unstructured":"Ma, Z., et al.: DrVideo: document retrieval based long video understanding. arXiv preprint arXiv:2406.12846 (2024)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Mahasseni, B., Lam, M., Todorovic, S.: Unsupervised video summarization with adversarial LSTM networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.318"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Mai, J., Hamdi, A., Giancola, S., Zhao, C., Ghanem, B.: EgoLoc: revisiting 3D object localization from egocentric videos with visual queries. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00011"},{"key":"6_CR29","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: NeurIPS (2024)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Mavroudi, E., Afouras, T., Torresani, L.: Learning to ground instructional articles in videos through narrations. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01395"},{"key":"6_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105667","volume":"118","author":"P Meena","year":"2023","unstructured":"Meena, P., Kumar, H., Yadav, S.K.: A review on video summarization techniques. Eng. Appl. Artif. Intell. 118, 105667 (2023)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Li, Y., Feichtenhofer, C., Grauman, K.: EGO-TOPO: environment affordances from egocentric video. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00024"},{"key":"6_CR33","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"6_CR34","unstructured":"Park, J., Ranasinghe, K., Kahatapitiya, K., Ryoo, W., Kim, D., Ryoo, M.S.: Too many frames, not all useful: efficient strategies for long-form video QA. arXiv preprint arXiv:2406.09396 (2024)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Price, W., Vondrick, C., Damen, D.: UnweaveNet: unweaving activity stories. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01340"},{"key":"6_CR36","unstructured":"Qian, R., et al.: Streaming long video understanding with large language models. arXiv preprint arXiv:2405.16009 (2024)"},{"key":"6_CR37","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.K., Al-Halah, Z., Grauman, K.: NaQ: leveraging narrations as queries to supervise episodic memory. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00647"},{"key":"6_CR39","unstructured":"Rawal, R., Saifullah, K., Basri, R., Jacobs, D., Somepalli, G., Goldstein, T.: CinePile: a long video question answering dataset and benchmark. arXiv preprint arXiv:2405.08813 (2024)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"6_CR41","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-030-01258-8_22","volume-title":"ECCV 2018","author":"M Rochan","year":"2018","unstructured":"Rochan, M., Ye, L., Wang, Y.: Video summarization using fully convolutional sequence networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 358\u2013374. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_22"},{"key":"6_CR42","doi-asserted-by":"crossref","unstructured":"Rodin, I., Furnari, A., Min, K., Tripathi, S., Farinella, G.M.: Action scene graphs for long-form understanding of egocentric videos. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01762"},{"key":"6_CR43","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"6_CR44","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: Revisiting weakly supervised pre-training of visual perception models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"6_CR45","doi-asserted-by":"crossref","unstructured":"Song, E., et al.: MovieChat: from dense token to sparse memory for long video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"6_CR46","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/978-3-030-01252-6_20","volume-title":"ECCV 2018","author":"C Sun","year":"2018","unstructured":"Sun, C., Shrivastava, A., Vondrick, C., Murphy, K., Sukthankar, R., Schmid, C.: Actor-centric relation network. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 335\u2013351. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_20"},{"key":"6_CR47","unstructured":"Tang, H., Liang, K.J., Grauman, K., Feiszli, M., Wang, W.: EgoTracks: a long-term egocentric visual object tracking dataset. In: NeurIPS (2024)"},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.501"},{"key":"6_CR49","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"6_CR50","unstructured":"Tschernezki, V., et al.: EPIC fields: marrying 3D geometry and video understanding. In: NeurIPS (2024)"},{"issue":"1","key":"6_CR51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1146\/annurev.psych.53.100901.135114","volume":"53","author":"E Tulving","year":"2002","unstructured":"Tulving, E.: Episodic memory: from mind to brain. Annu. Rev. Psychol. 53(1), 1\u201325 (2002)","journal-title":"Annu. Rev. Psychol."},{"key":"6_CR52","unstructured":"Tulving, E., et al.: Episodic and semantic memory. In: Organization of Memory, pp. 381\u2013403 (1972)"},{"key":"6_CR53","unstructured":"Wang, W., et al.: LVBench: an extreme long video understanding benchmark. arXiv preprint arXiv:2406.08035 (2024)"},{"key":"6_CR54","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, Y., Zohar, O., Yeung-Levy, S.: VideoAgent: long-form video understanding with large language model as agent. arXiv preprint arXiv:2403.10517 (2024)","DOI":"10.1007\/978-3-031-72989-8_4"},{"key":"6_CR55","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-030-01228-1_25","volume-title":"ECCV 2018","author":"X Wang","year":"2018","unstructured":"Wang, X., Gupta, A.: Videos as space-time region graphs. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 413\u2013431. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_25"},{"key":"6_CR56","unstructured":"Wang, Y., Yang, Y., Ren, M.: LifelongMemory: leveraging LLMs for answering queries in egocentric videos. arXiv preprint arXiv:2312.05269 (2023)"},{"key":"6_CR57","unstructured":"Wang, Z., et al.: VideoTree: adaptive tree-based video representation for LLM reasoning on long videos. arXiv preprint arXiv:2405.19209 (2024)"},{"key":"6_CR58","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: MeMViT: memory-augmented multiscale vision transformer for efficient long-term video recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"6_CR59","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-319-10602-1_19","volume-title":"ECCV 2014","author":"B Xiong","year":"2014","unstructured":"Xiong, B., Grauman, K.: Detecting snap points in egocentric video with a web photo prior. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 282\u2013298. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_19"},{"key":"6_CR60","doi-asserted-by":"crossref","unstructured":"Xiong, B., Kim, G., Sigal, L.: Storyline representation of egocentric videos with an applications to story-based search. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.514"},{"key":"6_CR61","doi-asserted-by":"crossref","unstructured":"Xu, M., Li, Y., Fu, C.Y., Ghanem, B., Xiang, T., P\u00e9rez-R\u00faa, J.M.: Where is my wallet? Modeling object proposal sets for egocentric visual query localization. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00255"},{"key":"6_CR62","doi-asserted-by":"crossref","unstructured":"Yagi, T., Nishiyasu, T., Kawasaki, K., Matsuki, M., Sato, Y.: GO-finder: a registration-free wearable system for assisting users in finding lost objects via hand-held object discovery. In: International Conference on Intelligent User Interfaces (2021)","DOI":"10.1145\/3397481.3450664"},{"key":"6_CR63","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: CVPR (2021)","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"6_CR64","unstructured":"Yang, J., Zhu, Y., Wang, Y., Yi, R., Zadeh, A., Morency, L.P.: What gives the answer away? Question answering bias analysis on video QA datasets. arXiv preprint arXiv:2007.03626 (2020)"},{"key":"6_CR65","doi-asserted-by":"crossref","unstructured":"Yang, X., Chu, F.J., Feiszli, M., Goyal, R., Torresani, L., Tran, D.: Relational space-time query in long-form videos. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00619"},{"key":"6_CR66","doi-asserted-by":"crossref","unstructured":"Yu, Z., et al.: ActivityNet-QA: a dataset for understanding complex web videos via question answering. In: Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"6_CR67","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y.: From recognition to cognition: visual commonsense reasoning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00688"},{"key":"6_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A simple LLM framework for long-range video question-answering. arXiv preprint arXiv:2312.17235 (2023)","DOI":"10.18653\/v1\/2024.emnlp-main.1209"},{"key":"6_CR69","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1007\/978-3-031-19772-7_29","volume-title":"ECCV 2022","author":"CL Zhang","year":"2022","unstructured":"Zhang, C.L., Wu, J., Li, Y.: ActionFormer: localizing moments of actions with transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13664, pp. 492\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19772-7_29"},{"key":"6_CR70","doi-asserted-by":"crossref","unstructured":"Zhao, B., Xing, E.P.: Quasi real-time summarization for consumer videos. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.322"},{"key":"6_CR71","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Misra, I., Kr\u00e4henb\u00fchl, P., Girdhar, R.: Learning video representations from large language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6586\u20136597 (2023)","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"6_CR72","unstructured":"Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NeurIPS (2014)"},{"key":"6_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, K., Qiao, Y., Xiang, T.: Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. In: Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12255"}],"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\/978-3-031-72624-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T07:45:36Z","timestamp":1732952736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72624-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726231","9783031726248"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72624-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}