{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:20:58Z","timestamp":1783437658897,"version":"3.54.6"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031920882","type":"print"},{"value":"9783031920899","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92089-9_2","type":"book-chapter","created":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:47:55Z","timestamp":1748090875000},"page":"15-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MVTN: A Multiscale Video Transformer Network for\u00a0Hand Gesture Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6056-6490","authenticated-orcid":false,"given":"Mallika","family":"Garg","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5672-7645","authenticated-orcid":false,"given":"Debashis","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-5577","authenticated-orcid":false,"given":"Pyari Mohan","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Abavisani, M., Joze, H.R.V., Patel, V.M.: Improving the performance of unimodal dynamic hand-gesture recognition with multimodal training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1165\u20131174 (2019)","DOI":"10.1109\/CVPR.2019.00126"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"145929","DOI":"10.1109\/ACCESS.2021.3122921","volume":"9","author":"N Aloysius","year":"2021","unstructured":"Aloysius, N., Geetha, M., Nedungadi, P.: Incorporating relative position information in transformer-based sign language recognition and translation. IEEE Access 9, 145929\u2013145942 (2021)","journal-title":"IEEE Access"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Cao, C., Zhang, Y., Wu, Y., Lu, H., Cheng, J.: Egocentric gesture recognition using recurrent 3d convolutional neural networks with spatiotemporal transformer modules. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (Oct 2017)","DOI":"10.1109\/ICCV.2017.406"},{"key":"2_CR4","unstructured":"Chen, B., et al.: Psvit: Better vision transformer via token pooling and attention sharing. arXiv preprint arXiv:2108.03428 (2021)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Li, Y., Fang, H., Xin, W., Lu, Z., Miao, Q.: Multi-scale attention 3d convolutional network for multimodal gesture recognition. Sensors 22 (2022)","DOI":"10.3390\/s22062405"},{"key":"2_CR6","unstructured":"Choromanski, K., et\u00a0al.: Rethinking attention with performers. arXiv preprint arXiv:2009.14794 (2020)"},{"key":"2_CR7","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., et al.: Twins: Revisiting the design of spatial attention in vision transformers. Adv. Neural. Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR8","unstructured":"De\u00a0Coster, M., Van\u00a0Herreweghe, M., Dambre, J.: Sign language recognition with transformer networks. In: Proceedings of the Twelfth Language Resources and Evaluation Conference (May 2020)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Deshmukh, G., Susladkar, O., Makwana, D., Mittal, S., et\u00a0al.: Textual alchemy: Coformer for scene text understanding. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2931\u20132941 (2024)","DOI":"10.1109\/WACV57701.2024.00291"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Dhingra, N., Kunz, A.: Res3atn-deep 3d residual attention network for hand gesture recognition in videos. In: 2019 International Conference on 3D Vision (3DV), pp. 491\u2013501. IEEE (2019)","DOI":"10.1109\/3DV.2019.00061"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Dong, X., eta al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"2_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"D\u2019Eusanio, A., Simoni, A., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: Multimodal hand gesture classification for the human\u2013car interaction. Informatics, 31 (2020)","DOI":"10.3390\/informatics7030031"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"D\u2019Eusanio, A., Simoni, A., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: A transformer-based network for dynamic hand gesture recognition. In: 2020 International Conference on 3D Vision (3DV), pp. 623\u2013632. IEEE (2020)","DOI":"10.1109\/3DV50981.2020.00072"},{"issue":"23","key":"2_CR16","doi-asserted-by":"publisher","first-page":"27026","DOI":"10.1109\/JSEN.2021.3123443","volume":"21","author":"D Fan","year":"2021","unstructured":"Fan, D., Lu, H., Xu, S., Cao, S.: Multi-task and multi-modal learning for rgb dynamic gesture recognition. IEEE Sens. J. 21(23), 27026\u201327036 (2021)","journal-title":"IEEE Sens. J."},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"2_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/3-540-45103-X_50","volume-title":"Image Analysis","author":"G Farneb\u00e4ck","year":"2003","unstructured":"Farneb\u00e4ck, G.: Two-Frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363\u2013370. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45103-X_50"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/LSP.2023.3241857","volume":"30","author":"M Garg","year":"2023","unstructured":"Garg, M., Ghosh, D., Pradhan, P.M.: Multiscaled multi-head attention-based video transformer network for hand gesture recognition. IEEE Signal Process. Lett. 30, 80\u201384 (2023)","journal-title":"IEEE Signal Process. Lett."},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Garg, M., Ghosh, D., Pradhan, P.M.: Gestformer: multiscale wavelet pooling transformer network for dynamic hand gesture recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 2473\u20132483 (June 2024)","DOI":"10.1109\/CVPRW63382.2024.00254"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Garg, M., Pradhan, P.M., Ghosh, D.: Multiview hand gesture recognition using deep learning. In: 2021 IEEE 18th India Council International Conference (INDICON) (2021)","DOI":"10.1109\/INDICON52576.2021.9691523"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., J\u00e9gou, H., Douze, M.: Levit: a vision transformer in convnet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12259\u201312269 (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Multi-scale high-resolution vision transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12094\u201312103 (2022)","DOI":"10.1109\/CVPR52688.2022.01178"},{"issue":"9","key":"2_CR24","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11936\u201311945 (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"2_CR27","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180 (2019)"},{"key":"2_CR28","unstructured":"Huang, C.Z.A., et al.: Music transformer. arXiv preprint arXiv:1809.04281 (2018)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Jeevan, P., Sethi, A.: Resource-efficient hybrid x-formers for vision. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2982\u20132990 (2022)","DOI":"10.1109\/WACV51458.2022.00361"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc, O., Gunduz, A., Kose, N., Rigoll, G.: Real-time hand gesture detection and classification using convolutional neural networks. In: 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp.\u00a01\u20138. IEEE (2019)","DOI":"10.1109\/FG.2019.8756576"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Kopuklu, O., Kose, N., Rigoll, G.: Motion fused frames: data level fusion strategy for hand gesture recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2103\u20132111 (2018)","DOI":"10.1109\/CVPRW.2018.00284"},{"key":"2_CR32","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1109\/TIP.2022.3166673","volume":"31","author":"J Li","year":"2022","unstructured":"Li, J., Zha, S., Chen, C., Ding, M., Zhang, T., Yu, H.: Attention guided global enhancement and local refinement network for semantic segmentation. IEEE Trans. Image Process. 31, 3211\u20133223 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Uniformer: unifying convolution and self-attention for visual recognition. IEEE Trans. Pattern Analy. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: Improved multiscale vision transformers for classification and detection. arxiv 2021. arXiv preprint arXiv:2112.01526","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Mallika, G., Ghosh, D., Pradhan, P.M.: A two-stage convolutional neural network for hand gesture recognition. In: Proceedings of the 6th International Conference on Advance Computing and Intelligent Engineering: ICACIE 2021 (2022)","DOI":"10.1007\/978-981-19-2225-1_34"},{"key":"2_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1007\/978-3-030-30645-8_51","volume-title":"Image Analysis and Processing \u2013 ICIAP 2019","author":"F Manganaro","year":"2019","unstructured":"Manganaro, F., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: Hand gestures for the human-car interaction: the briareo dataset. In: Ricci, E., Rota Bul\u00f2, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019. LNCS, vol. 11752, pp. 560\u2013571. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30645-8_51"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215 (2016)","DOI":"10.1109\/CVPR.2016.456"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Neimark, D., Bar, O., Zohar, M., Asselmann, D.: Video transformer network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3163\u20133172 (2021)","DOI":"10.1109\/ICCVW54120.2021.00355"},{"key":"2_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105488","volume":"87","author":"G Siddhad","year":"2024","unstructured":"Siddhad, G., Gupta, A., Dogra, D.P., Roy, P.P.: Efficacy of transformer networks for classification of eeg data. Biomed. Signal Process. Control 87, 105488 (2024)","journal-title":"Biomed. Signal Process. Control"},{"key":"2_CR41","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. Adv. Neural Inform. Process. Syst. 27 (2014)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4489\u20134497 (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"2_CR43","unstructured":"Vadis, Q., Carreira, J., Zisserman, A.: Action recognition? a new model and the kinetics dataset. Joao Carreira, Andrew Zisserman"},{"key":"2_CR44","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"2_CR45","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang, H., Oneata, D., Verbeek, J., Schmid, C.: A robust and efficient video representation for action recognition. Int. J. Comput. Vision 119, 219\u2013238 (2016)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR46","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768 (2020)"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22\u201331 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Y.H., Liu, Y., Zhan, X., Cheng, M.M.: P2t: pyramid pooling transformer for scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3202765"},{"key":"2_CR50","first-page":"30392","volume":"34","author":"T Xiao","year":"2021","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., Girshick, R.: Early convolutions help transformers see better. Adv. Neural. Inf. Process. Syst. 34, 30392\u201330400 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Xiong, Y., et al.: Nystr\u00f6mformer: A nystr\u00f6m-based algorithm for approximating self-attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 14138\u201314148 (2021)","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Yang, X., Molchanov, P., Kautz, J.: Making convolutional networks recurrent for visual sequence learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6469\u20136478 (2018)","DOI":"10.1109\/CVPR.2018.00677"},{"key":"2_CR53","doi-asserted-by":"publisher","first-page":"5626","DOI":"10.1109\/TIP.2021.3087348","volume":"30","author":"Z Yu","year":"2021","unstructured":"Yu, Z., et al.: Searching multi-rate and multi-modal temporal enhanced networks for gesture recognition. IEEE Trans. Image Process. 30, 5626\u20135640 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"2_CR55","unstructured":"Yuan, Y., et al.: Hrformer: high-resolution transformer for dense prediction. arXiv preprint arXiv:2110.09408 (2021)"},{"issue":"1","key":"2_CR56","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/JAS.2020.1003465","volume":"8","author":"W Zhang","year":"2020","unstructured":"Zhang, W., Wang, J., Lan, F.: Dynamic hand gesture recognition based on short-term sampling neural networks. IEEE\/CAA J. Automatica Sinica 8(1), 110\u2013120 (2020)","journal-title":"IEEE\/CAA J. Automatica Sinica"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Zheng, C., Liu, X., Qi, G.J., Chen, C.: Potter: pooling attention transformer for efficient human mesh recovery. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1611\u20131620 (2023)","DOI":"10.1109\/CVPR52729.2023.00161"},{"key":"2_CR58","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Zhao, X., Wang, Y., Wang, P., Foroosh, H.: Centerformer: center-based transformer for 3d object detection. In: European Conference on Computer Vision. pp. 496\u2013513. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_29","DOI":"10.1007\/978-3-031-19839-7_29"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92089-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T12:48:07Z","timestamp":1748090887000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92089-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031920882","9783031920899"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92089-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}