{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:06:40Z","timestamp":1761898000804,"version":"3.40.3"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732089"},{"type":"electronic","value":"9783031732096"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73209-6_22","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"377-395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Audio-Visual Generalized Zero-Shot Learning the\u00a0Easy Way"],"prefix":"10.1007","author":[{"given":"Shentong","family":"Mo","sequence":"first","affiliation":[]},{"given":"Pedro","family":"Morgado","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/978-3-030-58539-6_2","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Chen","year":"2020","unstructured":"Chen, C., et al.: SoundSpaces: audio-visual navigation in 3D environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 17\u201336. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_2"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Majumder, S., Ziad, A.H., Gao, R., Kumar\u00a0Ramakrishnan, S., Grauman, K.: Learning to set waypoints for audio-visual navigation. In: Proceedings of International Conference on Learning Representations (ICLR) (2021)","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"22_CR6","unstructured":"Chen, C., et al.: SoundSpaces 2.0: a simulation platform for visual-acoustic learning. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track (2022)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: VGGSound: a large-scale audio-visual dataset. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 721\u2013725. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. arXiv preprint arXiv:1804.03619 (2018)","DOI":"10.1145\/3197517.3201357"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Fayek, H.M., Kumar, A.: Large scale audiovisual learning of sounds with weakly labeled data. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (2021)","DOI":"10.24963\/ijcai.2020\/78"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Zhao, H., Tenenbaum, J.B., Torralba, A.: Music gesture for visual sound separation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10478\u201310487 (2020)","DOI":"10.1109\/CVPR42600.2020.01049"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: 2.5d visual sound. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 324\u2013333 (2019)","DOI":"10.1109\/CVPR.2019.00041"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Girdhar, R., et al.: ImageBind: one embedding space to bind them all. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"22_CR13","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":"22_CR14","unstructured":"Hershey, J., Casey, M.: Audio-visual sound separation via hidden Markov models. Adv. Neural Inf. Process. Syst. 14 (2001)"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Hong, J., Hayder, Z., Han, J., Fang, P., Harandi, M., Petersson, L.: Hyperbolic audio-visual zero-shot learning. In: Proceedings of the International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00724"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Hu, D., Nie, F., Li, X.: Deep multimodal clustering for unsupervised audiovisual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9248\u20139257 (2019)","DOI":"10.1109\/CVPR.2019.00947"},{"key":"22_CR18","unstructured":"Huang, P.Y., et al.: Masked autoencoders that listen. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"22_CR19","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver: general perception with iterative attention. In: Proceedings of the International Conference on Machine Learning (ICML) (2021)"},{"key":"22_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"22_CR21","unstructured":"Korbar, B., Tran, D., Torresani, L.: Cooperative learning of audio and video models from self-supervised synchronization. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Li, Y.J., Wang, Y.C.F.: Dual-modality Seq2Seq network for audio-visual event localization. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2002\u20132006 (2019)","DOI":"10.1109\/ICASSP.2019.8683226"},{"key":"22_CR23","unstructured":"Lin, Y.B., Tseng, H.Y., Lee, H.Y., Lin, Y.Y., Yang, M.H.: Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: Proceedings of the Asian Conference on Computer Vision (ACCV) (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"22_CR25","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. arXiv preprint arXiv:2207.07285 (2022)","DOI":"10.1145\/3503161.3547910"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Mazumder, P., Sing, P., Kumar\u00a0Parida, K., Namboodiri, V.P.: AVGZSLNet: audio-visual generalized zero-shot learning by reconstructing label features from multi-modal embeddings. In: Proceedings of 2021 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3089\u20133098 (2021)","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"22_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"488","DOI":"10.1007\/978-3-031-20044-1_28","volume-title":"Computer Vision \u2013 ECCV 2022","author":"OB Mercea","year":"2022","unstructured":"Mercea, O.B., Hummel, T., Koepke, A.S., Akata, Z.: Temporal and cross-modal attention for audio-visual zero-shot learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13680, pp. 488\u2013505. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20044-1_28"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Riesch, L., Koepke, A.S., Akata, Z.: Audio-visual generalised zero-shot learning with cross-modal attention and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10553\u201310563 (2022)","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"22_CR29","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: Proceedings of International Conference on Learning Representations (ICLR) (2013)"},{"key":"22_CR30","unstructured":"Mo, S., Morgado, P.: Benchmarking weakly-supervised audio-visual sound localization. In: European Conference on Computer Vision (ECCV) Workshop (2022)"},{"key":"22_CR31","unstructured":"Mo, S., Morgado, P.: A closer look at weakly-supervised audio-visual source localization. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"22_CR32","unstructured":"Mo, S., Morgado, P.: A unified audio-visual learning framework for localization, separation, and recognition. In: Proceedings of the International Conference on Machine Learning (ICML) (2023)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Mo, S., Morgado, P.: Unveiling the power of audio-visual early fusion transformers with dense interactions through masked modeling. arXiv preprint arXiv:2312.01017 (2023)","DOI":"10.1109\/CVPR52733.2024.02567"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Mo, S., Pian, W., Tian, Y.: Class-incremental grouping network for continual audio-visual learning. arXiv preprint arXiv:2309.05281 (2023)","DOI":"10.1109\/ICCV51070.2023.00716"},{"key":"22_CR35","unstructured":"Mo, S., Shi, J., Tian, Y.: DiffAVA: personalized text-to-audio generation with visual alignment. arXiv preprint arXiv:2305.12903 (2023)"},{"key":"22_CR36","unstructured":"Mo, S., Shi, J., Tian, Y.: Text-to-audio generation synchronized with videos. arXiv preprint arXiv:2403.07938 (2024)"},{"key":"22_CR37","unstructured":"Mo, S., Tian, Y.: Multi-modal grouping network for weakly-supervised audio-visual video parsing. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"22_CR38","unstructured":"Mo, S., Tian, Y.: Semantic-aware multi-modal grouping for weakly-supervised audio-visual video parsing. In: European Conference on Computer Vision (ECCV) Workshop (2022)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Mo, S., Tian, Y.: Audio-visual grouping network for sound localization from mixtures. arXiv preprint arXiv:2303.17056 (2023)","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"22_CR40","unstructured":"Mo, S., Tian, Y.: AV-SAM: segment anything model meets audio-visual localization and segmentation. arXiv preprint arXiv:2305.01836 (2023)"},{"key":"22_CR41","unstructured":"Mo, S., Tian, Y.: Semantic grouping network for audio source separation. arXiv preprint arXiv:2407.03736 (2024)"},{"key":"22_CR42","unstructured":"Morgado, P., Li, Y., Vasconcelos, N.: Learning representations from audio-visual spatial alignment. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), pp. 4733\u20134744 (2020)"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Morgado, P., Li, Y., Costa\u00a0Pereira, J., Saberian, M., Vasconcelos, N.: Deep hashing with hash-consistent large margin proxy embeddings. Int. J. Comput. Vision (2020)","DOI":"10.1007\/s11263-020-01362-7"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Morgado, P., Misra, I., Vasconcelos, N.: Robust audio-visual instance discrimination. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12934\u201312945 (2021)","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"22_CR45","unstructured":"Morgado, P., Vasconcelos, N., Langlois, T., Wang, O.: Self-supervised generation of spatial audio for 360 video. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Morgado, P., Vasconcelos, N., Misra, I.: Audio-visual instance discrimination with cross-modal agreement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12475\u201312486 (2021)","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"22_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-319-46448-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Owens","year":"2016","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 801\u2013816. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Parida, K.K., Matiyali, N., Guha, T., Sharma, G.: Coordinated joint multimodal embeddings for generalized audio-visual zero-shot classification and retrieval of videos. In: Proceedings of 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3240\u20133249 (2020)","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Pian, W., Mo, S., Guo, Y., Tian, Y.: Audio-visual class-incremental learning. arXiv preprint arXiv:2308.11073 (2023)","DOI":"10.1109\/ICCV51070.2023.00717"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Senocak, A., Oh, T.H., Kim, J., Yang, M.H., Kweon, I.S.: Learning to localize sound source in visual scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4358\u20134366 (2018)","DOI":"10.1109\/CVPR.2018.00458"},{"key":"22_CR51","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)"},{"issue":"1","key":"22_CR52","first-page":"1","volume":"27","author":"PML Tammes","year":"1930","unstructured":"Tammes, P.M.L.: On the origin of number and arrangement of the places of exit on the surface of pollen-grains. Recueil travaux botaniques n\u00e9erlandais 27(1), 1\u201384 (1930)","journal-title":"Recueil travaux botaniques n\u00e9erlandais"},{"key":"22_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58580-8_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Li, D., Xu, C.: Unified multisensory perception: weakly-supervised audio-visual video\u00a0parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_26"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"22_CR55","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"22_CR56","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 (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1326\u20131335 (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 6291\u20136299 (2019)","DOI":"10.1109\/ICCV.2019.00639"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Wu, Y., Chen, K., Zhang, T., Hui, Y., Berg-Kirkpatrick, T., Dubnov, S.: Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (2023)","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, L., Mo, S., Zhang, Y., Morgado, P.: Audio-synchronized visual animation. arXiv preprint arXiv:2403.05659 (2024)","DOI":"10.1007\/978-3-031-72940-9_1"},{"key":"22_CR61","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Ma, W.C., Torralba, A.: The sound of motions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1735\u20131744 (2019)","DOI":"10.1109\/ICCV.2019.00182"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, H., Gan, C., Rouditchenko, A., Vondrick, C., McDermott, J., Torralba, A.: The sound of pixels. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 570\u2013586 (2018)","DOI":"10.1007\/978-3-030-01246-5_35"}],"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\/978-3-031-73209-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T12:23:34Z","timestamp":1744115014000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73209-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732089","9783031732096"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73209-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 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"}}]}}