{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:43:16Z","timestamp":1781797396566,"version":"3.54.5"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733895","type":"print"},{"value":"9783031733901","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\/978-3-031-73390-1_26","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:24:01Z","timestamp":1730305441000},"page":"448-466","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Semantically Guided Representation Learning For Action Anticipation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3084-9377","authenticated-orcid":false,"given":"Anxhelo","family":"Diko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9437-6217","authenticated-orcid":false,"given":"Danilo","family":"Avola","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2991-2279","authenticated-orcid":false,"given":"Bardh","family":"Prenkaj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0437-7832","authenticated-orcid":false,"given":"Federico","family":"Fontana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9149-2175","authenticated-orcid":false,"given":"Luigi","family":"Cinque","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Abu\u00a0Farha, Y., Gall, J.: Uncertainty-aware anticipation of activities. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp.\u00a00\u20138 (2019)","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Abu\u00a0Farha, Y., Richard, A., Gall, J.: When will you do what?-Anticipating temporal occurrences of activities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5343\u20135352 (2018)","DOI":"10.1109\/CVPR.2018.00560"},{"key":"26_CR3","first-page":"24206","volume":"34","author":"H Akbari","year":"2021","unstructured":"Akbari, H., et al.: VATT: transformers for multimodal self-supervised learning from raw video, audio and text. Adv. Neural. Inf. Process. Syst. 34, 24206\u201324221 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Bokhari, S.Z., Kitani, K.M.: Long-term activity forecasting using first-person vision. In: 13th Asian Conference on Computer Vision, pp. 346\u2013360 (2017)","DOI":"10.1007\/978-3-319-54193-8_22"},{"key":"26_CR6","doi-asserted-by":"publisher","first-page":"510","DOI":"10.3758\/BF03193020","volume":"39","author":"JA Bullinaria","year":"2007","unstructured":"Bullinaria, J.A., Levy, J.P.: Extracting semantic representations from word co-occurrence statistics: a computational study. Behav. Res. Method 39, 510\u2013526 (2007)","journal-title":"Behav. Res. Method"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Damen, D., et\u00a0al.: Scaling egocentric vision: The EPIC-KITCHENS dataset. In: Proceedings of the European Conference on Computer Vision, pp. 720\u2013736 (2018)","DOI":"10.1007\/978-3-030-01225-0_44"},{"key":"26_CR8","doi-asserted-by":"publisher","unstructured":"Dessalene, E., Devaraj, C., Maynord, M., Ferm\u00fcller, C., Aloimonos, Y.: Forecasting action through contact representations from first person video. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6703\u20136714 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2021.3055233","DOI":"10.1109\/TPAMI.2021.3055233"},{"issue":"1","key":"26_CR9","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11263-021-01531-2","volume":"130","author":"D Dima","year":"2022","unstructured":"Dima, D., et al.: Rescaling egocentric vision: collection, pipeline and challenges for EPIC-KITCHENS-100. Int. J. Comput. Vis. 130(1), 33\u201355 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"26_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations, pp. 1\u201321 (2021)"},{"key":"26_CR11","doi-asserted-by":"publisher","unstructured":"Frederiksen, C.: Propositional representations in psychology. In: Int. Encyclopedia of the Social & Behavioral Sci.s, pp. 12219\u201312224. Springer (2001). https:\/\/doi.org\/10.1016\/B0-08-043076-7\/01490-X","DOI":"10.1016\/B0-08-043076-7\/01490-X"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Furnari, A., Battiato, S., Maria\u00a0Farinella, G.: Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pp. 0\u201310 (2018)","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"26_CR13","doi-asserted-by":"publisher","unstructured":"Furnari, A., Farinella, G.M.: Rolling-unrolling LSTMs for action anticipation from first-person video. IEEE Trans. on Pattern Anal. and Mach. Intell. 43(11), 4021\u20134036 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2992889","DOI":"10.1109\/TPAMI.2020.2992889"},{"key":"26_CR14","doi-asserted-by":"publisher","unstructured":"Girase, H., Agarwal, N., Choi, C., Mangalam, K.: Latency matters: real-time action forecasting transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18759\u201318769 (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.01799","DOI":"10.1109\/CVPR52729.2023.01799"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13505\u201313515 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"26_CR16","first-page":"1","volume":"30","author":"R Girdhar","year":"2017","unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognit. Adv. Neural. Inf. Process. Syst. 30, 1\u201310 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Huang, J., Li, Y., Feng, J., Wu, X., Sun, X., Ji, R.: Clover: towards a unified video-language alignment and fusion model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14856\u201314866 (2023)","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"26_CR18","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916 (2021)"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Ke, Q., Fritz, M., Schiele, B.: Time-conditioned action anticipation in one shot. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9925\u20139934 (2019)","DOI":"10.1109\/CVPR.2019.01016"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 14\u201329 (2015)","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: MViTv2: improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"26_CR22","doi-asserted-by":"publisher","first-page":"5623","DOI":"10.1109\/TIP.2023.3321462","volume":"32","author":"F Lin","year":"2023","unstructured":"Lin, F., Qiu, Z., Liu, C., Yao, T., Xie, H., Zhang, Y.: Prototypical matching networks for video object segmentation. IEEE Trans. Imag. Process. 32, 5623\u20135636 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3321462","journal-title":"IEEE Trans. Imag. Process."},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Liu, T., Lam, K.M.: A hybrid egocentric activity anticipation framework via memory-augmented recurrent and one-shot representation forecasting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13904\u201313913 (2022)","DOI":"10.1109\/CVPR52688.2022.01353"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., et\u00a0al.: Swin transformer V2: scaling up capacity and resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12009\u201312019 (2022)","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"26_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. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 638\u2013647 (2022)","DOI":"10.1145\/3503161.3547910"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Manousaki, V., Bacharidis, K., Papoutsakis, K., Argyros, A.: VLMAH: visual-linguistic modeling of action history for effective action anticipation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1917\u20131927 (2023)","DOI":"10.1109\/ICCVW60793.2023.00206"},{"key":"26_CR27","doi-asserted-by":"publisher","unstructured":"Marchetti, F., Becattini, F., Seidenari, L., Bimbo, A.D.: Multiple trajectory prediction of moving agents with memory augmented networks. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6688\u20136702 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2020.3008558","DOI":"10.1109\/TPAMI.2020.3008558"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Martinez, B., Modolo, D., Xiong, Y., Tighe, J.: Action recognition with spatial-temporal discriminative filter banks. In: International Conference on Computer Vision, pp. 5482\u20135491 (2019)","DOI":"10.1109\/ICCV.2019.00558"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: UMAP: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"26_CR30","unstructured":"Miech, A., Laptev, I., Sivic, J.: Learnable pooling with context gating for video classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshop, pp.\u00a01\u20138 (2017)"},{"key":"26_CR31","doi-asserted-by":"publisher","unstructured":"Osman, N., Camporese, G., Coscia, P., Ballan, L.: SlowFast rolling-unrolling LSTMs for action anticipation in egocentric videos. In: IEEE\/CVF International Conference on Computer Vision Workshops, pp. 3430\u20133438 (2021). https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00383","DOI":"10.1109\/ICCVW54120.2021.00383"},{"key":"26_CR32","doi-asserted-by":"publisher","unstructured":"Qi, Z., Wang, S., Su, C., Su, L., Huang, Q., Tian, Q.: Self-regulated learning for egocentric video activity anticipation. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 6715\u20136730 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2021.3059923","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"26_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Ramanathan, V., et al.: Learning semantic relationships for better action retrieval in images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1100\u20131109 (2015)","DOI":"10.1109\/CVPR.2015.7298713"},{"key":"26_CR35","doi-asserted-by":"publisher","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp. 3980\u20133990 (2019). https:\/\/doi.org\/10.18653\/V1\/D19-1410","DOI":"10.18653\/V1\/D19-1410"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Richard, A., Kuehne, H., Gall, J.: Weakly supervised action learning with RNN based fine-to-coarse modeling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 754\u2013763 (2017)","DOI":"10.1109\/CVPR.2017.140"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Roy, D., Fernando, B.: Action anticipation using latent goal learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2745\u20132753 (2022)","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"26_CR38","doi-asserted-by":"crossref","unstructured":"Roy, D., Rajendiran, R., Fernando, B.: Interaction region visual transformer for egocentric action anticipation. In: Winter Conference on Applications of Computer Vision, pp. 6740\u20136750 (2024)","DOI":"10.1109\/WACV57701.2024.00660"},{"key":"26_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1007\/978-3-030-58517-4_10","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Sener","year":"2020","unstructured":"Sener, F., Singhania, D., Yao, A.: Temporal aggregate representations for long-range video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 154\u2013171. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_10"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Fatahalian, K., Efros, A.A.: KrishnaCam: using a longitudinal, single-person, egocentric dataset for scene understanding tasks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp.\u00a01\u20139 (2016)","DOI":"10.1109\/WACV.2016.7477717"},{"key":"26_CR41","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"26_CR42","doi-asserted-by":"publisher","unstructured":"Somin, W., Silvio, A., Byron, C.W.: Revisiting relation extraction in the era of large language models. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, pp. 15566\u201315589 (2023). https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.868","DOI":"10.18653\/V1\/2023.ACL-LONG.868"},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Soran, B., Farhadi, A., Shapiro, L.: Generating notifications for missing actions: Don\u2019t forget to turn the lights off! In: Proceedings of the IEEE\/CVF IEEE International Conference on Computer Vision, pp. 4669\u20134677 (2015)","DOI":"10.1109\/ICCV.2015.530"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Stein, S., McKenna, S.J.: Combining embedded accelerometers with computer vision for recognizing food preparation activities. In: Proceedings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp. 729\u2013738 (2013)","DOI":"10.1145\/2493432.2493482"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Sung, F., Yang, Y., Zhang, L., Xiang, T., Torr, P.H., Hospedales, T.M.: Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208 (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"26_CR46","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030, pp. 1\u201311 (2017)"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Anticipating visual representations from unlabeled video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 98\u2013106 (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"26_CR48","doi-asserted-by":"publisher","unstructured":"Wang, D., Liu, H., Wang, N., Wang, Y., Wang, H., McLoone, S.: SEEM: a sequence entropy energy-based model for pedestrian trajectory all-then-one prediction. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 1070\u20131086 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3147639","DOI":"10.1109\/TPAMI.2022.3147639"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. In: Proceedings of the 57th Conference on Association for Computational Linguistics, pp. 1\u201313 (2019)","DOI":"10.18653\/v1\/P19-1176"},{"key":"26_CR50","unstructured":"Wilson, S., Mihalcea, R.: Measuring semantic relations between human activities. In: International Joint Conference on Natural Language Processing, pp. 664\u2013673 (2017)"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Wu, C.Y., et al.: MeMViT: memory-augmented multiscale vision transformer for efficient long-term video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13587\u201313597 (2022)","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"26_CR52","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1109\/TIP.2020.3040521","volume":"30","author":"Y Wu","year":"2020","unstructured":"Wu, Y., Zhu, L., Wang, X., Yang, Y., Wu, F.: Learning to anticipate egocentric actions by imagination. IEEE Trans. Imag. Process. 30, 1143\u20131152 (2020)","journal-title":"IEEE Trans. Imag. Process."},{"key":"26_CR53","doi-asserted-by":"publisher","unstructured":"Xu, X., Li, Y.L., Lu, C.: Learning to anticipate future with dynamic context removal. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12724\u201312734 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01240","DOI":"10.1109\/CVPR52688.2022.01240"},{"key":"26_CR54","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: LiT: Zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"26_CR55","doi-asserted-by":"publisher","unstructured":"Zhang, M., Ma, K.T., Lim, J.H., Zhao, Q., Feng, J.: Deep future gaze: gaze anticipation on egocentric videos using adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3539\u20133548 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.377","DOI":"10.1109\/CVPR.2017.377"},{"key":"26_CR56","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Schneider, D., Voit, M., Stiefelhagen, R., Beyerer, J.: Anticipative feature fusion transformer for multi-modal action anticipation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6068\u20136077 (2023)","DOI":"10.1109\/WACV56688.2023.00601"}],"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\/978-3-031-73390-1_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T16:38:33Z","timestamp":1730306313000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73390-1_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733895","9783031733901"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73390-1_26","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"}}]}}