{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:30:11Z","timestamp":1777995011435,"version":"3.51.4"},"publisher-location":"Cham","reference-count":89,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031546044","type":"print"},{"value":"9783031546051","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-54605-1_32","type":"book-chapter","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:43:10Z","timestamp":1709811790000},"page":"491-507","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Text-to-Feature Diffusion for\u00a0Audio-Visual Few-Shot Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3586-1703","authenticated-orcid":false,"given":"Otniel-Bogdan","family":"Mercea","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3201-360X","authenticated-orcid":false,"given":"Thomas","family":"Hummel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5807-0576","authenticated-orcid":false,"given":"A. Sophia","family":"Koepke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1432-7747","authenticated-orcid":false,"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,8]]},"reference":[{"key":"32_CR1","unstructured":"Abu-El-Haija, S., et al.: Youtube-8m: a large-scale video classification benchmark. arXiv:1609.08675 (2016)"},{"key":"32_CR2","unstructured":"Adler, J., Lunz, S.: Banach Wasserstein GAN. In: NeurIPS (2018)"},{"key":"32_CR3","doi-asserted-by":"crossref","unstructured":"Afouras, T., Asano, Y.M., Fagan, F., Vedaldi, A., Metze, F.: Self-supervised object detection from audio-visual correspondence. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01032"},{"issue":"12","key":"32_CR4","doi-asserted-by":"publisher","first-page":"8717","DOI":"10.1109\/TPAMI.2018.2889052","volume":"44","author":"T Afouras","year":"2018","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE TPAMI 44(12), 8717\u20138727 (2018)","journal-title":"IEEE TPAMI"},{"key":"32_CR5","doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: ASR is all you need: cross-modal distillation for lip reading. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Afouras, T., Owens, A., Chung, J.S., Zisserman, A.: Self-supervised learning of audio-visual objects from video. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"32_CR7","unstructured":"Alwassel, H., Mahajan, D., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. In: NeurIPS (2020)"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Objects that sound. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"32_CR9","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML (2017)"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: Soundnet: learning sound representations from unlabeled video. In: NeurIPS (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"32_CR11","unstructured":"Bishay, M., Zoumpourlis, G., Patras, I.: Tarn: Temporal attentive relation network for few-shot and zero-shot action recognition. In: BMVC (2019)"},{"key":"32_CR12","unstructured":"Blattmann, A., Rombach, R., Oktay, K., M\u00fcller, J., Ommer, B.: Semi-parametric neural image synthesis. In: NeurIPS (2022)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Bo, Y., Lu, Y., He, W.: Few-shot learning of video action recognition only based on video contents. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093481"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Boes, W., Van hamme, H.: Audiovisual transformer architectures for large-scale classification and synchronization of weakly labeled audio events. In: ACM MM (2019)","DOI":"10.1145\/3343031.3350873"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Cao, K., Ji, J., Cao, Z., Chang, C.Y., Niebles, J.C.: Few-shot video classification via temporal alignment. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01063"},{"key":"32_CR16","unstructured":"Carreira, J., et al.: Hierarchical perceiver. arXiv preprint arXiv:2202.10890 (2022)"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Chao, W.L., Changpinyo, S., Gong, B., Sha, F.: An empirical study and analysis of generalized zero-shot learning for object recognition in the wild. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46475-6_4"},{"key":"32_CR18","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Afouras, T., Nagrani, A., Vedaldi, A., Zisserman, A.: Localizing visual sounds the hard way. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01659"},{"key":"32_CR19","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: Vggsound: a large-scale audio-visual dataset. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"32_CR20","unstructured":"Chen, W.Y., Liu, Y.C., Kira, Z., Wang, Y.C.F., Huang, J.B.: A closer look at few-shot classification. arXiv:1904.04232 (2019)"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xian, Y., Koepke, A.S., Shan, Y., Akata, Z.: Distilling audio-visual knowledge by compositional contrastive learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"32_CR22","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Douze, M., Szlam, A., Hariharan, B., J\u00e9gou, H.: Low-shot learning with large-scale diffusion. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00353"},{"key":"32_CR24","unstructured":"Esser, P., Rombach, R., Blattmann, A., Ommer, B.: Imagebart: bidirectional context with multinomial diffusion for autoregressive image synthesis. In: NeurIPS (2021)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Fayek, H.M., Kumar, A.: Large scale audiovisual learning of sounds with weakly labeled data. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/78"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"32_CR27","doi-asserted-by":"crossref","unstructured":"Gan, C., Huang, D., Chen, P., Tenenbaum, J.B., Torralba, A.: Foley music: learning to generate music from videos. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"Gao, R., Grauman, K.: Co-separating sounds of visual objects. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00398"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. arXiv:1508.06576 (2015)","DOI":"10.1167\/16.12.326"},{"key":"32_CR30","unstructured":"Goldstein, S., Moses, Y.: Guitar music transcription from silent video. In: BMVC (2018)"},{"issue":"11","key":"32_CR31","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"32_CR32","doi-asserted-by":"crossref","unstructured":"Hariharan, B., Girshick, R.: Low-shot visual recognition by shrinking and hallucinating features. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.328"},{"key":"32_CR33","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: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Hershey, S., et al.: CNN architectures for large-scale audio classification. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"32_CR35","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"32_CR36","doi-asserted-by":"crossref","unstructured":"Iashin, V., Rahtu, E.: A better use of audio-visual cues: Dense video captioning with bi-modal transformer. In: BMVC (2020)","DOI":"10.1109\/CVPRW50498.2020.00487"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"32_CR38","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: ICML (2021)"},{"key":"32_CR39","unstructured":"Kang, B., et al.: Decoupling representation and classifier for long-tailed recognition. In: ICLR (2020)"},{"key":"32_CR40","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: CVPR (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Kim, S., Choi, D.W.: Better generalized few-shot learning even without base data. arXiv:2211.16095 (2022)","DOI":"10.1609\/aaai.v37i7.25999"},{"key":"32_CR42","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"32_CR43","doi-asserted-by":"crossref","unstructured":"Koepke, A.S., Wiles, O., Moses, Y., Zisserman, A.: Sight to sound: an end-to-end approach for visual piano transcription. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"32_CR44","unstructured":"Koepke, A.S., Wiles, O., Zisserman, A.: Visual pitch estimation. In: SMC (2019)"},{"key":"32_CR45","unstructured":"Korbar, B., Tran, D., Torresani, L.: Cooperative learning of audio and video models from self-supervised synchronization. In: NeurIPS (2018)"},{"key":"32_CR46","doi-asserted-by":"crossref","unstructured":"Kumar Dwivedi, S., Gupta, V., Mitra, R., Ahmed, S., Jain, A.: Protogan: towards few shot learning for action recognition. In: ICCVW (2019)","DOI":"10.1109\/ICCVW.2019.00166"},{"key":"32_CR47","unstructured":"Li, X., et al.: Learning to self-train for semi-supervised few-shot classification. In: NeurIPS (2019)"},{"key":"32_CR48","doi-asserted-by":"crossref","unstructured":"Lin, Y.B., Wang, Y.C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: ACCV (2020)","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"32_CR49","unstructured":"Liu, Y., et al.: Learning to propagate labels: transductive propagation network for few-shot learning. arXiv:1805.10002 (2018)"},{"key":"32_CR50","unstructured":"Majumder, S., Chen, C., Al-Halah, Z., Grauman, K.: Few-shot audio-visual learning of environment acoustics. In: NeurIPS (2022)"},{"key":"32_CR51","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Hummel, T., Koepke, A.S., Akata, Z.: Temporal and cross-modal attention for audio-visual zero-shot learning. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"32_CR52","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01030"},{"key":"32_CR53","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"32_CR54","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv:1411.1784 (2014)"},{"key":"32_CR55","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. In: NeurIPS (2021)"},{"key":"32_CR56","doi-asserted-by":"crossref","unstructured":"Narasimhan, M., Ginosar, S., Owens, A., Efros, A.A., Darrell, T.: Strumming to the beat: audio-conditioned contrastive video textures. arXiv:2104.02687 (2021)","DOI":"10.1109\/WACV51458.2022.00058"},{"key":"32_CR57","doi-asserted-by":"crossref","unstructured":"Narayan, S., Gupta, A., Khan, F.S., Snoek, C.G., Shao, L.: Latent embedding feedback and discriminative features for zero-shot classification. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"32_CR58","doi-asserted-by":"crossref","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"32_CR59","doi-asserted-by":"crossref","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"32_CR60","doi-asserted-by":"crossref","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Learning sight from sound: ambient sound provides supervision for visual learning. In: IJCV (2018)","DOI":"10.1007\/s11263-018-1083-5"},{"key":"32_CR61","unstructured":"Patrick, M., Asano, Y.M., Fong, R., Henriques, J.F., Zweig, G., Vedaldi, A.: Multi-modal self-supervision from generalized data transformations. In: NeurIPS (2020)"},{"key":"32_CR62","doi-asserted-by":"crossref","unstructured":"Perrett, T., Masullo, A., Burghardt, T., Mirmehdi, M., Damen, D.: Temporal-relational crosstransformers for few-shot action recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00054"},{"key":"32_CR63","doi-asserted-by":"crossref","unstructured":"Qi, H., Brown, M., Lowe, D.G.: Low-shot learning with imprinted weights. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00610"},{"key":"32_CR64","unstructured":"Ravi, S., Larochelle, H.: Optimization as a model for few-shot learning. In: ICLR (2017)"},{"key":"32_CR65","unstructured":"Recasens, A., et al.: Zorro: the masked multimodal transformer. arXiv preprint arXiv:2301.09595 (2023)"},{"key":"32_CR66","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"32_CR67","unstructured":"Roy, A., Shah, A., Shah, K., Roy, A., Chellappa, R.: Diffalign: few-shot learning using diffusion based synthesis and alignment. arXiv preprint arXiv:2212.05404 (2022)"},{"issue":"3","key":"32_CR68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3446374","volume":"54","author":"D Saxena","year":"2021","unstructured":"Saxena, D., Cao, J.: Generative adversarial networks (GANs) challenges, solutions, and future directions. ACM Comput. Surv. (CSUR) 54(3), 1\u201342 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"32_CR69","unstructured":"Snell, J., Swersky, K., Zemel, R.: Prototypical networks for few-shot learning. In: NeurIPS (2017)"},{"key":"32_CR70","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402 (2012)"},{"key":"32_CR71","unstructured":"Su, K., Liu, X., Shlizerman, E.: Multi-instrumentalist net: unsupervised generation of music from body movements. arXiv:2012.03478 (2020)"},{"key":"32_CR72","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00131"},{"key":"32_CR73","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"32_CR74","doi-asserted-by":"crossref","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"32_CR75","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"32_CR76","unstructured":"Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. In: NeurIPS (2021)"},{"key":"32_CR77","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"32_CR78","unstructured":"Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., et al.: Matching networks for one shot learning. In: NeurIPS (2016)"},{"key":"32_CR79","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhu, L., Yang, Y.: T2VLAD: global-local sequence alignment for text-video retrieval. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"32_CR80","unstructured":"Wang, Y., Chao, W.L., Weinberger, K.Q., van der Maaten, L.: Simpleshot: revisiting nearest-neighbor classification for few-shot learning. arXiv:1911.04623 (2019)"},{"key":"32_CR81","doi-asserted-by":"crossref","unstructured":"Wang, Y.X., Girshick, R., Hebert, M., Hariharan, B.: Low-shot learning from imaginary data. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00760"},{"issue":"12","key":"32_CR82","doi-asserted-by":"publisher","first-page":"8949","DOI":"10.1109\/TPAMI.2021.3120550","volume":"44","author":"Y Xian","year":"2021","unstructured":"Xian, Y., Korbar, B., Douze, M., Torresani, L., Schiele, B., Akata, Z.: Generalized few-shot video classification with video retrieval and feature generation. IEEE TPAMI 44(12), 8949\u20138961 (2021)","journal-title":"IEEE TPAMI"},{"key":"32_CR83","doi-asserted-by":"crossref","unstructured":"Xian, Y., Sharma, S., Schiele, B., Akata, Z.: F-VAEGAN-D2: a feature generating framework for any-shot learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01052"},{"key":"32_CR84","unstructured":"Xiao, F., Lee, Y.J., Grauman, K., Malik, J., Feichtenhofer, C.: Audiovisual slowfast networks for video recognition. arXiv:2001.08740 (2020)"},{"key":"32_CR85","doi-asserted-by":"crossref","unstructured":"Ye, H.J., Hu, H., Zhan, D.C., Sha, F.: Few-shot learning via embedding adaptation with set-to-set functions. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"32_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, H., Zhang, L., Qi, X., Li, H., Torr, P.H., Koniusz, P.: Few-shot action recognition with permutation-invariant attention. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"32_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, Y.K., Zhou, D.W., Ye, H.J., Zhan, D.C.: Audio-visual generalized few-shot learning with prototype-based co-adaptation. In: Proceedings of Interspeech 2022 (2022)","DOI":"10.21437\/Interspeech.2022-652"},{"key":"32_CR88","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Z., Xu, X., Luo, P., Wang, X.: Vision-infused deep audio inpainting. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00037"},{"key":"32_CR89","doi-asserted-by":"crossref","unstructured":"Zhu, L., Yang, Y.: Compound memory networks for few-shot video classification. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01234-2_46"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-54605-1_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T23:24:52Z","timestamp":1731540292000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-54605-1_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031546044","9783031546051"],"references-count":89,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-54605-1_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"8 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAGM GCPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"DAGM German Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heidelberg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"45","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dagm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dagm-gcpr.de\/year\/2023","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"76","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"53% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}