{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:27:24Z","timestamp":1784215644292,"version":"3.55.0"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200434","type":"print"},{"value":"9783031200441","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20044-1_28","type":"book-chapter","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T23:12:10Z","timestamp":1666221130000},"page":"488-505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["Temporal and\u00a0Cross-modal Attention for\u00a0Audio-Visual Zero-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":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3201-360X","authenticated-orcid":false,"given":"Thomas","family":"Hummel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5807-0576","authenticated-orcid":false,"given":"A. Sophia","family":"Koepke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1432-7747","authenticated-orcid":false,"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,20]]},"reference":[{"key":"28_CR1","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"},{"key":"28_CR2","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE TPAMI (2018)"},{"key":"28_CR3","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":"28_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58523-5_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Afouras","year":"2020","unstructured":"Afouras, T., Owens, A., Chung, J.S., Zisserman, A.: Self-supervised learning of audio-visual objects from video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 208\u2013224. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_13"},{"key":"28_CR5","doi-asserted-by":"crossref","unstructured":"Akata, Z., Perronnin, F., Harchaoui, Z., Schmid, C.: Label-embedding for image classification. IEEE TPAMI (2015)","DOI":"10.1109\/TPAMI.2015.2487986"},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Akata, Z., Reed, S., Walter, D., Lee, H., Schiele, B.: Evaluation of output embeddings for fine-grained image classification. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298911"},{"key":"28_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":"28_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"28_CR9","unstructured":"Asano, Y., Patrick, M., Rupprecht, C., Vedaldi, A.: Labelling unlabelled videos from scratch with multi-modal self-supervision. In: NeurIPS (2020)"},{"key":"28_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":"28_CR11","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"28_CR12","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":"28_CR13","doi-asserted-by":"crossref","unstructured":"Brattoli, B., Tighe, J., Zhdanov, F., Perona, P., Chalupka, K.: Rethinking zero-shot video classification: End-to-end training for realistic applications. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"28_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-319-46475-6_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W-L Chao","year":"2016","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: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 52\u201368. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_4"},{"key":"28_CR15","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":"28_CR16","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":"28_CR17","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: ACL (2019)"},{"key":"28_CR18","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"28_CR20","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":"28_CR21","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: NeurIPS (2013)"},{"key":"28_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"key":"28_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1007\/978-3-030-58621-8_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Gan","year":"2020","unstructured":"Gan, C., Huang, D., Chen, P., Tenenbaum, J.B., Torralba, A.: Foley music: learning to generate music from videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 758\u2013775. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_44"},{"key":"28_CR24","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":"28_CR25","unstructured":"Goldstein, S., Moses, Y.: Guitar music transcription from silent video. In: BMVC (2018)"},{"key":"28_CR26","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415 (2016)"},{"key":"28_CR27","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":"28_CR28","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":"28_CR29","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"28_CR30","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: ICML (2021)"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Jamaludin, A., Chung, J.S., Zisserman, A.: You said that?: synthesising talking faces from audio. In: IJCV (2019)","DOI":"10.1007\/s11263-019-01150-y"},{"key":"28_CR32","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":"28_CR33","unstructured":"Kerrigan, A., Duarte, K., Rawat, Y., Shah, M.: Reformulating zero-shot action recognition for multi-label actions. In: NeurIPS (2021)"},{"key":"28_CR34","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"28_CR35","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":"28_CR36","unstructured":"Koepke, A.S., Wiles, O., Zisserman, A.: Visual pitch estimation. In: SMC (2019)"},{"key":"28_CR37","unstructured":"Korbar, B., Tran, D., Torresani, L.: Cooperative learning of audio and video models from self-supervised synchronization. In: NeurIPS (2018)"},{"key":"28_CR38","doi-asserted-by":"crossref","unstructured":"Li, G., Duan, N., Fang, Y., Gong, M., Jiang, D.: Unicoder-VL: a universal encoder for vision and language by cross-modal pre-training. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"28_CR39","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Lin, C.C., Lin, K., Wang, L., Liu, Z., Li, L.: Cross-modal representation learning for zero-shot action recognition. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01935"},{"key":"28_CR41","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":"28_CR42","doi-asserted-by":"crossref","unstructured":"Liu, S., Fan, H., Qian, S., Chen, Y., Ding, W., Wang, Z.: Hit: Hierarchical transformer with momentum contrast for video-text retrieval. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Y., Guo, J., Cai, D., He, X.: Attribute attention for semantic disambiguation in zero-shot learning. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00680"},{"key":"28_CR44","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: NeurIPS (2019)"},{"key":"28_CR45","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. In: JMLR (2008)"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Mazumder, P., Singh, P., Parida, K.K., Namboodiri, V.P.: AVGZSLNet: audio-visual generalized zero-shot learning by reconstructing label features from multi-modal embeddings. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"28_CR47","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":"28_CR48","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"28_CR49","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)"},{"key":"28_CR50","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 preprint arXiv:2104.02687 (2021)","DOI":"10.1109\/WACV51458.2022.00058"},{"key":"28_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/978-3-030-58542-6_29","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Narayan","year":"2020","unstructured":"Narayan, S., Gupta, A., Khan, F.S., Snoek, C.G.M., Shao, L.: Latent embedding feedback and discriminative features for zero-shot classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 479\u2013495. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_29"},{"key":"28_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"issue":"10","key":"28_CR53","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1007\/s11263-018-1083-5","volume":"126","author":"A Owens","year":"2018","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Learning sight from sound: ambient sound provides supervision for visual learning. Int. J. Comput. Vis. 126(10), 1120\u20131137 (2018). https:\/\/doi.org\/10.1007\/s11263-018-1083-5","journal-title":"Int. J. Comput. Vis."},{"key":"28_CR54","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":"28_CR55","doi-asserted-by":"crossref","unstructured":"Parida, K., Matiyali, N., Guha, T., Sharma, G.: Coordinated joint multimodal embeddings for generalized audio-visual zero-shot classification and retrieval of videos. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"28_CR56","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":"28_CR57","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners. In: OpenAI blog (2019)"},{"key":"28_CR58","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. In: JMLR (2014)"},{"key":"28_CR59","unstructured":"Su, K., Liu, X., Shlizerman, E.: Multi-instrumentalist net: unsupervised generation of music from body movements. arXiv preprint arXiv:2012.03478 (2020)"},{"key":"28_CR60","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: VL-BERT: pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"28_CR61","unstructured":"Sun, C., Baradel, F., Murphy, K., Schmid, C.: Learning video representations using contrastive bidirectional transformer. arXiv preprint arXiv:1906.05743 (2019)"},{"key":"28_CR62","doi-asserted-by":"crossref","unstructured":"Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00756"},{"key":"28_CR63","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: learning cross-modality encoder representations from transformers. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"28_CR64","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"28_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"},{"key":"28_CR66","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":"28_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"28_CR68","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"28_CR69","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":"28_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1007\/978-3-030-01261-8_41","volume-title":"Computer Vision \u2013 ECCV 2018","author":"O Wiles","year":"2018","unstructured":"Wiles, O., Koepke, A.S., Zisserman, A.: X2Face: a network for controlling face generation using images, audio, and pose codes. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 690\u2013706. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_41"},{"key":"28_CR71","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE TPAMI (2018)","DOI":"10.1109\/CVPR.2017.328"},{"key":"28_CR72","doi-asserted-by":"crossref","unstructured":"Xian, Y., Lorenz, T., Schiele, B., Akata, Z.: Feature generating networks for zero-shot learning. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00581"},{"key":"28_CR73","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":"28_CR74","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"28_CR75","doi-asserted-by":"crossref","unstructured":"Xie, G.S., et al.: Attentive region embedding network for zero-shot learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00961"},{"key":"28_CR76","unstructured":"Xu, W., Xian, Y., Wang, J., Schiele, B., Akata, Z.: Attribute prototype network for zero-shot learning. In: NeurIPS (2020)"},{"key":"28_CR77","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":"28_CR78","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Xie, J., Liu, B., Elgammal, A.: Learning feature-to-feature translator by alternating back-propagation for generative zero-shot learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00994"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20044-1_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T04:31:58Z","timestamp":1728189118000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20044-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200434","9783031200441"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20044-1_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"20 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}