{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:02:49Z","timestamp":1764784969114,"version":"3.40.3"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031198328"},{"type":"electronic","value":"9783031198335"}],"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\/978-3-031-19833-5_39","type":"book-chapter","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T00:40:30Z","timestamp":1667522430000},"page":"671-690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Automatic Dense Annotation of\u00a0Large-Vocabulary Sign Language Videos"],"prefix":"10.1007","author":[{"given":"Liliane","family":"Momeni","sequence":"first","affiliation":[]},{"given":"Hannah","family":"Bull","sequence":"additional","affiliation":[]},{"given":"K. R.","family":"Prajwal","sequence":"additional","affiliation":[]},{"given":"Samuel","family":"Albanie","sequence":"additional","affiliation":[]},{"given":"G\u00fcl","family":"Varol","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,4]]},"reference":[{"key":"39_CR1","unstructured":"Albanie, S., et al.: BOBSL: BBC-Oxford British Sign Language Dataset. arXiv preprint arXiv:2111.03635 (2021)"},{"key":"39_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/978-3-030-58621-8_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Albanie","year":"2020","unstructured":"Albanie, S., et al.: BSL-1K: scaling up co-articulated sign language recognition using mouthing cues. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 35\u201353. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_3"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Bauer, B., Hienz, H.: Relevant features for video-based continuous sign language recognition. In: Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), pp. 440\u2013445. IEEE (2000)","DOI":"10.1109\/AFGR.2000.840672"},{"issue":"12","key":"39_CR4","doi-asserted-by":"publisher","first-page":"310","DOI":"10.3390\/a13120310","volume":"13","author":"V Belissen","year":"2020","unstructured":"Belissen, V., Braffort, A., Gouiff\u00e8s, M.: Experimenting the automatic recognition of non-conventionalized units in sign language. Algorithms 13(12), 310 (2020)","journal-title":"Algorithms"},{"key":"39_CR5","volume-title":"The Hands are the Head of the Mouth. The Mouth as Articulator in Sign Languages","author":"P Boyes Braem","year":"2001","unstructured":"Boyes Braem, P., Sutton-Spence, R.: The Hands are the Head of the Mouth. The Mouth as Articulator in Sign Languages. Signum Press, Hamburg (2001)"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Bragg, D., et al.: Sign language recognition, generation, and translation: an interdisciplinary perspective. In: ACM SIGACCESS (2019)","DOI":"10.1145\/3308561.3353774"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"Buehler, P., Zisserman, A., Everingham, M.: Learning sign language by watching tv (using weakly aligned subtitles). In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2961\u20132968. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206523"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Bull, H., Afouras, T., Varol, G., Albanie, S., Momeni, L., Zisserman, A.: Aligning subtitles in sign language videos. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01135"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Camgoz, N., et al.: Content4all open research sign language translation datasets. arXiv:abs\/2105.02351 (2021)","DOI":"10.1109\/FG52635.2021.9667087"},{"key":"39_CR10","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"39_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/978-3-030-66823-5_18","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"NC Camgoz","year":"2020","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Multi-channel transformers for multi-articulatory sign language translation. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12538, pp. 301\u2013319. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66823-5_18"},{"key":"39_CR12","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: joint end-to-end sign language recognition and translation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)"},{"issue":"5","key":"39_CR13","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1016\/0141-5425(92)90088-3","volume":"14","author":"C Charayaphan","year":"1992","unstructured":"Charayaphan, C., Marble, A.: Image processing system for interpreting motion in American sign language. J. Biomed. Eng. 14(5), 419\u2013425 (1992)","journal-title":"J. Biomed. Eng."},{"key":"39_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1007\/978-3-030-58586-0_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"KL Cheng","year":"2020","unstructured":"Cheng, K.L., Yang, Z., Chen, Q., Tai, Y.-W.: Fully convolutional networks for continuous sign language recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12369, pp. 697\u2013714. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_41"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Cho, M., Kwak, S., Schmid, C., Ponce, J.: Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1201\u20131210 (2015)","DOI":"10.1109\/CVPR.2015.7298724"},{"key":"39_CR16","doi-asserted-by":"crossref","unstructured":"Cooper, H., Bowden, R.: Learning signs from subtitles: a weakly supervised approach to sign language recognition. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2568\u20132574. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206647"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Cui, R., Liu, H., Zhang, C.: Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7361\u20137369 (2017)","DOI":"10.1109\/CVPR.2017.175"},{"key":"39_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/978-3-642-15561-1_33","volume-title":"Computer Vision \u2013 ECCV 2010","author":"T Deselaers","year":"2010","unstructured":"Deselaers, T., Alexe, B., Ferrari, V.: Localizing objects while learning their appearance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 452\u2013466. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_33"},{"key":"39_CR19","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"39_CR20","unstructured":"Farhadi, A., Forsyth, D.: Aligning ASL for statistical translation using a discriminative word model. In: CVPR (2006)"},{"key":"39_CR21","unstructured":"Feinerer, I., Hornik, K.: wordnet: WordNet Interface (2020). https:\/\/CRAN.R-project.org\/package=wordnet, r package version 0.1-15"},{"key":"39_CR22","doi-asserted-by":"crossref","unstructured":"Gokberk Cinbis, R., Verbeek, J., Schmid, C.: Multi-fold mil training for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2409\u20132416 (2014)","DOI":"10.1109\/CVPR.2014.309"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhao, W., Zhou, W., Wang, Y., Li, H.: Signbert: pre-training of hand-model-aware representation for sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11087\u201311096 (2021)","DOI":"10.1109\/ICCV48922.2021.01090"},{"issue":"3","key":"39_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3436754","volume":"17","author":"H Hu","year":"2021","unstructured":"Hu, H., Zhou, W., Pu, J., Li, H.: Global-local enhancement network for NMF-aware sign language recognition. ACM Trans. Multimedia Comput. Commun. Appl. TOMM 17(3), 1\u201319 (2021)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. TOMM"},{"issue":"9","key":"39_CR25","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/TCSVT.2018.2870740","volume":"29","author":"J Huang","year":"2018","unstructured":"Huang, J., Zhou, W., Li, H., Li, W.: Attention-based 3D-CNNs for large-vocabulary sign language recognition. IEEE Trans. Circuits Syst. Video Technol. 29(9), 2822\u20132832 (2018)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, T., Camgoz, N.C., Bowden, R.: Looking for the signs: identifying isolated sign instances in continuous video footage. In: IEEE International Conference on Automatic Face and Gesture Recognition (2021)","DOI":"10.1109\/FG52635.2021.9667037"},{"key":"39_CR27","doi-asserted-by":"crossref","unstructured":"Jin, T., Zhao, Z.: Contrastive disentangled meta-learning for signer-independent sign language translation. In: Proceedings of the 29th ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475456"},{"issue":"2","key":"39_CR28","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1093\/deafed\/enr036","volume":"17","author":"T Johnston","year":"2012","unstructured":"Johnston, T.: Lexical frequency in sign languages. J. Deaf Stud. Deaf Educ. 17(2), 163\u2013193 (2012)","journal-title":"J. Deaf Stud. Deaf Educ."},{"key":"39_CR29","doi-asserted-by":"crossref","unstructured":"Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1943\u20131950. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5539868"},{"key":"39_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-319-10599-4_17","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Joulin","year":"2014","unstructured":"Joulin, A., Tang, K., Fei-Fei, L.: Efficient image and video co-localization with Frank-Wolfe algorithm. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 253\u2013268. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_17"},{"key":"39_CR31","unstructured":"Joze, H.R.V., Koller, O.: MS-ASL: a large-scale data set and benchmark for understanding American sign language. arXiv preprint arXiv:1812.01053 (2018)"},{"issue":"2","key":"39_CR32","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1109\/TSMCB.2010.2065802","volume":"41","author":"D Kelly","year":"2010","unstructured":"Kelly, D., Mc Donald, J., Markham, C.: Weakly supervised training of a sign language recognition system using multiple instance learning density matrices. IEEE Trans. Syst. Man Cybern. Part B (Cybernetics) 41(2), 526\u2013541 (2010)","journal-title":"IEEE Trans. Syst. Man Cybern. Part B (Cybernetics)"},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Kim, G., Xing, E.P., Fei-Fei, L., Kanade, T.: Distributed cosegmentation via submodular optimization on anisotropic diffusion. In: 2011 International Conference on Computer Vision, pp. 169\u2013176. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126239"},{"key":"39_CR34","unstructured":"Koller, O.: Quantitative survey of the state of the art in sign language recognition. arXiv:abs\/2008.09918 (2020)"},{"key":"39_CR35","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.cviu.2015.09.013","volume":"141","author":"O Koller","year":"2015","unstructured":"Koller, O., Forster, J., Ney, H.: Continuous sign language recognition: towards large vocabulary statistical recognition systems handling multiple signers. Comput. Vis. Image Underst. 141, 108\u2013125 (2015)","journal-title":"Comput. Vis. Image Underst."},{"key":"39_CR36","doi-asserted-by":"crossref","unstructured":"Koller, O., Ney, H., Bowden, R.: Deep hand: How to train a CNN on 1 million hand images when your data is continuous and weakly labelled. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3793\u20133802 (2016)","DOI":"10.1109\/CVPR.2016.412"},{"key":"39_CR37","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, S., Ney, H.: Re-sign: re-aligned end-to-end sequence modelling with deep recurrent CNN-HMMs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4297\u20134305 (2017)","DOI":"10.1109\/CVPR.2017.364"},{"key":"39_CR38","unstructured":"Lee, D.H., et al.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol. 3, p. 896 (2013)"},{"key":"39_CR39","doi-asserted-by":"crossref","unstructured":"Li, D., Rodriguez, C., Yu, X., Li, H.: Word-level deep sign language recognition from video: a new large-scale dataset and methods comparison. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"39_CR40","unstructured":"Li, D., et al.: Transcribing natural languages for the deaf via neural editing programs. arXiv preprint arXiv:2112.09600 (2021)"},{"key":"39_CR41","unstructured":"Li, D., et al.: Tspnet: hierarchical feature learning via temporal semantic pyramid for sign language translation. arXiv preprint arXiv:2010.05468 (2020)"},{"key":"39_CR42","doi-asserted-by":"crossref","unstructured":"Li, D., Yu, X., Xu, C., Petersson, L., Li, H.: Transferring cross-domain knowledge for video sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6205\u20136214 (2020)","DOI":"10.1109\/CVPR42600.2020.00624"},{"key":"39_CR43","unstructured":"Momeni, L., Afouras, T., Stafylakis, T., Albanie, S., Zisserman, A.: Seeing wake words: audio-visual keyword spotting. BMVC (2020)"},{"key":"39_CR44","doi-asserted-by":"crossref","unstructured":"Momeni, L., Varol, G., Albanie, S., Afouras, T., Zisserman, A.: Watch, read and lookup: learning to spot signs from multiple supervisors. In: ACCV (2020)","DOI":"10.1007\/978-3-030-69544-6_18"},{"key":"39_CR45","unstructured":"Moryossef, A., Yin, K., Neubig, G., Goldberg, Y.: Data augmentation for sign language gloss translation. In: MTSUMMIT (2021)"},{"key":"39_CR46","doi-asserted-by":"crossref","unstructured":"Nguyen, M.H., Torresani, L., De La Torre, F., Rother, C.: Weakly supervised discriminative localization and classification: a joint learning process. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1925\u20131932. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459426"},{"key":"39_CR47","doi-asserted-by":"crossref","unstructured":"Ong, E.J., Cooper, H., Pugeault, N., Bowden, R.: Sign language recognition using sequential pattern trees. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2200\u20132207. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247928"},{"key":"39_CR48","doi-asserted-by":"crossref","unstructured":"Ong, E.J., Koller, O., Pugeault, N., Bowden, R.: Sign spotting using hierarchical sequential patterns with temporal intervals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1923\u20131930 (2014)","DOI":"10.1109\/CVPR.2014.248"},{"key":"39_CR49","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: GloVe: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"39_CR50","doi-asserted-by":"crossref","unstructured":"Pfister, T., Charles, J., Zisserman, A.: Large-scale learning of sign language by watching tv (using co-occurrences). In: BMVC (2013)","DOI":"10.5244\/C.27.20"},{"key":"39_CR51","unstructured":"Prajwal, K., Momeni, L., Afouras, T., Zisserman, A.: Visual keyword spotting with attention. In: BMVC (2021)"},{"key":"39_CR52","doi-asserted-by":"crossref","unstructured":"Renz, K., Stache, N.C., Fox, N., Varol, G., Albanie, S.: Sign segmentation with changepoint-modulated pseudo-labelling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3403\u20133412 (2021)","DOI":"10.1109\/CVPRW53098.2021.00379"},{"key":"39_CR53","doi-asserted-by":"crossref","unstructured":"Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), vol. 1, pp. 993\u20131000. IEEE (2006)","DOI":"10.1109\/CVPR.2006.91"},{"key":"39_CR54","doi-asserted-by":"crossref","unstructured":"Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1939\u20131946 (2013)","DOI":"10.1109\/CVPR.2013.253"},{"key":"39_CR55","doi-asserted-by":"crossref","unstructured":"Shi, Z., Hospedales, T.M., Xiang, T.: Bayesian joint topic modelling for weakly supervised object localisation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2984\u20132991 (2013)","DOI":"10.1109\/ICCV.2013.371"},{"key":"39_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-030-01225-0_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Stafylakis","year":"2018","unstructured":"Stafylakis, T., Tzimiropoulos, G.: Zero-shot keyword spotting for visual speech recognition in-the-wild. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 536\u2013552. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_32"},{"key":"39_CR57","unstructured":"Starner, T.E.: Visual recognition of American sign language using hidden Markov models. Technical report, Massachusetts Inst Of Tech Cambridge Dept Of Brain And Cognitive Sciences (1995)"},{"key":"39_CR58","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139167048","volume-title":"The Linguistics of British Sign Language: An Introduction","author":"R Sutton-Spence","year":"1999","unstructured":"Sutton-Spence, R., Woll, B.: The Linguistics of British Sign Language: An Introduction. Cambridge University Press, Cambridge (1999)"},{"issue":"4","key":"39_CR59","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/0031-3203(88)90048-9","volume":"21","author":"S Tamura","year":"1988","unstructured":"Tamura, S., Kawasaki, S.: Recognition of sign language motion images. Pattern Recogn. 21(4), 343\u2013353 (1988)","journal-title":"Pattern Recogn."},{"key":"39_CR60","doi-asserted-by":"crossref","unstructured":"Tang, K., Joulin, A., Li, L.J., Fei-Fei, L.: Co-localization in real-world images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1464\u20131471 (2014)","DOI":"10.1109\/CVPR.2014.190"},{"key":"39_CR61","doi-asserted-by":"crossref","unstructured":"Varol, G., Momeni, L., Albanie, S., Afouras, T., Zisserman, A.: Read and attend: temporal localisation in sign language videos. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01658"},{"key":"39_CR62","unstructured":"Viitaniemi, V., Jantunen, T., Savolainen, L., Karppa, M., Laaksonen, J.: S-pot-a benchmark in spotting signs within continuous signing. In: Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC 2014), ISBN 978-2-9517408-8-4. European Language Resources Association (LREC) (2014)"},{"key":"39_CR63","unstructured":"Vo, V.H., Sizikova, E., Schmid, C., P\u00e9rez, P., Ponce, J.: Large-scale unsupervised object discovery. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"39_CR64","doi-asserted-by":"crossref","unstructured":"Vogler, C., Metaxas, D.: Adapting hidden Markov models for ASL recognition by using three-dimensional computer vision methods. In: 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, vol. 1, pp. 156\u2013161. IEEE (1997)","DOI":"10.1109\/ICSMC.1997.625741"},{"key":"39_CR65","doi-asserted-by":"crossref","unstructured":"Vogler, C., Metaxas, D.: ASL recognition based on a coupling between HMMS and 3D motion analysis. In: Sixth International Conference on Computer Vision (IEEE Cat. No. 98CH36271), pp. 363\u2013369. IEEE (1998)","DOI":"10.1109\/ICCV.1998.710744"},{"key":"39_CR66","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-319-10599-4_28","volume-title":"Computer Vision \u2013 ECCV 2014","author":"C Wang","year":"2014","unstructured":"Wang, C., Ren, W., Huang, K., Tan, T.: Weakly supervised object localization with latent category learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 431\u2013445. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_28"},{"issue":"7","key":"39_CR67","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1109\/TPAMI.2008.172","volume":"31","author":"HD Yang","year":"2008","unstructured":"Yang, H.D., Sclaroff, S., Lee, S.W.: Sign language spotting with a threshold model based on conditional random fields. IEEE Trans. Pattern Anal. Mach. Intell. 31(7), 1264\u20131277 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"39_CR68","doi-asserted-by":"crossref","unstructured":"Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: 33rd Annual Meeting of the Association for Computational Linguistics, pp. 189\u2013196 (1995)","DOI":"10.3115\/981658.981684"},{"key":"39_CR69","doi-asserted-by":"crossref","unstructured":"Yin, K., Read, J.: Better sign language translation with STMC-transformer. In: COLING (2020)","DOI":"10.18653\/v1\/2020.coling-main.525"},{"key":"39_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, J., Zhou, W., Li, H.: A threshold-based HMM-DTW approach for continuous sign language recognition. In: Proceedings of International Conference on Internet Multimedia Computing and Service, pp. 237\u2013240 (2014)","DOI":"10.1145\/2632856.2632931"},{"key":"39_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Qi, W., Pu, J., Li, H.: Improving sign language translation with monolingual data by sign back-translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"39_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for continuous sign language recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"39_CR73","doi-asserted-by":"publisher","first-page":"161669","DOI":"10.1109\/ACCESS.2021.3132668","volume":"9","author":"Z Zhou","year":"2021","unstructured":"Zhou, Z., Tam, V.W., Lam, E.Y.: SIGNBERT: a Bert-based deep learning framework for continuous sign language recognition. IEEE Access 9, 161669\u2013161682 (2021)","journal-title":"IEEE Access"}],"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\/978-3-031-19833-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T06:27:16Z","timestamp":1728282436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19833-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198328","9783031198335"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19833-5_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"4 November 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)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}