{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:33:21Z","timestamp":1766428401899,"version":"3.40.4"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T00:00:00Z","timestamp":1740960000000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00530-025-01695-8","type":"journal-article","created":{"date-parts":[[2025,3,3]],"date-time":"2025-03-03T15:07:05Z","timestamp":1741014425000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking the temporal downsampling paradigm for continuous sign language recognition"],"prefix":"10.1007","volume":"31","author":[{"given":"Caifeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,3]]},"reference":[{"unstructured":"LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., Jackel, L.: Handwritten digit recognition with a back-propagation network. Adv. Neural Inf. Process. Syst. 2 (1989)","key":"1695_CR1"},{"doi-asserted-by":"crossref","unstructured":"Saeedan, F., Weber, N., Goesele, M., Roth, S.: Detail-preserving pooling in deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 9108\u20139116 (2018)","key":"1695_CR2","DOI":"10.1109\/CVPR.2018.00949"},{"unstructured":"Zhao, J., Snoek, C.G.: Liftpool: Bidirectional convnet pooling. arXiv preprint arXiv:2104.00996 (2021)","key":"1695_CR3"},{"doi-asserted-by":"crossref","unstructured":"Stergiou, A., Poppe, R., Kalliatakis, G.: Refining activation downsampling with softpool. arXiv preprint arXiv:2101.00440 (2021)","key":"1695_CR4","DOI":"10.1109\/ICCV48922.2021.01019"},{"doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, O., Ney, H., Bowden, R.: Deep sign: Hybrid cnn-hmm for continuous sign language recognition. In: Proceedings of the British Machine Vision Conference 2016 (2016)","key":"1695_CR5","DOI":"10.5244\/C.30.136"},{"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: CVPR (2017)","key":"1695_CR6","DOI":"10.1109\/CVPR.2017.364"},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376 (2006)","key":"1695_CR7","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"crossref","unstructured":"Pu, J., Zhou, W., Li, H.: Iterative alignment network for continuous sign language recognition. In: CVPR (2019)","key":"1695_CR8","DOI":"10.1109\/CVPR.2019.00429"},{"doi-asserted-by":"crossref","unstructured":"Pu, J., Zhou, W., Hu, H., Li, H.: Boosting continuous sign language recognition via cross modality augmentation. In: ACM MM (2020)","key":"1695_CR9","DOI":"10.1145\/3394171.3413931"},{"doi-asserted-by":"crossref","unstructured":"Cheng, K.L., Yang, Z., Chen, Q., Tai, Y.-W.: Fully convolutional networks for continuous sign language recognition. In: ECCV (2020)","key":"1695_CR10","DOI":"10.1007\/978-3-030-58586-0_41"},{"issue":"7","key":"1695_CR11","first-page":"1880","volume":"21","author":"R Cui","year":"2019","unstructured":"Cui, R., Liu, H., Zhang, C.: A deep neural framework for continuous sign language recognition by iterative training. TMM 21(7), 1880\u20131891 (2019)","journal-title":"TMM"},{"doi-asserted-by":"crossref","unstructured":"Niu, Z., Mak, B.: Stochastic fine-grained labeling of multi-state sign glosses for continuous sign language recognition. In: ECCV (2020)","key":"1695_CR12","DOI":"10.1007\/978-3-030-58517-4_11"},{"doi-asserted-by":"crossref","unstructured":"Min, Y., Hao, A., Chai, X., Chen, X.: Visual alignment constraint for continuous sign language recognition. In: ICCV (2021)","key":"1695_CR13","DOI":"10.1109\/ICCV48922.2021.01134"},{"doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Temporal lift pooling for continuous sign language recognition. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV, pp. 511\u2013527 (2022). Springer","key":"1695_CR14","DOI":"10.1007\/978-3-031-19833-5_30"},{"doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Self-emphasizing network for continuous sign language recognition. In: Thirty-seventh AAAI Conference on Artificial Intelligence (2023)","key":"1695_CR15","DOI":"10.1609\/aaai.v37i1.25164"},{"doi-asserted-by":"crossref","unstructured":"Zheng, J., Wang, Y., Tan, C., Li, S., Wang, G., Xia, J., Chen, Y., Li, S.Z.: Cvt-slr: Contrastive visual-textual transformation for sign language recognition with variational alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23141\u201323150 (2023)","key":"1695_CR16","DOI":"10.1109\/CVPR52729.2023.02216"},{"doi-asserted-by":"crossref","unstructured":"Guo, L., Xue, W., Guo, Q., Liu, B., Zhang, K., Yuan, T., Chen, S.: Distilling cross-temporal contexts for continuous sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10771\u201310780 (2023)","key":"1695_CR17","DOI":"10.1109\/CVPR52729.2023.01037"},{"unstructured":"Boureau, Y.-L., Ponce, J., LeCun, Y.: A theoretical analysis of feature pooling in visual recognition. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 111\u2013118 (2010)","key":"1695_CR18"},{"doi-asserted-by":"crossref","unstructured":"Yu, D., Wang, H., Chen, P., Wei, Z.: Mixed pooling for convolutional neural networks. In: International Conference on Rough Sets and Knowledge Technology, pp. 364\u2013375 (2014). Springer","key":"1695_CR19","DOI":"10.1007\/978-3-319-11740-9_34"},{"doi-asserted-by":"crossref","unstructured":"Gulcehre, C., Cho, K., Pascanu, R., Bengio, Y.: Learned-norm pooling for deep feedforward and recurrent neural networks. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 530\u2013546 (2014). Springer","key":"1695_CR20","DOI":"10.1007\/978-3-662-44848-9_34"},{"unstructured":"Zeiler, M.D., Fergus, R.: Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557 (2013)","key":"1695_CR21"},{"doi-asserted-by":"crossref","unstructured":"Zhai, S., Wu, H., Kumar, A., Cheng, Y., Lu, Y., Zhang, Z., Feris, R.: S3pool: Pooling with stochastic spatial sampling. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4970\u20134978 (2017)","key":"1695_CR22","DOI":"10.1109\/CVPR.2017.426"},{"doi-asserted-by":"crossref","unstructured":"Gao, Z., Wang, L., Wu, G.: Lip: Local importance-based pooling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3355\u20133364 (2019)","key":"1695_CR23","DOI":"10.1109\/ICCV.2019.00345"},{"doi-asserted-by":"crossref","unstructured":"Song, S., Cheung, N.-M., Chandrasekhar, V., Mandal, B.: Deep adaptive temporal pooling for activity recognition. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1829\u20131837 (2018)","key":"1695_CR24","DOI":"10.1145\/3240508.3240713"},{"doi-asserted-by":"crossref","unstructured":"Nguyen, P., Liu, T., Prasad, G., Han, B.: Weakly supervised action localization by sparse temporal pooling network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6752\u20136761 (2018)","key":"1695_CR25","DOI":"10.1109\/CVPR.2018.00706"},{"doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tang, S., Muandet, K., Jarvers, C., Neumann, H.: Local temporal bilinear pooling for fine-grained action parsing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12005\u201312015 (2019)","key":"1695_CR26","DOI":"10.1109\/CVPR.2019.01228"},{"unstructured":"Girdhar, R., Ramanan, D.: Attentional pooling for action recognition. Adv. Neural Inf. Process. Syst. 30 (2017)","key":"1695_CR27"},{"issue":"1","key":"1695_CR28","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TCDS.2022.3145839","volume":"15","author":"H Li","year":"2022","unstructured":"Li, H., Huang, J., Zhou, M., Shi, Q., Fei, Q.: Self-attention pooling-based long-term temporal network for action recognition. IEEE Trans. Cognit. Dev. Syst. 15(1), 65\u201377 (2022)","journal-title":"IEEE Trans. Cognit. Dev. Syst."},{"issue":"4","key":"1695_CR29","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/s11263-018-1111-5","volume":"127","author":"A Cherian","year":"2019","unstructured":"Cherian, A., Gould, S.: Second-order temporal pooling for action recognition. Int. J. Comput. Vision 127(4), 340\u2013362 (2019)","journal-title":"Int. J. Comput. Vision"},{"doi-asserted-by":"crossref","unstructured":"Hu, L., Feng, L., Liu, S.: Hfnet: a novel model for human focused sports action recognition. In: Proceedings of the 3rd International Workshop on Multimedia Content Analysis in Sports, pp. 35\u201343 (2020)","key":"1695_CR30","DOI":"10.1145\/3422844.3423052"},{"key":"1695_CR31","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."},{"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)","key":"1695_CR32","DOI":"10.1109\/CVPR.2018.00812"},{"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)","key":"1695_CR33","DOI":"10.1109\/CVPR46437.2021.00137"},{"doi-asserted-by":"crossref","unstructured":"Huang, J., Zhou, W., Zhang, Q., Li, H., Li, W.: Video-based sign language recognition without temporal segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","key":"1695_CR34","DOI":"10.1609\/aaai.v32i1.11903"},{"doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","key":"1695_CR35","DOI":"10.1109\/CVPR.2016.90"},{"doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). Ieee","key":"1695_CR36","DOI":"10.1109\/CVPR.2009.5206848"},{"unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)","key":"1695_CR37"},{"doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","key":"1695_CR38","DOI":"10.1007\/978-3-030-01264-9_8"},{"doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10428\u201310436 (2020)","key":"1695_CR39","DOI":"10.1109\/CVPR42600.2020.01044"},{"doi-asserted-by":"crossref","unstructured":"Hao, A., Min, Y., Chen, X.: Self-mutual distillation learning for continuous sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11303\u201311312 (2021)","key":"1695_CR40","DOI":"10.1109\/ICCV48922.2021.01111"},{"doi-asserted-by":"crossref","unstructured":"Jiao, P., Min, Y., Li, Y., Wang, X., Lei, L., Chen, X.: Cosign: Exploring co-occurrence signals in skeleton-based continuous sign language recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20676\u201320686 (2023)","key":"1695_CR41","DOI":"10.1109\/ICCV51070.2023.01890"},{"key":"1695_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109903","volume":"145","author":"L Hu","year":"2024","unstructured":"Hu, L., Gao, L., Liu, Z., Feng, W.: Scalable frame resolution for efficient continuous sign language recognition. Pattern Recogn. 145, 109903 (2024)","journal-title":"Pattern Recogn."},{"doi-asserted-by":"crossref","unstructured":"Hu, L., Gao, L., Liu, Z., Pun, C.-M., Feng, W.: Adabrowse: Adaptive video browser for efficient continuous sign language recognition. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 709\u2013718 (2023)","key":"1695_CR43","DOI":"10.1145\/3581783.3611745"},{"doi-asserted-by":"crossref","unstructured":"Min, Y., Jiao, P., Li, Y., Wang, X., Lei, L., Chai, X., Chen, X.: Deep radial embedding for visual sequence learning. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part VI, pp. 240\u2013256 (2022). Springer","key":"1695_CR44","DOI":"10.1007\/978-3-031-20068-7_14"},{"issue":"9","key":"1695_CR45","doi-asserted-by":"publisher","first-page":"2306","DOI":"10.1109\/TPAMI.2019.2911077","volume":"42","author":"O Koller","year":"2019","unstructured":"Koller, O., Camgoz, N.C., Ney, H., Bowden, R.: Weakly supervised learning with multi-stream cnn-lstm-hmms to discover sequential parallelism in sign language videos. PAMI 42(9), 2306\u20132320 (2019)","journal-title":"PAMI"},{"doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for continuous sign language recognition. In: AAAI (2020)","key":"1695_CR46","DOI":"10.1609\/aaai.v34i07.7001"},{"doi-asserted-by":"crossref","unstructured":"Zuo, R., Mak, B.: C2slr: Consistency-enhanced continuous sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5131\u20135140 (2022)","key":"1695_CR47","DOI":"10.1109\/CVPR52688.2022.00507"},{"unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: Joint end-to-end sign language recognition and translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10023\u201310033 (2020)","key":"1695_CR48"},{"unstructured":"Yang, Z., Shi, Z., Shen, X., Tai, Y.-W.: Sf-net: Structured feature network for continuous sign language recognition. arXiv preprint arXiv:1908.01341 (2019)","key":"1695_CR49"},{"doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.-T., Wang, G.: Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","key":"1695_CR50","DOI":"10.1109\/CVPR.2016.115"},{"doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","key":"1695_CR51","DOI":"10.1109\/CVPR52688.2022.00298"},{"issue":"2","key":"1695_CR52","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","volume":"45","author":"Y-F Song","year":"2023","unstructured":"Song, Y.-F., Zhang, Z., Shan, C., Wang, L.: Constructing stronger and faster baselines for skeleton-based action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1474\u20131488 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01695-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01695-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01695-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,21]],"date-time":"2025-04-21T19:36:02Z","timestamp":1745264162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01695-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,3]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["1695"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01695-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,3,3]]},"assertion":[{"value":"1 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"134"}}