{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T07:19:30Z","timestamp":1765610370066,"version":"3.37.3"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T00:00:00Z","timestamp":1690675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072334"],"award-info":[{"award-number":["62072334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s00371-023-02979-8","type":"journal-article","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T07:01:30Z","timestamp":1690700490000},"page":"3417-3428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Difference-guided multi-scale spatial-temporal representation for sign language recognition"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4518-2154","authenticated-orcid":false,"given":"Liqing","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianyu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Wan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,7,30]]},"reference":[{"key":"2979_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv (2014)"},{"key":"2979_CR2","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: CVPR, pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"2979_CR3","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: joint end-to-end sign language recognition and translation. In: CVPR, pp. 10023\u201310033 (2020)"},{"key":"2979_CR4","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, pp. 697\u2013714 (2020)","DOI":"10.1007\/978-3-030-58586-0_41"},{"key":"2979_CR5","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv (2014)"},{"key":"2979_CR6","doi-asserted-by":"crossref","unstructured":"Cihan\u00a0Camgoz, N., Hadfield, S., Koller, O., Bowden, R.: Subunets: end-to-end hand shape and continuous sign language recognition. In: ICCV, pp. 3056\u20133065 (2017)","DOI":"10.1109\/ICCV.2017.332"},{"key":"2979_CR7","doi-asserted-by":"crossref","unstructured":"Cui, R., Liu, H., Zhang, C.: Recurrent convolutional neural networks for continuous sign language recognition by staged optimization. In: CVPR, pp. 7361\u20137369 (2017)","DOI":"10.1109\/CVPR.2017.175"},{"issue":"7","key":"2979_CR8","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. IEEE TMM 21(7), 1880\u20131891 (2019)","journal-title":"IEEE TMM"},{"key":"2979_CR9","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, vol. 1, pp. 886\u2013893 (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"2979_CR10","doi-asserted-by":"crossref","unstructured":"Evangelidis, G., Singh, G., Horaud, R.: Continuous gesture recognition from articulated poses. In: ECCVW, pp. 595\u2013607 (2014)","DOI":"10.1007\/978-3-319-16178-5_42"},{"key":"2979_CR11","doi-asserted-by":"crossref","unstructured":"Gharbi, H., Bahroun, S., Massaoudi, M., Zagrouba, E.: Key frames extraction using graph modularity clustering for efficient video summarization. In: ICASSP, pp. 1502\u20131506 (2017)","DOI":"10.1109\/ICASSP.2017.7952407"},{"key":"2979_CR12","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: ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"2979_CR13","doi-asserted-by":"crossref","unstructured":"Guo, D., Zhou, W., Li, H., Wang, M.: Hierarchical LSTM for sign language translation. In: AAAI, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12235"},{"key":"2979_CR14","doi-asserted-by":"crossref","unstructured":"Guo, D., Wang, S., Tian, Q., Wang, M.: Dense temporal convolution network for sign language translation. In: IJCAI, pp. 744\u2013750 (2019)","DOI":"10.24963\/ijcai.2019\/105"},{"key":"2979_CR15","doi-asserted-by":"crossref","unstructured":"Hao, A., Min, Y., Chen, X.: Self-mutual distillation learning for continuous sign language recognition. In: ICCV, pp. 11303\u201311312 (2021)","DOI":"10.1109\/ICCV48922.2021.01111"},{"key":"2979_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"2979_CR17","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"2979_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., Zhou, W., Zhang, Q., Li, H., Li, W.: Video-based sign language recognition without temporal segmentation. In: AAAI, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.11903"},{"key":"2979_CR19","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 (2016)"},{"key":"2979_CR20","doi-asserted-by":"crossref","unstructured":"Kar, A., Rai, N., Sikka, K., Sharma, G.: Adascan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: CVPR, pp. 3376\u20133385 (2017)","DOI":"10.1109\/CVPR.2017.604"},{"key":"2979_CR21","first-page":"108","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. CVIU 141, 108\u2013125 (2015)","journal-title":"CVIU"},{"key":"2979_CR22","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, O., Ney, H., Bowden, R.: Deep sign: hybrid CNN-HMM for continuous sign language recognition. In: BMVC (2016)","DOI":"10.5244\/C.30.136"},{"key":"2979_CR23","doi-asserted-by":"crossref","unstructured":"Koller, O., Zargaran, O., Ney, H., Bowden, R.: Deep sign: hybrid CNN-HMM for continuous sign language recognition. In: BMVC (2016)","DOI":"10.5244\/C.30.136"},{"key":"2979_CR24","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, pp. 4297\u20134305 (2017)","DOI":"10.1109\/CVPR.2017.364"},{"issue":"9","key":"2979_CR25","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. IEEE TPAMI 42(9), 2306\u20132320 (2019)","journal-title":"IEEE TPAMI"},{"key":"2979_CR26","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.jvcir.2018.02.010","volume":"52","author":"LI Kuncheva","year":"2018","unstructured":"Kuncheva, L.I., Yousefi, P., Almeida, J.: Edited nearest neighbour for selecting keyframe summaries of egocentric videos. J. Vis. Commun. Image Represent. 52, 118\u2013130 (2018)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"2979_CR27","doi-asserted-by":"crossref","unstructured":"Li, H., Gao, L., Han, R., Wan, L., Feng, W.: Key action and joint CTC-attention based sign language recognition. In: ICASSP, pp. 2348\u20132352 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054316"},{"key":"2979_CR28","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: TSM: temporal shift module for efficient video understanding. In: ICCV, pp. 7083\u20137093 (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2979_CR29","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.T., Sun, J.: Shufflenet v2: practical guidelines for efficient CNN architecture design. In: ECCV, pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"2979_CR30","doi-asserted-by":"crossref","unstructured":"Min, Y., Hao, A., Chai, X., Chen, X.: Visual alignment constraint for continuous sign language recognition. In: ICCV, pp. 11542\u201311551 (2021)","DOI":"10.1109\/ICCV48922.2021.01134"},{"key":"2979_CR31","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, pp. 172\u2013186 (2020)","DOI":"10.1007\/978-3-030-58517-4_11"},{"key":"2979_CR32","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: CVPR, pp. 4594\u20134602 (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"2979_CR33","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":"2979_CR34","doi-asserted-by":"crossref","unstructured":"Pu, J., Zhou, W., Li, H.: Dilated convolutional network with iterative optimization for continuous sign language recognition. In: IJCAI, vol.\u00a03, p.\u00a07 (2018)","DOI":"10.24963\/ijcai.2018\/123"},{"key":"2979_CR35","doi-asserted-by":"crossref","unstructured":"Pu, J., Zhou, W., Li, H.: Iterative alignment network for continuous sign language recognition. In: CVPR, pp. 4165\u20134174 (2019)","DOI":"10.1109\/CVPR.2019.00429"},{"key":"2979_CR36","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, pp. 1497\u20131505 (2020)","DOI":"10.1145\/3394171.3413931"},{"key":"2979_CR37","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: ICCV, pp. 5533\u20135541 (2017)","DOI":"10.1109\/ICCV.2017.590"},{"key":"2979_CR38","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: CVPR, pp. 10428\u201310436 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"2979_CR39","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS, vol.\u00a027 (2014)"},{"key":"2979_CR40","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: NIPS, vol.\u00a030 (2017)"},{"key":"2979_CR41","doi-asserted-by":"crossref","unstructured":"Vazquez-Enriquez, M., Alba-Castro, J.L., Doc\u00edo-Fern\u00e1ndez, L., Rodriguez-Banga, E.: Isolated sign language recognition with multi-scale spatial-temporal graph convolutional networks. In: CVPR, pp. 3462\u20133471 (2021)","DOI":"10.1109\/CVPRW53098.2021.00385"},{"key":"2979_CR42","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: ICCV, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"2979_CR43","doi-asserted-by":"crossref","unstructured":"Wang, S., Guo, D., Zhou, W.G., Zha, Z.J., Wang, M.: Connectionist temporal fusion for sign language translation. In: ACM MM, pp. 1483\u20131491 (2018)","DOI":"10.1145\/3240508.3240671"},{"issue":"3","key":"2979_CR44","first-page":"1138","volume":"31","author":"C Wei","year":"2020","unstructured":"Wei, C., Zhao, J., Zhou, W., Li, H.: Semantic boundary detection with reinforcement learning for continuous sign language recognition. IEEE TCSVT 31(3), 1138\u20131149 (2020)","journal-title":"IEEE TCSVT"},{"key":"2979_CR45","first-page":"3908","volume":"24","author":"P Xie","year":"2021","unstructured":"Xie, P., Zhao, M., Hu, X.: PiSLTRc: position-informed sign language transformer with content-aware convolution. IEEE TMM 24, 3908\u20133919 (2021)","journal-title":"IEEE TMM"},{"key":"2979_CR46","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2022.109233","volume":"136","author":"P Xie","year":"2023","unstructured":"Xie, P., Cui, Z., Du, Y., Zhao, M., Cui, J., Wang, B., Hu, X.: Multi-scale local-temporal similarity fusion for continuous sign language recognition. Pattern Recognit. 136, 109\u2013233 (2023)","journal-title":"Pattern Recognit."},{"key":"2979_CR47","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.patrec.2016.03.030","volume":"78","author":"W Yang","year":"2016","unstructured":"Yang, W., Tao, J., Ye, Z.: Continuous sign language recognition using level building based on fast hidden Markov model. Pattern Recognit. Lett. 78, 28\u201335 (2016)","journal-title":"Pattern Recognit. Lett."},{"key":"2979_CR48","unstructured":"Yang, Z., Shi, Z., Shen, X., Tai, Y.W.: Sf-net: Structured feature network for continuous sign language recognition. arXiv (2019)"},{"key":"2979_CR49","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: ICCV, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"2979_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Li, H.: Dynamic pseudo label decoding for continuous sign language recognition. In: ICME, pp. 1282\u20131287 (2019)","DOI":"10.1109\/ICME.2019.00223"},{"key":"2979_CR51","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, vol.\u00a034, pp. 13009\u201313016 (2020)","DOI":"10.1609\/aaai.v34i07.7001"},{"key":"2979_CR52","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: CVPR, pp. 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"2979_CR53","first-page":"768","volume":"24","author":"H Zhou","year":"2021","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for sign language recognition and translation. IEEE TMM 24, 768\u2013779 (2021)","journal-title":"IEEE TMM"},{"key":"2979_CR54","doi-asserted-by":"crossref","unstructured":"Zhu, W., Hu, J., Sun, G., Cao, X., Qiao, Y.: A key volume mining deep framework for action recognition. In: CVPR, pp. 1991\u20131999 (2016)","DOI":"10.1109\/CVPR.2016.219"},{"key":"2979_CR55","unstructured":"Zhu, Q., Li, J., Yuan, F., Gan, Q.: Multi-scale temporal network for continuous sign language recognition. arXiv preprint arXiv:2204.03864 (2022)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02979-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02979-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02979-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:09:50Z","timestamp":1729847390000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02979-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,30]]},"references-count":55,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["2979"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02979-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2023,7,30]]},"assertion":[{"value":"14 June 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2023","order":2,"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"}},{"value":"All datasets analysed during this study are available in links.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data Availability Statement"}}]}}