{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T22:57:40Z","timestamp":1793141860764,"version":"4.5.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"28","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s11042-023-15112-7","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:02:15Z","timestamp":1682380935000},"page":"43781-43796","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["ZS-GR: zero-shot gesture recognition from RGB-D videos"],"prefix":"10.1007","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7963-9461","authenticated-orcid":false,"given":"Razieh","family":"Rastgoo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kourosh","family":"Kiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"key":"15112_CR1","unstructured":"Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. ICLR"},{"key":"15112_CR2","unstructured":"Bilge YC, Ikizler-Cinbis N, Gokberk Cinbis R (2019) Zero-Shot Sign language recognition: can textual data uncover sign languages? BMVC"},{"key":"15112_CR3","unstructured":"Bishay M, Zoumpourlis G, Patras I (2019) TARN : temporal attentive relation network for few-shot and zero-shot action recognition. arXiv:1907.09021v1"},{"key":"15112_CR4","first-page":"172","volume":"4","author":"Zh Cao","year":"2019","unstructured":"Cao Zh, Hidalgo G, Simon T, Wei ShE, Sheikh Y (2019) Openpose: realtime multi-person 2D Pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell 4:172\u2013186","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"15112_CR5","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko Sergey (2020) End-to-end object detection with transformers. ECCV:213\u2013229","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"15112_CR6","unstructured":"Chan W, Saharia C, Hinton G, Norouzi M, Jaitly N (2020) Imputer: sequence modelling via imputation and dynamic programming. arXiv:2002.08926"},{"key":"15112_CR7","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805"},{"key":"15112_CR8","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner Th, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N (2021) An image is worth 16x16 words: transformers for image recognition at scale. ICLR"},{"key":"15112_CR9","doi-asserted-by":"crossref","unstructured":"Escalera S, Gonzalez J, Baro X, Reyes M, Lopes O, Guyon I, Athitsos V, Escalante H (2013) Multi-modal gesture recognition challenge 2013: dataset and results. In: Proceedings of the 15th ACM on international conference on multi-modal interaction, pp 445\u2013452","DOI":"10.1145\/2522848.2532595"},{"key":"15112_CR10","unstructured":"Gu J, Bradbury J, Xiong C, Li VO, Socher R (2018) Non-autoregressive neural machine translation. ICLR"},{"key":"15112_CR11","doi-asserted-by":"crossref","unstructured":"Gupta P, Sharma D, Kiran R (2021) Sarvadevabhatla, Syntactically guided generative embeddings for zero-shot skeleton action recognition. IEEE Int Conf Image Process (ICIP), Anchorage, Alaska USA","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"15112_CR12","doi-asserted-by":"crossref","unstructured":"Gupta P, Sharma D, Kiran Sarvadevabhatla R (2021) Syntactically guided generative embeddings for zero-shot skeleton action recognition arXiv:2101.11530v1","DOI":"10.1109\/ICIP42928.2021.9506179"},{"key":"15112_CR13","unstructured":"Hahn M, Silva A, Rehg JM (2019) Action2vec: a crossmodal embedding approach to action learning. arXiv:1901.00484v1"},{"key":"15112_CR14","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 (1997) Long short-term memory. Neural Comput 9:1735\u20131780","journal-title":"Neural Comput"},{"key":"15112_CR15","unstructured":"Huang G, Bors AG (2021) Video classification with FineCoarse networks. arXiv:2103.15584v1"},{"key":"15112_CR16","doi-asserted-by":"crossref","unstructured":"Kalfaoglu ME, Kalkan S, Alatan A (2020) Late temporal modeling in 3D CNN architectures with BERT for action recognition. arXiv:2008.01232v3","DOI":"10.1007\/978-3-030-68238-5_48"},{"key":"15112_CR17","doi-asserted-by":"crossref","unstructured":"Khan S, Naseer M, Hayat M, Zamir SW, Khan FSh, Shah M (2022) Transformers in vision: a survey. arXiv:2101.01169v5","DOI":"10.1145\/3505244"},{"key":"15112_CR18","doi-asserted-by":"publisher","unstructured":"Kiani K, Hematpour R, Rastgoo R (2021) Automatic grayscale image colorization using a deep hybrid model. J AI Data Mining. https:\/\/doi.org\/10.22044\/JADM.2021.9957.2131","DOI":"10.22044\/JADM.2021.9957.2131"},{"key":"15112_CR19","unstructured":"Li D, Xu Ch, Yu X, Zhang K, Swift B, Suominen H, Li H (2020) TSPNet hierarchical feature learning via temporal semantic pyramid for sign language translation, NIPS"},{"key":"15112_CR20","doi-asserted-by":"crossref","unstructured":"Li C. h., Zhang X, Liao L, Jin L, Yang W (2019) Skeleton-based gesture recognition using several fully connected layers with path signature features and temporal transformer module. In: Proceedings of the AAAI conference on artificial intelligence, pp 8585\u20138593","DOI":"10.1609\/aaai.v33i01.33018585"},{"key":"15112_CR21","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy Ch, Reed S, Fu ChY, Berg AC (2016) SSD: single shot MultiBox detector. ECCV:21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"15112_CR22","doi-asserted-by":"crossref","unstructured":"Madapana N, Wachs JP (2020) Feature selection for zero-shot gesture recognition. In: 15th IEEE international conference on automatic face and gesture recognition (FG 2020)","DOI":"10.1109\/FG47880.2020.00046"},{"key":"15112_CR23","doi-asserted-by":"crossref","unstructured":"Madapana N, Wachs JP (2020) Zero-shot learning for gesture recognition. In: 15th IEEE international conference on automatic face and gesture recognition (FG 2020)","DOI":"10.1145\/3382507.3421161"},{"key":"15112_CR24","unstructured":"Madapana N, Wachs JP (2020) A semantical and analytical approach for zero shot gesture learning. In: 15th IEEE international conference on automatic face and gesture recognition (FG 2020)"},{"key":"15112_CR25","first-page":"451","volume":"8","author":"N Majidi","year":"2020","unstructured":"Majidi N, Kiani K, Rastgoo R (2020) A deep model for super-resolution enhancement from a single image. J AI Data Mining 8:451\u2013460","journal-title":"J AI Data Mining"},{"key":"15112_CR26","doi-asserted-by":"crossref","unstructured":"Mishra A, Kumar Verma V, Shiva M, Reddy K, Arulkumar S, Rai P, Mittal A (2018) A generative approach to zero-shot and few-shot action recognition. In: 2018 IEEE Winter conference on applications of computer vision, pp 372\u2013380","DOI":"10.1109\/WACV.2018.00047"},{"key":"15112_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen M, Qi-Yan W, Ho H (2021) Sign language recognition from digital videos using deep learning methods. Geomet Vision:108\u2013118","DOI":"10.1007\/978-3-030-72073-5_9"},{"key":"15112_CR28","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1007\/s11042-022-13573-w","volume":"82","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) A deep co-attentive hand-based video question answering framework using multi-view skeleton. Multimed Tools Appl 82:1401\u20131429","journal-title":"Multimed Tools Appl"},{"key":"15112_CR29","doi-asserted-by":"crossref","unstructured":"Rastgoo R, Kiani K, Escalera S (2018) Multi-modal deep hand sign language recognition in still images using restricted Boltzmann machine. Entropy, vol 20(809)","DOI":"10.3390\/e20110809"},{"key":"15112_CR30","doi-asserted-by":"publisher","first-page":"22965","DOI":"10.1007\/s11042-020-09048-5","volume":"79","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) Video-based isolated hand sign language recognition using a deep cascaded model. Multimed Tools Appl 79:22965\u201322987","journal-title":"Multimed Tools Appl"},{"key":"15112_CR31","doi-asserted-by":"publisher","first-page":"113336","DOI":"10.1016\/j.eswa.2020.113336","volume":"150","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) Hand sign language recognition using multi-view hand skeleton. Expert Syst Appl 150:113336","journal-title":"Expert Syst Appl"},{"key":"15112_CR32","first-page":"164","volume":"113794","author":"R Rastgoo","year":"2021","unstructured":"Rastgoo R, Kiani K, Escalera S (2021) Sign language recognition: a deep survey. Expert Syst Appl 113794:164","journal-title":"Expert Syst Appl"},{"key":"15112_CR33","doi-asserted-by":"crossref","unstructured":"Rastgoo R, Kiani K, Escalera S (2021) Real-time isolated hand sign language recognition using deep networks and SVD, J Ambient Intell Humanized Comput","DOI":"10.1016\/j.eswa.2020.113794"},{"key":"15112_CR34","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1007\/s11042-020-09700-0","volume":"80","author":"R Rastgoo","year":"2021","unstructured":"Rastgoo R, Kiani K, Escalera S (2021) Hand pose aware multi-modal isolated sign language recognition. Multimed Tools Appl 80:127\u2013163","journal-title":"Multimed Tools Appl"},{"key":"15112_CR35","doi-asserted-by":"crossref","unstructured":"Rastgoo R, Kiani K, Escalera S, Sabokrou M (2021) Sign Language Production: a review. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3451\u20133461","DOI":"10.1109\/CVPRW53098.2021.00384"},{"key":"15112_CR36","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv:1804.02767"},{"key":"15112_CR37","doi-asserted-by":"crossref","unstructured":"Ren S, He K, Girshick RB, Sun J, Faster R -C N N (2015) Towards real-time object detection with region proposal networks. PAMI:1137\u20131149","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"15112_CR38","unstructured":"Schonfeld E, Ebrahimi S, Sinha S, Darrell T, Akata Z (2022) Generalized zero-shot learning via aligned variational auto-encoders, CVPR:8247\u20138255"},{"key":"15112_CR39","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G, NTU R G B +D (2016) A large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"15112_CR40","unstructured":"Sung J, Ponce C, Selman B, Saxena A (2012) Unstructured human activity detection from RGBD images. IEEE Int Conf Robot Automation"},{"key":"15112_CR41","doi-asserted-by":"crossref","unstructured":"Tsai YH, Huang LK, Salakhutdinov R (2017) Learning robust visual-semantic embeddings. In: Proceedings of the IEEE International conference on computer vision, pp 3571\u20133580","DOI":"10.1109\/ICCV.2017.386"},{"key":"15112_CR42","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. NIPS"},{"key":"15112_CR43","doi-asserted-by":"crossref","unstructured":"Wan J, Zhao Y, Zhou S. h., Guyon I, Escalera S, Li SZ (2016) Chalearn Looking at people RGB -d isolated and continuous datasets for gesture recognition. CVPR Workshop","DOI":"10.1109\/CVPRW.2016.100"},{"key":"15112_CR44","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2012) Mining actionlet ensemble for action recognition with depth cameras. In: IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp 1290\u20131297","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"15112_CR45","doi-asserted-by":"crossref","unstructured":"Wray M, Larlus D, Csurka G, Damen D (2019) Fine-grained action retrieval through multiple partsof-speech embeddings. In: IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00054"},{"key":"15112_CR46","doi-asserted-by":"crossref","unstructured":"Wu J, Li K, Zhao X, Tan M (2018) Unfamiliar dynamic hand gestures recognition based on zero-shot learning. ICONIP:244\u2013254","DOI":"10.1007\/978-3-030-04221-9_22"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15112-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15112-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15112-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T02:05:55Z","timestamp":1698458755000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15112-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":46,"journal-issue":{"issue":"28","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["15112"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15112-7","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"13 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 March 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors confirm their consent for publication.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Consent for Publication"}},{"value":"The authors certify that they have no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}