{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:58:30Z","timestamp":1769007510799,"version":"3.49.0"},"reference-count":78,"publisher":"Springer Science and Business Media LLC","issue":"33","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["No. 2022C01011"],"award-info":[{"award-number":["No. 2022C01011"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18430-6","type":"journal-article","created":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T07:01:52Z","timestamp":1709362912000},"page":"79009-79028","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Learning a compact embedding for fine-grained few-shot static gesture recognition"],"prefix":"10.1007","volume":"83","author":[{"given":"Zhipeng","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1834-4429","authenticated-orcid":false,"given":"Yu","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tangjie","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,2]]},"reference":[{"issue":"3","key":"18430_CR1","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1016\/j.jvcir.2011.12.006","volume":"23","author":"M Roccetti","year":"2012","unstructured":"Roccetti M, Marfia G, Semeraro A (2012) Playing into the wild: A gesture-based interface for gaming in public spaces. J Vis Commun Image Represent 23(3):426\u2013440","journal-title":"J Vis Commun Image Represent"},{"key":"18430_CR2","doi-asserted-by":"crossref","unstructured":"Suarez J, Murphy RR (2012) Hand gesture recognition with depth images: A review. In: 2012 IEEE RO-MAN: the 21st IEEE International Symposium on Robot and Human Interactive Communication, pp. 411\u2013417. IEEE","DOI":"10.1109\/ROMAN.2012.6343787"},{"key":"18430_CR3","doi-asserted-by":"crossref","unstructured":"Guo L, Lu Z, Yao L (2021) Human-machine interaction sensing technology based on hand gesture recognition: A review. IEEE Transactions on Human-Machine Systems 51(4):300\u2013309","DOI":"10.1109\/THMS.2021.3086003"},{"key":"18430_CR4","unstructured":"Rahimian E, Zabihi S, Atashzar SF, Asif A, Mohammadi A (2019) Xceptiontime: A novel deep architecture based on depthwise separable convolutions for hand gesture classification. arXiv:1911.03803"},{"key":"18430_CR5","unstructured":"Zhang L, Zhu G, Mei L, Shen P, Shah SAA, Bennamoun M (2018) Attention in convolutional lstm for gesture recognition. Advances in neural information processing systems 31"},{"key":"18430_CR6","doi-asserted-by":"crossref","unstructured":"Abavisani M, Joze HRV, Patel VM (2019) Improving the performance of unimodal dynamic hand-gesture recognition with multimodal training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1165\u20131174","DOI":"10.1109\/CVPR.2019.00126"},{"key":"18430_CR7","doi-asserted-by":"crossref","unstructured":"Pu J, Zhou W, Hu H, Li H (2020) Boosting continuous sign language recognition via cross modality augmentation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1497\u20131505","DOI":"10.1145\/3394171.3413931"},{"key":"18430_CR8","doi-asserted-by":"publisher","first-page":"13009","DOI":"10.1609\/aaai.v34i07.7001","volume":"34","author":"H Zhou","year":"2020","unstructured":"Zhou H, Zhou W, Zhou Y, Li H (2020) Spatial-temporal multi-cue network for continuous sign language recognition. Proceedings of the AAAI Conference on Artificial Intelligence 34:13009\u201313016","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"18430_CR9","unstructured":"Kapitanov A, Makhlyarchuk A, Kvanchiani K (2022) Hagrid-hand gesture recognition image dataset. arXiv:2206.08219"},{"key":"18430_CR10","unstructured":"Mavi A, Dikle Z (2022) A new 27 class sign language dataset collected from 173 individuals. https:\/\/doi.org\/10.48550\/arXiv.2203.038592203.03859"},{"key":"18430_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2021.106791","volume":"35","author":"C Nuzzi","year":"2021","unstructured":"Nuzzi C, Pasinetti S, Pagani R, Coffetti G, Sansoni G (2021) Hands: an rgb-d dataset of static hand-gestures for human-robot interaction. Data Brief 35:106791","journal-title":"Data Brief"},{"key":"18430_CR12","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: International Conference on Machine Learning, pp. 1126\u20131135. PMLR"},{"key":"18430_CR13","unstructured":"Nichol A, Schulman J (2018) Reptile: a scalable metalearning algorithm 2(3):4. arXiv:1803.02999"},{"key":"18430_CR14","unstructured":"Rusu AA, Rao D, Sygnowski J, Vinyals O, Pascanu R, Osindero S, Hadsell R (2018) Meta-learning with latent embedding optimization. arXiv:1807.05960"},{"key":"18430_CR15","unstructured":"Schwartz E, Karlinsky L, Shtok J, Harary S, Marder M, Kumar A, Feris R, Giryes R, Bronstein A (2018) Delta-encoder: an effective sample synthesis method for few-shot object recognition. Advances in neural information processing systems 31"},{"key":"18430_CR16","doi-asserted-by":"crossref","unstructured":"Hariharan B, Girshick R (2017) Low-shot visual recognition by shrinking and hallucinating features. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3018\u20133027","DOI":"10.1109\/ICCV.2017.328"},{"key":"18430_CR17","doi-asserted-by":"crossref","unstructured":"Chen Z, Fu Y, Wang YX, Ma L, Liu W, Hebert M (2019) Image deformation meta-networks for one-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8680\u20138689","DOI":"10.1109\/CVPR.2019.00888"},{"key":"18430_CR18","unstructured":"Li Z, Zhou F, Chen F, Li H (2017) Meta-sgd: Learning to learn quickly for few-shot learning. arXiv:1707.09835"},{"key":"18430_CR19","unstructured":"Vinyals O, Blundell C, Lillicrap T, Wierstra D et al (2016) Matching networks for one shot learning. Advances in neural information processing systems 29"},{"key":"18430_CR20","doi-asserted-by":"crossref","unstructured":"Qiao S, Liu C, Shen W, Yuille AL (2018) Few-shot image recognition by predicting parameters from activations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7229\u20137238","DOI":"10.1109\/CVPR.2018.00755"},{"key":"18430_CR21","doi-asserted-by":"crossref","unstructured":"Hao F, He F, Cheng J, Wang L, Cao J, Tao D (2019) Collect and select: Semantic alignment metric learning for few-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8460\u20138469","DOI":"10.1109\/ICCV.2019.00855"},{"key":"18430_CR22","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhao Y, Li J, Tian Y (2020) Cooperative bi-path metric for few-shot learning. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1524\u20131532","DOI":"10.1145\/3394171.3413946"},{"key":"18430_CR23","unstructured":"Yoon SW, Seo J, Moon J (2019) Tapnet: Neural network augmented with task-adaptive projection for few-shot learning. In: International Conference on Machine Learning, pp. 7115\u20137123. PMLR"},{"key":"18430_CR24","unstructured":"Oreshkin B, Rodr\u00edguez L\u00f3pez P, Lacoste A (2018) Tadam: Task dependent adaptive metric for improved few-shot learning. Advances in neural information processing systems 31"},{"key":"18430_CR25","unstructured":"Wang Y, Chao WL, Weinberger KQ, Van Der Maaten L (2019) Simpleshot:Revisiting nearest-neighbor classification for few-shot learning. arXiv:1911.04623"},{"key":"18430_CR26","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. Advances in neural information processing systems 30"},{"key":"18430_CR27","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-sne. Journal of machine learning research 9(11)"},{"issue":"5","key":"18430_CR28","doi-asserted-by":"publisher","first-page":"3422","DOI":"10.1109\/TCYB.2020.3012092","volume":"52","author":"J Wan","year":"2020","unstructured":"Wan J, Lin C, Wen L, Li Y, Miao Q, Escalera S, Anbarjafari G, Guyon I, Guo G, Li SZ (2020) Chalearn looking at people: Isogd and congd large-scale rgb-d gesture recognition. IEEE Transactions on Cybernetics 52(5):3422\u20133433","journal-title":"IEEE Transactions on Cybernetics"},{"key":"18430_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-6180-2014-170","volume":"170","author":"M Kawulok","year":"2014","unstructured":"Kawulok M, Kawulok J, Nalepa J (2014) Smolka B (2014) Self-adaptive algorithm for segmenting skin regions. EURASIP Journal on Advances in Signal Processing 170:1\u201322. https:\/\/doi.org\/10.1186\/1687-6180-2014-170","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"18430_CR30","doi-asserted-by":"publisher","unstructured":"Nalepa J, Kawulok M (2014) Fast and accurate hand shape classification. In: Kozielski S, Mrozek D, Kasprowski P, Malysiak-Mrozek B, Kostrzewa D (eds.) Beyond Databases, Architectures, and Structures. Communications in Computer and Information Science, vol. 424, pp. 364\u2013373. Springer. https:\/\/doi.org\/10.1007\/978-3-319-06932-635","DOI":"10.1007\/978-3-319-06932-635"},{"issue":"23","key":"18430_CR31","doi-asserted-by":"publisher","first-page":"16363","DOI":"10.1007\/s11042-015-2934-5","volume":"75","author":"T Grzejszczak","year":"2016","unstructured":"Grzejszczak T, Kawulok M, Galuszka A (2016) Hand landmarks detection and localization in color images. Multimedia Tools and Applications 75(23):16363\u201316387. https:\/\/doi.org\/10.1007\/s11042-015-2934-5","journal-title":"Multimedia Tools and Applications"},{"key":"18430_CR32","unstructured":"Barczak A, Reyes N, Abastillas M, Piccio A, Susnjak T (2011) A new 2d static hand gesture colour image dataset for asl gestures"},{"key":"18430_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/4167890","volume":"2019","author":"RF Pinto","year":"2019","unstructured":"Pinto RF, Borges CD, Almeida AM, Paula IC (2019) Static hand gesture recognition based on convolutional neural networks. Journal of Electrical and Computer Engineering 2019:1\u201312","journal-title":"Journal of Electrical and Computer Engineering"},{"key":"18430_CR34","doi-asserted-by":"crossref","unstructured":"Molchanov P, Yang X, Gupta S, Kim K, Tyree S, Kautz J (2016) Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215","DOI":"10.1109\/CVPR.2016.456"},{"key":"18430_CR35","doi-asserted-by":"crossref","unstructured":"Benitez-Garcia G, Olivares-Mercado J, Sanchez-Perez G, Yanai K (2021) Ipn hand: A video dataset and benchmark for real-time continuous hand gesture recognition. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 4340\u20134347. IEEE","DOI":"10.1109\/ICPR48806.2021.9412317"},{"key":"18430_CR36","doi-asserted-by":"crossref","unstructured":"Materzynska J, Berger G, Bax I, Memisevic R (2019) The jester dataset: A large-scale video dataset of human gestures. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp. 0\u20130","DOI":"10.1109\/ICCVW.2019.00349"},{"issue":"5","key":"18430_CR37","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/TMM.2018.2808769","volume":"20","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Cao C, Cheng J, Lu H (2018) Egogesture: A new dataset and benchmark for egocentric hand gesture recognition. IEEE Trans Multimedia 20(5):1038\u20131050","journal-title":"IEEE Trans Multimedia"},{"key":"18430_CR38","doi-asserted-by":"crossref","unstructured":"Song Y, Demirdjian D, Davis R (2011) Tracking body and hands for gesture recognition: Natops aircraft handling signals database. In: 2011 IEEE International Conference on Automatic Face & Gesture Recognition (FG), pp. 500\u2013506. IEEE","DOI":"10.1109\/FG.2011.5771448"},{"key":"18430_CR39","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando G, Yuan S, Baek S, Kim TK (2018) First-person hand action benchmark with rgb-d videos and 3d hand pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 409\u2013419","DOI":"10.1109\/CVPR.2018.00050"},{"key":"18430_CR40","doi-asserted-by":"crossref","unstructured":"Liu D, Zhang L, Wu Y (2022) Ld-congr: A large rgb-d video dataset for long-distance continuous gesture recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3304\u20133312","DOI":"10.1109\/CVPR52688.2022.00330"},{"key":"18430_CR41","doi-asserted-by":"crossref","unstructured":"Escalera S, Gonz\u00e1lez J, Bar\u00f3 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 Multimodal Interaction, pp. 445\u2013452","DOI":"10.1145\/2522848.2532595"},{"key":"18430_CR42","doi-asserted-by":"crossref","unstructured":"Wan J, Zhao Y, Zhou S, Guyon I, Escalera S, Li SZ (2016) Chalearn looking at people rgb-d isolated and continuous datasets for gesture recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 56\u201364","DOI":"10.1109\/CVPRW.2016.100"},{"key":"18430_CR43","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Ceylan D, Yang J, Russell B, Argus M, Brox T (2019) Freihand: A dataset for markerless capture of hand pose and shape from single rgb images. In Proceedings of the IEEE\/CVF International Conference on Computer Vision 2019 (pp. 813\u2013822)","DOI":"10.1109\/ICCV.2019.00090"},{"issue":"6","key":"18430_CR44","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3390\/jimaging8060153","volume":"8","author":"F Al Farid","year":"2022","unstructured":"Al Farid F, Hashim N, Abdullah J, Bhuiyan MR, Shahida Mohd Isa WN, Uddin J, Haque MA, Husen MN (2022) A structured and methodological review on vision-based hand gesture recognition system. Journal of Imaging 8(6):153","journal-title":"Journal of Imaging"},{"key":"18430_CR45","doi-asserted-by":"crossref","unstructured":"Oudah M, Al-Naji A, Chahl J (2020) Hand gesture recognition based on computer vision: a review of techniques. journal of Imaging 6(8):73","DOI":"10.3390\/jimaging6080073"},{"key":"18430_CR46","doi-asserted-by":"crossref","unstructured":"Xu C, Wu X, Wang M, Qiu F, Liu Y, Ren J (2022) Improving dynamic gesture recognition in untrimmed videos by an online lightweight framework and a new gesture dataset zjugesture. Neurocomputing","DOI":"10.1016\/j.neucom.2022.12.022"},{"key":"18430_CR47","doi-asserted-by":"crossref","unstructured":"Quader N, Lu J, Dai P, Li W (2020) Towards efficient coarse-to-fine networks for action and gesture recognition. InComputer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16 2020 (pp. 35\u201351). Springer International Publishing","DOI":"10.1007\/978-3-030-58577-8_3"},{"key":"18430_CR48","doi-asserted-by":"crossref","unstructured":"Cheng KL, Yang Z, Chen Q, Tai YW (2020) Fully convolutional networks for continuous sign language recognition. In: Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIV 16, pp. 697\u2013714 (2020). Springer","DOI":"10.1007\/978-3-030-58586-0_41"},{"key":"18430_CR49","doi-asserted-by":"crossref","unstructured":"Zhou B, Wang P, Wan J, Liang Y, Wang F, Zhang D, Lei Z, Li H, Jin R (2022) Decoupling and recoupling spatiotemporal representation for rgb-d-based motion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20154\u201320163","DOI":"10.1109\/CVPR52688.2022.01952"},{"key":"18430_CR50","doi-asserted-by":"publisher","first-page":"5626","DOI":"10.1109\/TIP.2021.3087348","volume":"30","author":"Z Yu","year":"2021","unstructured":"Yu Z, Zhou B, Wan J, Wang P, Chen H, Liu X, Li SZ, Zhao G (2021) Searching multi-rate and multi-modal temporal enhanced networks for gesture recognition. IEEE Trans Image Process 30:5626\u20135640","journal-title":"IEEE Trans Image Process"},{"key":"18430_CR51","doi-asserted-by":"crossref","unstructured":"Miao Q, Li Y, Ouyang W, Ma Z, Xu X, Shi W, Cao X (2017) Multimodal gesture recognition based on the resc3d network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 3047\u20133055","DOI":"10.1109\/ICCVW.2017.360"},{"key":"18430_CR52","doi-asserted-by":"crossref","unstructured":"D\u2019Eusanio A, Simoni A, Pini S, Borghi G, Vezzani R, Cucchiara R (2020) A transformer-based network for dynamic hand gesture recognition. In: 2020 International Conference on 3D Vision (3DV), pp. 623\u2013632. IEEE","DOI":"10.1109\/3DV50981.2020.00072"},{"key":"18430_CR53","doi-asserted-by":"crossref","unstructured":"Zabihi S, Rahimian E, Asif A, Mohammadi A (2022) Trahgr: Transformer for hand gesture recognition via electromyography 2203","DOI":"10.1109\/TNSRE.2023.3324252"},{"key":"18430_CR54","doi-asserted-by":"crossref","unstructured":"Kr\u00e1lik M, \u0160uppa M (2021) Waveglove: Transformer-based hand gesture recognition using multiple inertial sensors. In: 2021 29th European Signal Processing Conference (EUSIPCO), pp. 1576\u20131580. IEEE","DOI":"10.23919\/EUSIPCO54536.2021.9616000"},{"key":"18430_CR55","unstructured":"Biju E, Sriram A, Khapra MM, Kumar P (2022) Joint transformer\/rnn architecture for gesture typing in indic languages. arXiv:2203.14049"},{"key":"18430_CR56","doi-asserted-by":"crossref","unstructured":"Truong TD, Bui QH, Duong CN, Seo HS, Phung SL, Li X, Luu K (2022) Direcformer: A directed attention in transformer approach to robust action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20030\u201320040","DOI":"10.1109\/CVPR52688.2022.01940"},{"key":"18430_CR57","doi-asserted-by":"publisher","first-page":"8585","DOI":"10.1609\/aaai.v33i01.33018585","volume":"33","author":"C Li","year":"2019","unstructured":"Li C, 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. Proceedings of the AAAI Conference on Artificial Intelligence 33:8585\u20138593","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"18430_CR58","unstructured":"Chen Y, Zhao L, Peng X, Yuan J, Metaxas DN (2019) Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. arXiv:1907.08871"},{"key":"18430_CR59","doi-asserted-by":"publisher","first-page":"3563","DOI":"10.1609\/aaai.v35i4.16471","volume":"35","author":"B Zhou","year":"2021","unstructured":"Zhou B, Li Y, Wan J (2021) Regional attention with architecture-rebuilt 3d network for rgb-d gesture recognition. Proceedings of the AAAI Conference on Artificial Intelligence 35:3563\u20133571","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"18430_CR60","unstructured":"Sung G, Sokal K, Uboweja E, Bazarevsky V, Baccash J, Bazavan EG, Chang CL, Grundmann M (2021) On-device real-time hand gesture recognition. arXiv:2111.00038"},{"key":"18430_CR61","doi-asserted-by":"publisher","DOI":"10.1016\/j.array.2022.100251","volume":"16","author":"TL Dang","year":"2022","unstructured":"Dang TL, Tran SD, Nguyen TH, Kim S, Monet N (2022) An improved hand gesture recognition system using keypoints and hand bounding boxes. Array 16:100251","journal-title":"Array"},{"issue":"6","key":"18430_CR62","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.3390\/s23063332","volume":"23","author":"J Baptista","year":"2023","unstructured":"Baptista J, Santos V, Silva F, Pinho D (2023) Domain adaptation with contrastive simultaneous multi-loss training for hand gesture recognition. Sensors 23(6):3332","journal-title":"Sensors"},{"key":"18430_CR63","doi-asserted-by":"crossref","unstructured":"Wang YX, Girshick R, Hebert M, Hariharan B (2018) Low-shot learning from imaginary data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7278\u20137286","DOI":"10.1109\/CVPR.2018.00760"},{"key":"18430_CR64","unstructured":"Ravi S, Larochelle H (2016) Optimization as a model for few-shot learning. In: International Conference on Learning Representations"},{"key":"18430_CR65","unstructured":"Rajeswaran A, Finn C, Kakade SM, Levine S (2019) Meta-learning with implicit gradients. Advances in neural information processing systems 32"},{"key":"18430_CR66","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1609\/aaai.v36i2.20029","volume":"36","author":"S Li","year":"2022","unstructured":"Li S, Liu H, Qian R, Li Y, See J, Fei M, Yu X, Lin W (2022) Ta2n: Two-stage action alignment network for few-shot action recognition. Proceedings of the AAAI Conference on Artificial Intelligence 36:1404\u20131411","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"18430_CR67","doi-asserted-by":"crossref","unstructured":"Jamal MA, Qi GJ (2019) Task agnostic meta-learning for few-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11719\u201311727","DOI":"10.1109\/CVPR.2019.01199"},{"key":"18430_CR68","doi-asserted-by":"crossref","unstructured":"Zhang H, Zhang L, Qi X, Li H, Torr PH, Koniusz P (2020) Few-shot action recognition with permutation-invariant attention. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part V 16, pp. 525\u2013542. Springer","DOI":"10.1007\/978-3-030-58558-7_31"},{"key":"18430_CR69","doi-asserted-by":"crossref","unstructured":"Sung F, Yang Y, Zhang L, Xiang T, Torr PH, Hospedales TM (2018) Learning to compare: Relation network for few-shot learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1199\u20131208","DOI":"10.1109\/CVPR.2018.00131"},{"key":"18430_CR70","doi-asserted-by":"crossref","unstructured":"Ye HJ, Hu H, Zhan DC, Sha F (2020) Few-shot learning via embedding adaptation with set-to-set functions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8808\u20138817","DOI":"10.1109\/CVPR42600.2020.00883"},{"key":"18430_CR71","unstructured":"Yu Z, Yang L, Chen S, Yao A (2021) Local and global point cloud reconstruction for 3d hand pose estimation. arXiv:2112.06389"},{"key":"18430_CR72","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"18430_CR73","doi-asserted-by":"crossref","unstructured":"Moon G, Yu SI, Wen H, Shiratori T, Lee KM (2020) Interhand2.6m: A dataset and baseline for 3d interacting hand pose estimation from a single rgb image. In: European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"18430_CR74","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"key":"18430_CR75","unstructured":"Loshchilov I, Hutter F (2016) Sgdr: Stochastic gradient descent with warm restarts. arXiv:1608.03983"},{"key":"18430_CR76","doi-asserted-by":"crossref","unstructured":"Wertheimer D, Tang L, Hariharan B (2021) Few-shot classification with feature map reconstruction networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8012\u20138021","DOI":"10.1109\/CVPR46437.2021.00792"},{"key":"18430_CR77","doi-asserted-by":"crossref","unstructured":"Afrasiyabi A, Larochelle H, Lalonde JF, Gagn\u2019e C (2022) Matching feature sets for few-shot image classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9014\u20139024","DOI":"10.1109\/CVPR52688.2022.00881"},{"key":"18430_CR78","unstructured":"Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18430-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18430-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18430-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T13:27:55Z","timestamp":1728307675000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18430-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":78,"journal-issue":{"issue":"33","published-online":{"date-parts":[[2024,10]]}},"alternative-id":["18430"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18430-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,2]]},"assertion":[{"value":"17 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2024","order":4,"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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interests"}}]}}