{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T01:24:07Z","timestamp":1768526647552,"version":"3.49.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"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":[[2023,7]]},"DOI":"10.1007\/s11042-023-14350-z","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T02:02:32Z","timestamp":1673316152000},"page":"25945-25971","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Still image action recognition based on interactions between joints and objects"],"prefix":"10.1007","volume":"82","author":[{"given":"Seyed Sajad","family":"Ashrafi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-6607","authenticated-orcid":false,"given":"Shahriar B.","family":"Shokouhi","sequence":"additional","affiliation":[]},{"given":"Ahmad","family":"Ayatollahi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,10]]},"reference":[{"key":"14350_CR1","doi-asserted-by":"publisher","unstructured":"Akti S, Ofli F, Imran M, Ekenel HK (2021) \u201cFight Detection from Still Images in the Wild,\u201d Proc. - 2022 IEEE\/CVF Winter Conf. Appl. Comput. Vis. Work. WACVW 2022, pp. 550\u2013559, https:\/\/doi.org\/10.48550\/arxiv.2111.08370","DOI":"10.48550\/arxiv.2111.08370"},{"key":"14350_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S11042-021-11215-1","volume":"2021","author":"SS Ashrafi","year":"2021","unstructured":"Ashrafi SS, Shokouhi SB, Ayatollahi A (Jul. 2021) Action recognition in still images using a multi-attention guided network with weakly supervised saliency detection. Multimed Tools Appl 2021:1\u201327. https:\/\/doi.org\/10.1007\/S11042-021-11215-1","journal-title":"Multimed Tools Appl"},{"key":"14350_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-020-09004-3","volume":"79","author":"DR Beddiar","year":"2020","unstructured":"Beddiar DR, Nini B, Sabokrou M, Hadid A (2020) Vision-based human activity recognition: a survey. Multimed Tools Appl 79:1\u201347. https:\/\/doi.org\/10.1007\/s11042-020-09004-3","journal-title":"Multimed Tools Appl"},{"key":"14350_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S11042-021-11136-Z","volume":"2021","author":"Y Cao","year":"2021","unstructured":"Cao Y, Liu C, Huang Z, Sheng Y, Ju Y (Jun. 2021) Skeleton-based action recognition with temporal action graph and temporal adaptive graph convolution structure. Multimed Tools Appl 2021:1\u201324. https:\/\/doi.org\/10.1007\/S11042-021-11136-Z","journal-title":"Multimed Tools Appl"},{"issue":"13","key":"14350_CR5","doi-asserted-by":"publisher","first-page":"20547","DOI":"10.1007\/S11042-021-10753-Y","volume":"80","author":"S Chakraborty","year":"2021","unstructured":"Chakraborty S, Mondal R, Singh PK, Sarkar R, Bhattacharjee D (2021) Transfer learning with fine tuning for human action recognition from still images. Multimed Tools Appl 2021 8013 80(13):20547\u201320578. https:\/\/doi.org\/10.1007\/S11042-021-10753-Y","journal-title":"Multimed Tools Appl 2021 8013"},{"key":"14350_CR6","doi-asserted-by":"publisher","unstructured":"Chapariniya M, Ashrafi SS, Shokouhi SB (2020) \u201cKnowledge Distillation Framework for Action Recognition in Still Images\u201d, 2020 10h Int. Conf Comput Knowl Eng ICCKE 2020, pp. 274\u2013277, https:\/\/doi.org\/10.1109\/ICCKE50421.2020.9303716","DOI":"10.1109\/ICCKE50421.2020.9303716"},{"key":"14350_CR7","doi-asserted-by":"crossref","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2016) \u201cDeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,\u201d IEEE Trans. Pattern Anal. Mach. Intell., vol. 40, no. 4, pp. 834\u2013848, Accessed: Aug. 12, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1606.00915v2","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"14350_CR8","unstructured":"Chollet F (2016) \u201cXception: Deep Learning with Depthwise Separable Convolutions,\u201d Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-January, pp. 1800\u20131807, Accessed: Aug. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1610.02357v3"},{"key":"14350_CR9","doi-asserted-by":"publisher","first-page":"19959","DOI":"10.1109\/ACCESS.2018.2815149","volume":"6","author":"J Chu","year":"2018","unstructured":"Chu J, Guo Z, Leng L (Mar. 2018) Object detection based on multi-layer convolution feature fusion and online hard example mining. IEEE Access 6:19959\u201319967. https:\/\/doi.org\/10.1109\/ACCESS.2018.2815149","journal-title":"IEEE Access"},{"key":"14350_CR10","doi-asserted-by":"publisher","unstructured":"Dehkordi HA, Nezhad AS, Ashrafi SS, Shokouhi SB (2021) \u201cStill Image Action Recognition Using Ensemble Learning,\u201d 2021 7th Int. Conf Web Res ICWR 2021, pp. 125\u2013129, https:\/\/doi.org\/10.1109\/ICWR51868.2021.9443021","DOI":"10.1109\/ICWR51868.2021.9443021"},{"key":"14350_CR11","doi-asserted-by":"publisher","unstructured":"Dehkordi HA, Nezhad AS, Kashiani H, Shokouhi SB, Ayatollahi A (2022) \u201cMulti-expert human action recognition with hierarchical super-class learning\u201d, Knowledge-Based Syst., p. 109091, https:\/\/doi.org\/10.1016\/J.KNOSYS.2022.109091","DOI":"10.1016\/J.KNOSYS.2022.109091"},{"key":"14350_CR12","unstructured":"Dosovitskiy A et al. (2020) \u201cAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale\u201d, Accessed: Aug. 12, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2010.11929v2"},{"issue":"2","key":"14350_CR13","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (Jun. 2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338. https:\/\/doi.org\/10.1007\/s11263-009-0275-4","journal-title":"Int J Comput Vis"},{"key":"14350_CR14","doi-asserted-by":"publisher","unstructured":"Gkioxari G, Girshick R, Malik J (2015) \u201cContextual action recognition with R\u2217CNN,\u201d Proc. IEEE Int. Conf. Comput. Vis., vol. 2015 Inter, pp 1080\u20131088 https:\/\/doi.org\/10.1109\/ICCV.2015.129","DOI":"10.1109\/ICCV.2015.129"},{"issue":"10","key":"14350_CR15","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","volume":"47","author":"G Guo","year":"2014","unstructured":"Guo G, Lai A (2014) A survey on still image based human action recognition. Pattern Recogn 47(10):3343\u20133361. https:\/\/doi.org\/10.1016\/j.patcog.2014.04.018","journal-title":"Pattern Recogn"},{"key":"14350_CR16","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \u201cDeep residual learning for image recognition,\u201d in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2016-December, pp. 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"14350_CR17","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","volume":"42","author":"K He","year":"2020","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (Feb. 2020) Mask R-CNN. IEEE Trans Pattern Anal Mach Intell 42(2):386\u2013397. https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14350_CR18","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.imavis.2017.01.010","volume":"60","author":"S Herath","year":"2017","unstructured":"Herath S, Harandi M, Porikli F (2017) Going deeper into action recognition: a survey. Image Vis Comput 60:4\u201321. https:\/\/doi.org\/10.1016\/j.imavis.2017.01.010","journal-title":"Image Vis Comput"},{"key":"14350_CR19","unstructured":"Hinton G, Vinyals O, Dean J (2015) \u201cDistilling the Knowledge in a Neural Network\u201d, Accessed: Aug. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1503.02531v1."},{"issue":"20","key":"14350_CR20","doi-asserted-by":"publisher","first-page":"28515","DOI":"10.1007\/S11042-017-5496-X","volume":"78","author":"T Hu","year":"2018","unstructured":"Hu T, Zhu X, Guo W, Wang S, Zhu J (Feb. 2018) Human action recognition based on scene semantics. Multimed Tools Appl 2018 7820 78(20):28515\u201328536. https:\/\/doi.org\/10.1007\/S11042-017-5496-X","journal-title":"Multimed Tools Appl 2018 7820"},{"key":"14350_CR21","doi-asserted-by":"crossref","unstructured":"Kim S, Yun K, Park J, Choi JY (2019) \u201cSkeleton-based Action Recognition of People Handling Objects\u201d, Proc. - 2019 IEEE Winter Conf. Appl. Comput. Vision, WACV 2019, pp. 61\u201370, Accessed: Aug. 13, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1901.06882v1","DOI":"10.1109\/WACV.2019.00014"},{"key":"14350_CR22","unstructured":"Kipf TN, Welling M(2016) \u201cSemi-Supervised Classification with Graph Convolutional Networks,\u201d 5th Int. Conf. Learn. Represent. ICLR 2017 - Conf. Track Proc., Accessed: Aug. 13, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1609.02907v4"},{"key":"14350_CR23","doi-asserted-by":"publisher","unstructured":"Li LJ, Fei-Fei L (2007) \u201cWhat, where and who? Classifying events by scene and object recognition\u201d, https:\/\/doi.org\/10.1109\/ICCV.2007.4408872","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"14350_CR24","doi-asserted-by":"publisher","first-page":"107341","DOI":"10.1016\/j.patcog.2020.107341","volume":"104","author":"Y Li","year":"2020","unstructured":"Li Y, Li K, Wang X (Aug. 2020) Recognizing actions in images by fusing multiple body structure cues. Pattern Recogn 104:107341. https:\/\/doi.org\/10.1016\/j.patcog.2020.107341","journal-title":"Pattern Recogn"},{"issue":"5","key":"14350_CR25","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1109\/JSTSP.2020.3002391","volume":"14","author":"X Liao","year":"2020","unstructured":"Liao X, Li K, Zhu X, Liu KJR (Aug. 2020) Robust detection of image operator chain with two-stream convolutional neural network. IEEE J Sel Top Signal Proc 14(5):955\u2013968. https:\/\/doi.org\/10.1109\/JSTSP.2020.3002391","journal-title":"IEEE J Sel Top Signal Proc"},{"key":"14350_CR26","doi-asserted-by":"publisher","unstructured":"Liu L, Tan RT, You S (2019) \u201cLoss Guided Activation for Action Recognition in Still Images\u201d, in Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 11365 LNCS, pp. 152\u2013167, https:\/\/doi.org\/10.1007\/978-3-030-20873-8_10","DOI":"10.1007\/978-3-030-20873-8_10"},{"key":"14350_CR27","doi-asserted-by":"publisher","unstructured":"Ludl D, Gulde T, Curio C (2019) \u201cSimple yet efficient real-time pose-based action recognition\u201d, in 2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019, pp. 581\u2013588, https:\/\/doi.org\/10.1109\/ITSC.2019.8917128","DOI":"10.1109\/ITSC.2019.8917128"},{"key":"14350_CR28","doi-asserted-by":"publisher","unstructured":"Ma W, Liang S (2020) \u201cHuman-object relation network for action recognition in still images\u201d, Proc. - IEEE Int. Conf. Multimed. Expo, vol. 2020-July, https:\/\/doi.org\/10.1109\/ICME46284.2020.9102933.","DOI":"10.1109\/ICME46284.2020.9102933"},{"key":"14350_CR29","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.patcog.2017.01.027","volume":"68","author":"S Ma","year":"2017","unstructured":"Ma S, Bargal SA, Zhang J, Sigal L, Sclaroff S (Aug. 2017) Do less and achieve more: training CNNs for action recognition utilizing action images from the web. Pattern Recogn 68:334\u2013345. https:\/\/doi.org\/10.1016\/j.patcog.2017.01.027","journal-title":"Pattern Recogn"},{"key":"14350_CR30","unstructured":"Maji S, Bourdev L, Malik J \u201cAction Recognition from a Distributed Representation of Pose and Appearance\u201d"},{"key":"14350_CR31","doi-asserted-by":"publisher","unstructured":"McAuley J, Leskovec J (2012) \u201cImage labeling on a network: Using social-network metadata for image classification,\u201d in Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), vol. 7575 LNCS, no. PART 4, pp. 828\u2013841, https:\/\/doi.org\/10.1007\/978-3-642-33765-9_59.","DOI":"10.1007\/978-3-642-33765-9_59"},{"key":"14350_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/S10489-021-02760-1","volume":"2021","author":"S Mi","year":"2021","unstructured":"Mi S, Zhang Y (2021) Pose-guided action recognition in static images using lie-group. Appl Intell 2021:1\u20139. https:\/\/doi.org\/10.1007\/S10489-021-02760-1","journal-title":"Appl Intell"},{"key":"14350_CR33","doi-asserted-by":"publisher","unstructured":"Mohammadi S, Majelan SG, Shokouhi SB (2019) \u201cEnsembles of deep neural networks for action recognition in still images\u201d, 2019 9th Int. Conf. Comput. Knowl. Eng. ICCKE 2019, pp. 315\u2013318, https:\/\/doi.org\/10.1109\/ICCKE48569.2019.8965014","DOI":"10.1109\/ICCKE48569.2019.8965014"},{"key":"14350_CR34","unstructured":"Procesi C (2007) \u201cLie groups\u00a0: an approach through invariants and representations,\u201d p. 596"},{"key":"14350_CR35","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.neucom.2017.06.041","volume":"267","author":"T Qi","year":"2017","unstructured":"Qi T, Xu Y, Quan Y, Wang Y, Ling H (Dec. 2017) Image-based action recognition using hint-enhanced deep neural networks. Neurocomputing 267:475\u2013488. https:\/\/doi.org\/10.1016\/j.neucom.2017.06.041","journal-title":"Neurocomputing"},{"issue":"6","key":"14350_CR36","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"14350_CR37","doi-asserted-by":"publisher","first-page":"16185","DOI":"10.1007\/S11042-019-08576-Z","volume":"80","author":"Z Ren","year":"2020","unstructured":"Ren Z, Zhang Q, Gao X, Hao P, Cheng J (Mar. 2020) Multi-modality learning for human action recognition. Multimed Tools Appl 2020 8011 80(11):16185\u201316203. https:\/\/doi.org\/10.1007\/S11042-019-08576-Z","journal-title":"Multimed Tools Appl 2020 8011"},{"key":"14350_CR38","unstructured":"Simonyan K, Zisserman A, \u201cTwo-Stream Convolutional Networks for Action Recognition in Videos.\u201d"},{"key":"14350_CR39","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) \u201cRethinking the Inception Architecture for Computer Vision\u201d, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-December, pp. 2818\u20132826, Accessed: Aug. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1512.00567v3."},{"key":"14350_CR40","doi-asserted-by":"publisher","unstructured":"Szegedy C et al. (2015) \u201cGoing deeper with convolutions\u201d, in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07\u201312-June-2015, pp. 1\u20139, https:\/\/doi.org\/10.1109\/CVPR.2015.7298594","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"14350_CR41","doi-asserted-by":"crossref","unstructured":"C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi (2016) \u201cInception-v4, Inception-ResNet and the Impact of Residual Connections on Learning,\u201d 31st AAAI Conf. Artif. Intell. AAAI 2017, pp. 4278\u20134284, Accessed: Aug. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1602.07261v2","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"14350_CR42","unstructured":"Tran D, Wang H, Torresani L, Ray J, LeCun Y, Paluri M (2017) \u201cA Closer Look at Spatiotemporal Convolutions for Action Recognition,\u201d Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 6450\u20136459, Accessed: Aug. 13, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1711.11248v3"},{"key":"14350_CR43","doi-asserted-by":"publisher","unstructured":"Wang J, Liang S, \u201cPose-Enhanced Relation Feature for Action Recognition in Still Images\u201d (2022) pp. 154\u2013165, https:\/\/doi.org\/10.1007\/978-3-030-98358-1_13","DOI":"10.1007\/978-3-030-98358-1_13"},{"issue":"11","key":"14350_CR44","doi-asserted-by":"publisher","first-page":"7413","DOI":"10.1007\/S11042-019-08535-8","volume":"79","author":"X Wang","year":"2019","unstructured":"Wang X, Qi C (Dec. 2019) Detecting action-relevant regions for action recognition using a three-stage saliency detection technique. Multimed Tools Appl 2019 7911 79(11):7413\u20137433. https:\/\/doi.org\/10.1007\/S11042-019-08535-8","journal-title":"Multimed Tools Appl 2019 7911"},{"key":"14350_CR45","doi-asserted-by":"publisher","unstructured":"Wang C, Yang H, Meinel C (2016) \u201cExploring multimodal video representation for action recognition,\u201d Proc. Int. Jt. Conf. Neural Networks, vol. 2016-October, pp. 1924\u20131931, https:\/\/doi.org\/10.1109\/IJCNN.2016.7727435","DOI":"10.1109\/IJCNN.2016.7727435"},{"key":"14350_CR46","doi-asserted-by":"publisher","unstructured":"Xin M, Wang S, Cheng J (2019) \u201cEntanglement loss for context-based still image action recognition,\u201d in Proceedings - IEEE International Conference on Multimedia and Expo, vol. 2019-July, pp. 1042\u20131047, https:\/\/doi.org\/10.1109\/ICME.2019.00183","DOI":"10.1109\/ICME.2019.00183"},{"issue":"17","key":"14350_CR47","doi-asserted-by":"publisher","first-page":"25063","DOI":"10.1007\/S11042-019-7593-5","volume":"78","author":"Y Xu","year":"2019","unstructured":"Xu Y, Hou Z, Liang J, Chen C, Jia L, Song Y (May 2019) Action recognition using weighted fusion of depth images and skeleton\u2019s key frames. Multimed Tools Appl 2019 7817 78(17):25063\u201325078. https:\/\/doi.org\/10.1007\/S11042-019-7593-5","journal-title":"Multimed Tools Appl 2019 7817"},{"issue":"4","key":"14350_CR48","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1109\/TCDS.2017.2783944","volume":"10","author":"S Yan","year":"2018","unstructured":"Yan S, Smith JS, Lu W, Zhang B (Dec. 2018) Multibranch attention networks for action recognition in still images. IEEE Trans Cogn Dev Syst 10(4):1116\u20131125. https:\/\/doi.org\/10.1109\/TCDS.2017.2783944","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"14350_CR49","doi-asserted-by":"publisher","unstructured":"Yao B, Jiang X, Khosla A, Lin AL, Guibas L, Fei-Fei L (2011) \u201cHuman action recognition by learning bases of action attributes and parts,\u201d in Proceedings of the IEEE International Conference on Computer Vision, pp. 1331\u20131338, https:\/\/doi.org\/10.1109\/ICCV.2011.6126386","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"14350_CR50","doi-asserted-by":"publisher","unstructured":"Zhang Y, Chu J, Leng L, Miao J (2020) Mask-Refined R-CNN: A Network for Refining Object Details in Instance Segmentation. Sensors (Basel) 20(4). https:\/\/doi.org\/10.3390\/S20041010","DOI":"10.3390\/S20041010"},{"key":"14350_CR51","doi-asserted-by":"publisher","unstructured":"Zhao Z, Ma H, You S (2017) \u201cSingle Image Action Recognition Using Semantic Body Part Actions,\u201d in Proceedings of the IEEE International Conference on Computer Vision, vol. 2017-October, pp. 3411\u20133419, https:\/\/doi.org\/10.1109\/ICCV.2017.367","DOI":"10.1109\/ICCV.2017.367"},{"key":"14350_CR52","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/J.NEUCOM.2020.07.016","volume":"413","author":"Y Zheng","year":"2020","unstructured":"Zheng Y, Zheng X, Lu X, Wu S (Nov. 2020) Spatial attention based visual semantic learning for action recognition in still images. Neurocomputing 413:383\u2013396. https:\/\/doi.org\/10.1016\/J.NEUCOM.2020.07.016","journal-title":"Neurocomputing"},{"key":"14350_CR53","unstructured":"Zhu Y et al. (2020) \u201cA Comprehensive Study of Deep Video Action Recognition\u201d, Accessed: Aug. 12, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/2012.06567v1."},{"key":"14350_CR54","unstructured":"Zoph B, Vasudevan V, Shlens J, Le QV (2017) \u201cLearning Transferable Architectures for Scalable Image Recognition\u201d, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 8697\u20138710, Accessed: Aug. 11, 2021. [Online]. Available: https:\/\/arxiv.org\/abs\/1707.07012v4."}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14350-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14350-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14350-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T19:54:58Z","timestamp":1687550098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14350-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":54,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["14350"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14350-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,10]]},"assertion":[{"value":"13 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 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":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}