{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:07:36Z","timestamp":1775743656383,"version":"3.50.1"},"reference-count":83,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T00:00:00Z","timestamp":1643500800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T00:00:00Z","timestamp":1643500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Still image human action recognition (HAR) is a challenging problem owing to limited sources of information and large intra-class and small inter-class variations which requires highly discriminative features. Transfer learning offers the necessary capabilities in producing such features by preserving prior knowledge while learning new representations. However, optimally identifying dynamic numbers of re-trainable layers in the transfer learning process poses a challenge. In this study, we aim to automate the process of optimal configuration identification. Specifically, we propose a novel particle swarm optimisation (PSO) variant, denoted as EnvPSO, for optimal hyper-parameter selection in the transfer learning process with respect to HAR tasks with still images. It incorporates Gaussian fitness surface prediction and exponential search coefficients to overcome stagnation. It optimises the learning rate, batch size, and number of re-trained layers of a pre-trained convolutional neural network (CNN). To overcome bias of single optimised networks, an ensemble model with three optimised CNN streams is introduced. The first and second streams employ raw images and segmentation masks yielded by mask R-CNN as inputs, while the third stream fuses a pair of networks with raw image and saliency maps as inputs, respectively. The final prediction results are obtained by computing the average of class predictions from all three streams. By leveraging differences between learned representations within optimised streams, our ensemble model outperforms counterparts devised by PSO and other state-of-the-art methods for HAR. In addition, evaluated using diverse artificial landscape functions, EnvPSO performs better than other search methods with statistically significant difference in performance.<\/jats:p>","DOI":"10.1007\/s00521-022-06947-6","type":"journal-article","created":{"date-parts":[[2022,1,30]],"date-time":"2022-01-30T11:03:27Z","timestamp":1643540607000},"page":"9205-9231","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["An evolving ensemble model of multi-stream convolutional neural networks for human action recognition in still images"],"prefix":"10.1007","volume":"34","author":[{"given":"Sam","family":"Slade","sequence":"first","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yonghong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Chee Peng","family":"Lim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,30]]},"reference":[{"issue":"10","key":"6947_CR1","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 Recognit 47(10):3343\u20133361","journal-title":"Pattern Recognit"},{"key":"6947_CR2","doi-asserted-by":"crossref","unstructured":"Zheng Y, Zhang Y-J, Li X, Liu B-D (2012) Action recognition in still images using a combination of human pose and context information. In: 2012 19th IEEE International Conference on Image Processing, pp. 785\u2013788 . IEEE","DOI":"10.1109\/ICIP.2012.6466977"},{"key":"6947_CR3","doi-asserted-by":"crossref","unstructured":"Thurau C, Hlav\u00e1c, V (2008) Pose primitive based human action recognition in videos or still images. In: 2008 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20138. IEEE","DOI":"10.1109\/CVPR.2008.4587721"},{"key":"6947_CR4","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D, Fowlkes C (2010) Discriminative models for static human-object interactions. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops, pp. 9\u201316. IEEE","DOI":"10.1109\/CVPRW.2010.5543176"},{"key":"6947_CR5","doi-asserted-by":"crossref","unstructured":"Shapovalova N, Gong W, Pedersoli M, Roca FX, Gonzalez J (2011) On importance of interactions and context in human action recognition. In: Iberian Conference on Pattern Recognition and Image Analysis, pp. 58\u201366. Springer","DOI":"10.1007\/978-3-642-21257-4_8"},{"key":"6947_CR6","doi-asserted-by":"crossref","unstructured":"Li, L.-J., Fei-Fei L (2007) What, where and who? classifying events by scene and object recognition. In: 2007 IEEE 11th International Conference on Computer Vision, pp. 1\u20138. IEEE","DOI":"10.1109\/ICCV.2007.4408872"},{"issue":"10","key":"6947_CR7","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TPAMI.2009.83","volume":"31","author":"A Gupta","year":"2009","unstructured":"Gupta A, Kembhavi A, Davis LS (2009) Observing human-object interactions: using spatial and functional compatibility for recognition. IEEE Trans Pattern Anal Mach Intell 31(10):1775\u20131789","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6947_CR8","doi-asserted-by":"crossref","unstructured":"Maji S, Bourdev L, Malik J (2011) Action recognition from a distributed representation of pose and appearance. In: CVPR 2011, pp. 3177\u20133184. IEEE","DOI":"10.1109\/CVPR.2011.5995631"},{"key":"6947_CR9","doi-asserted-by":"crossref","unstructured":"Desai C, Ramanan D (2012) Detecting actions, poses, and objects with relational phraselets. In: European Conference on Computer Vision, pp. 158\u2013172. Springer","DOI":"10.1007\/978-3-642-33765-9_12"},{"key":"6947_CR10","first-page":"1503","volume":"24","author":"V Delaitre","year":"2011","unstructured":"Delaitre V, Sivic J, Laptev I (2011) Learning person-object interactions for action recognition in still images. Adv Neural Inform Process Syst 24:1503\u20131511","journal-title":"Adv Neural Inform Process Syst"},{"key":"6947_CR11","doi-asserted-by":"crossref","unstructured":"Sener F, Bas C, Ikizler-Cinbis N (2012) On recognizing actions in still images via multiple features. In: European Conference on Computer Vision, pp. 263\u2013272. Springer","DOI":"10.1007\/978-3-642-33885-4_27"},{"issue":"9","key":"6947_CR12","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1109\/TPAMI.2012.67","volume":"34","author":"B Yao","year":"2012","unstructured":"Yao B, Fei-Fei L (2012) Recognizing human-object interactions in still images by modeling the mutual context of objects and human poses. IEEE Trans Pattern Anal Mach Intell 34(9):1691\u20131703","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6947_CR13","unstructured":"Yao B, Khosla A, Fei-Fei L (2011) Classifying actions and measuring action similarity by modeling the mutual context of objects and human poses. a) A 1(D2), p. 3"},{"key":"6947_CR14","doi-asserted-by":"crossref","unstructured":"Li P, Ma J (2011) What is happening in a still picture? In: The First Asian Conference on Pattern Recognition, pp. 32\u201336. IEEE","DOI":"10.1109\/ACPR.2011.6166555"},{"key":"6947_CR15","doi-asserted-by":"crossref","unstructured":"Le DT, Bernardi R, Uijlings J (2013) Exploiting language models to recognize unseen actions. In: Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval, pp. 231\u2013238","DOI":"10.1145\/2461466.2461504"},{"key":"6947_CR16","doi-asserted-by":"crossref","unstructured":"Yao B, Jiang X, Khosla A, Lin AL, Guibas L, Fei-Fei L (2011) Human action recognition by learning bases of action attributes and parts. In: 2011 International Conference on Computer Vision, pp. 1331\u20131338. IEEE","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"6947_CR17","doi-asserted-by":"crossref","unstructured":"Delaitre V, Laptev I, Sivic J (2010) Recognizing human actions in still images: a study of bag-of-features and part-based representations. In: BMVC 2010-21st British Machine Vision Conference, pp. 1\u201311","DOI":"10.5244\/C.24.97"},{"key":"6947_CR18","doi-asserted-by":"crossref","unstructured":"Qazi HA, Jahangir U, Yousuf BM, Noor A (2017) Human action recognition using SIFT and HOG method. In: 2017 International Conference on Information and Communication Technologies (ICICT), pp. 6\u201310. IEEE","DOI":"10.1109\/ICICT.2017.8320156"},{"key":"6947_CR19","doi-asserted-by":"crossref","unstructured":"Sharma G, Jurie F, Schmid C (2013) Expanded parts model for human attribute and action recognition in still images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013659","DOI":"10.1109\/CVPR.2013.90"},{"key":"6947_CR20","doi-asserted-by":"crossref","unstructured":"Dhulavvagol PM, Kundur NC (2017) Human action detection and recognition using SIFT and SVM. In: International Conference on Cognitive Computing and Information Processing, pp. 475\u2013491. Springer","DOI":"10.1007\/978-981-10-9059-2_42"},{"key":"6947_CR21","doi-asserted-by":"crossref","unstructured":"Li B, Xiao R, Li Z, Cai R, Lu B-L, Zhang L (2011) Rank-SIFT: Learning to rank repeatable local interest points. In: CVPR 2011, pp. 1737\u20131744. IEEE","DOI":"10.1109\/CVPR.2011.5995461"},{"issue":"2","key":"6947_CR22","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"6947_CR23","doi-asserted-by":"publisher","first-page":"128564","DOI":"10.1109\/ACCESS.2021.3104387","volume":"9","author":"P Kreowsky","year":"2021","unstructured":"Kreowsky P, Stabernack B (2021) A Full-featured FPGA-Based pipelined architecture for SIFT extraction. IEEE Access 9:128564\u2013128573","journal-title":"IEEE Access"},{"key":"6947_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.107704","volume":"158","author":"MF Aslan","year":"2020","unstructured":"Aslan MF, Durdu A, Sabanci K, Mutluer MA (2020) CNN and HOG based comparison study for complete occlusion handling in human tracking. Measurement 158:107704","journal-title":"Measurement"},{"key":"6947_CR25","doi-asserted-by":"crossref","unstructured":"Wang X, Han TX, Yan S (2009) An HOG-LBP human detector with partial occlusion handling. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 32\u201339. IEEE","DOI":"10.1109\/ICCV.2009.5459207"},{"issue":"18","key":"6947_CR26","doi-asserted-by":"publisher","first-page":"3823","DOI":"10.1016\/j.neucom.2011.07.024","volume":"74","author":"H Yang","year":"2011","unstructured":"Yang H, Shao L, Zheng F, Wang L, Song Z (2011) Recent advances and trends in visual tracking: a review. Neurocomputing 74(18):3823\u20133831","journal-title":"Neurocomputing"},{"key":"6947_CR27","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0079-6123(06)55002-2","volume":"155","author":"A Oliva","year":"2006","unstructured":"Oliva A, Torralba A (2006) Building the gist of a scene: the role of global image features in recognition. Prog Brain Res 155:23\u201336","journal-title":"Prog Brain Res"},{"issue":"2","key":"6947_CR28","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TPAMI.2007.40","volume":"29","author":"C Siagian","year":"2007","unstructured":"Siagian C, Itti L (2007) Rapid biologically-inspired scene classification using features shared with visual attention. IEEE Trans Pattern Anal Mach Intell 29(2):300\u2013312","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"6947_CR29","first-page":"609","volume":"20","author":"B Xie","year":"2018","unstructured":"Xie B, Qin J, Xiang X, Li H, Pan L (2018) An image retrieval algorithm based on gist and sift features. Int J Netw Secur 20(4):609\u2013616","journal-title":"Int J Netw Secur"},{"key":"6947_CR30","doi-asserted-by":"publisher","first-page":"106918","DOI":"10.1016\/j.knosys.2021.106918","volume":"220","author":"L Zhang","year":"2021","unstructured":"Zhang L, Lim CP, Yu Y (2021) Intelligent human action recognition using an ensemble model of evolving deep networks with swarm-based optimization. Knowledge-Based Sys 220:106918","journal-title":"Knowledge-Based Sys"},{"key":"6947_CR31","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. arXiv preprint arXiv:1406.2199"},{"issue":"6","key":"6947_CR32","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3390\/jimaging6060046","volume":"6","author":"M Al-Faris","year":"2020","unstructured":"Al-Faris M, Chiverton J, Ndzi D, Ahmed AI (2020) A review on computer vision-based methods for human action recognition. J Imaging 6(6):46","journal-title":"J Imaging"},{"issue":"18","key":"6947_CR33","doi-asserted-by":"publisher","first-page":"8324","DOI":"10.3390\/app11188324","volume":"11","author":"B Degardin","year":"2021","unstructured":"Degardin B, Proen\u00e7a H (2021) Human behavior analysis: a survey on action recognition. Appl Sci 11(18):8324","journal-title":"Appl Sci"},{"issue":"5","key":"6947_CR34","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3390\/s19051005","volume":"19","author":"H-B Zhang","year":"2019","unstructured":"Zhang H-B, Zhang Y-X, Zhong B, Lei Q, Yang L, Du J-X, Chen D-S (2019) A comprehensive survey of vision-based human action recognition methods. Sensors 19(5):1005","journal-title":"Sensors"},{"key":"6947_CR35","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.patrec.2018.05.018","volume":"118","author":"G Yao","year":"2019","unstructured":"Yao G, Lei T, Zhong J (2019) A review of convolutional-neural-network-based action recognition. Pattern Recognit Lett 118:14\u201322","journal-title":"Pattern Recognit Lett"},{"key":"6947_CR36","unstructured":"Kong Y, Fu Y (2018) Human action recognition and prediction: a survey. arXiv preprint arXiv:1806.11230"},{"key":"6947_CR37","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.knosys.2016.08.018","volume":"111","author":"L Zhang","year":"2016","unstructured":"Zhang L, Mistry K, Neoh SC, Lim CP (2016) Intelligent facial emotion recognition using moth-firefly optimization. Knowl-Based Syst 111:248\u2013267","journal-title":"Knowl-Based Syst"},{"issue":"23","key":"6947_CR38","doi-asserted-by":"publisher","first-page":"7936","DOI":"10.3390\/s21237936","volume":"21","author":"T Lawrence","year":"2021","unstructured":"Lawrence T, Zhang L, Rogage K, Lim CP (2021) Evolving deep architecture generation with residual connections for image classification using particle swarm optimization. Sensors 21(23):7936","journal-title":"Sensors"},{"key":"6947_CR39","doi-asserted-by":"publisher","first-page":"104807","DOI":"10.1016\/j.knosys.2019.06.015","volume":"187","author":"TY Tan","year":"2020","unstructured":"Tan TY, Zhang L, Lim CP (2020) Adaptive melanoma diagnosis using evolving clustering, ensemble and deep neural networks. Knowl-Based Syst 187:104807","journal-title":"Knowl-Based Syst"},{"key":"6947_CR40","doi-asserted-by":"publisher","first-page":"34004","DOI":"10.1109\/ACCESS.2019.2903015","volume":"7","author":"TY Tan","year":"2019","unstructured":"Tan TY, Zhang L, Lim CP, Fielding B, Yu Y, Anderson E (2019) Evolving ensemble models for image segmentation using enhanced particle swarm optimization. IEEE Access 7:34004\u201334019","journal-title":"IEEE Access"},{"key":"6947_CR41","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6947_CR42","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.swevo.2019.06.002","volume":"49","author":"Y Wang","year":"2019","unstructured":"Wang Y, Zhang H, Zhang G (2019) cPSO-CNN: An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks. Swarm and Evol Comput 49:114\u2013123","journal-title":"Swarm and Evol Comput"},{"key":"6947_CR43","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cmpb.2018.05.006","volume":"162","author":"GLF da Silva","year":"2018","unstructured":"da Silva GLF, Valente TLA, Silva AC, de Paiva AC, Gattass M (2018) Convolutional neural network-based PSO for lung nodule false positive reduction on CT images. Comput Methods Prog Biomed 162:109\u2013118","journal-title":"Comput Methods Prog Biomed"},{"issue":"8","key":"6947_CR44","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1049\/iet-its.2018.5127","volume":"12","author":"FC Soon","year":"2018","unstructured":"Soon FC, Khaw HY, Chuah JH, Kanesan J (2018) Hyper-parameters optimisation of deep CNN architecture for vehicle logo recognition. IET Intell Trans Syst 12(8):939\u2013946","journal-title":"IET Intell Trans Syst"},{"key":"6947_CR45","doi-asserted-by":"publisher","first-page":"105725","DOI":"10.1016\/j.asoc.2019.105725","volume":"84","author":"TY Tan","year":"2019","unstructured":"Tan TY, Zhang L, Lim CP (2019) Intelligent skin cancer diagnosis using improved particle swarm optimization and deep learning models. Appl Soft Comput 84:105725","journal-title":"Appl Soft Comput"},{"key":"6947_CR46","doi-asserted-by":"publisher","first-page":"68560","DOI":"10.1109\/ACCESS.2018.2880416","volume":"6","author":"B Fielding","year":"2018","unstructured":"Fielding B, Zhang L (2018) Evolving image classification architectures with enhanced particle swarm optimisation. IEEE Access 6:68560\u201368575","journal-title":"IEEE Access"},{"issue":"1","key":"6947_CR47","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1):67\u201382","journal-title":"IEEE Trans Evol Comput"},{"issue":"6","key":"6947_CR48","doi-asserted-by":"publisher","first-page":"1496","DOI":"10.1109\/TCYB.2016.2549639","volume":"47","author":"K Mistry","year":"2016","unstructured":"Mistry K, Zhang L, Neoh SC, Lim CP, Fielding B (2016) A micro-GA embedded PSO feature selection approach to intelligent facial emotion recognition. IEEE Trans Cybernet 47(6):1496\u20131509","journal-title":"IEEE Trans Cybernet"},{"issue":"11","key":"6947_CR49","doi-asserted-by":"publisher","first-page":"1880","DOI":"10.3390\/electronics9111880","volume":"9","author":"B Fielding","year":"2020","unstructured":"Fielding B, Zhang L (2020) Evolving deep denseBlock architecture ensembles for image classification. Electronics 9(11):1880","journal-title":"Electronics"},{"key":"6947_CR50","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.swevo.2017.09.001","volume":"39","author":"MS Nobile","year":"2018","unstructured":"Nobile MS, Cazzaniga P, Besozzi D, Colombo R, Mauri G, Pasi G (2018) Fuzzy Self-tuning PSO: a settings-free algorithm for global optimization. Swarm Evol Comput 39:70\u201385","journal-title":"Swarm Evol Comput"},{"key":"6947_CR51","doi-asserted-by":"publisher","first-page":"100863","DOI":"10.1016\/j.swevo.2021.100863","volume":"63","author":"P Singh","year":"2021","unstructured":"Singh P, Chaudhury S, Panigrahi BK (2021) Hybrid MPSO-CNN: Multi-level particle swarm optimized hyperparameters of convolutional neural network. Swarm and Evol Comput 63:100863","journal-title":"Swarm and Evol Comput"},{"key":"6947_CR52","doi-asserted-by":"crossref","unstructured":"Bai B, Zhang J, Wu X, wei Zhu G, Li X (2021) Reliability prediction-based improved dynamic weight particle swarm optimization and back propagation neural network in engineering systems. Exp Syst Appl 177:114952","DOI":"10.1016\/j.eswa.2021.114952"},{"key":"6947_CR53","doi-asserted-by":"publisher","first-page":"40625","DOI":"10.1109\/ACCESS.2019.2906082","volume":"7","author":"R Lan","year":"2019","unstructured":"Lan R, Zhang L, Tang Z, Liu Z, Luo X (2019) A hierarchical sorting swarm optimizer for large-scale optimization. IEEE Access 7:40625\u201340635","journal-title":"IEEE Access"},{"issue":"11","key":"6947_CR54","doi-asserted-by":"publisher","first-page":"3067","DOI":"10.1109\/TCYB.2017.2756874","volume":"48","author":"H Han","year":"2017","unstructured":"Han H, Lu W, Zhang L, Qiao J (2017) Adaptive gradient multiobjective particle swarm optimization. IEEE Trans Cybernet 48(11):3067\u20133079","journal-title":"IEEE Trans Cybernet"},{"issue":"2","key":"6947_CR55","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1162\/106365600568202","volume":"8","author":"E Zitzler","year":"2000","unstructured":"Zitzler E, Deb K, Thiele L (2000) Comparison of multiobjective evolutionary algorithms: empirical results. Evol Comput 8(2):173\u2013195","journal-title":"Evol Comput"},{"key":"6947_CR56","doi-asserted-by":"crossref","unstructured":"Deb K, Thiele L, Laumanns M, Zitzler E (2005) Scalable test problems for evolutionary multiobjective optimization. In: Evolutionary Multiobjective Optimization, pp. 105\u2013145. Springer, London","DOI":"10.1007\/1-84628-137-7_6"},{"key":"6947_CR57","doi-asserted-by":"publisher","first-page":"88200","DOI":"10.1109\/ACCESS.2020.2992903","volume":"8","author":"J Cai","year":"2020","unstructured":"Cai J, Wei H, Yang H, Zhao X (2020) A novel clustering algorithm based on DPC and PSO. IEEE Access 8:88200\u201388214","journal-title":"IEEE Access"},{"issue":"1","key":"6947_CR58","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2016.2537325","volume":"39","author":"G Sharma","year":"2016","unstructured":"Sharma G, Jurie F, Schmid C (2016) Expanded parts model for semantic description of humans in still images. IEEE Trans Pattern Anal Mach Intell 39(1):87\u2013101","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"6947_CR59","doi-asserted-by":"publisher","first-page":"5479","DOI":"10.1109\/TIP.2016.2605305","volume":"25","author":"Y Zhang","year":"2016","unstructured":"Zhang Y, Cheng L, Wu J, Cai J, Do MN, Lu J (2016) Action recognition in still images with minimum annotation efforts. IEEE Trans Image Process 25(11):5479\u20135490","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"6947_CR60","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/TCSVT.2016.2586853","volume":"28","author":"J Wang","year":"2016","unstructured":"Wang J, Wang G (2016) Hierarchical spatial sum-product networks for action recognition in still images. IEEE Trans Circuits Syst Video Technol 28(1):90\u2013100","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6947_CR61","doi-asserted-by":"crossref","unstructured":"Li J, Wong Y, Zhao Q, Kankanhalli MS (2017) Attention transfer from web images for video recognition. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1\u20139","DOI":"10.1145\/3123266.3123432"},{"key":"6947_CR62","unstructured":"Safaei M (2020) Action recognition in still images: confluence of multilinear methods and deep learning methods and deep learning. PhD thesis, University of Central Florida"},{"key":"6947_CR63","doi-asserted-by":"crossref","unstructured":"Yu X, Zhang Z, Wu L, Pang W, Chen H, Yu Z, Li B (2020) Deep ensemble learning for human action recognition in still images. Complexity 2020, 1\u201323. Article ID 9428612","DOI":"10.1155\/2020\/9428612"},{"key":"6947_CR64","doi-asserted-by":"crossref","unstructured":"Liu L, Tan RT, You S (2018) Loss guided activation for action recognition in still images. In: Asian Conference on Computer Vision, pp. 152\u2013167. Springer","DOI":"10.1007\/978-3-030-20873-8_10"},{"issue":"4","key":"6947_CR65","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1109\/TCDS.2017.2783944","volume":"10","author":"S Yan","year":"2017","unstructured":"Yan S, Smith JS, Lu W, Zhang B (2017) Multibranch attention networks for action recognition in still images. IEEE Trans Cognit Develop Syst 10(4):1116\u20131125","journal-title":"IEEE Trans Cognit Develop Syst"},{"key":"6947_CR66","unstructured":"Masters D, Luschi C (2018) Revisiting small batch training for deep neural networks. arXiv preprint arXiv:1804.07612"},{"key":"6947_CR67","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Doll\u00e1r P, Girshick R (2017) Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969","DOI":"10.1109\/ICCV.2017.322"},{"key":"6947_CR68","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 (2017) Do less and achieve more: training CNNs for action recognition utilizing action images from the web. Pattern Recognit 68:334\u2013345","journal-title":"Pattern Recognit"},{"key":"6947_CR69","doi-asserted-by":"crossref","unstructured":"Safaei M, Foroosh H (2019) Still image action recognition by predicting spatial-temporal pixel evolution. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 111\u2013120. IEEE","DOI":"10.1109\/WACV.2019.00019"},{"key":"6947_CR70","doi-asserted-by":"crossref","unstructured":"Sharma G, Jurie F, Schmid C (2012) Discriminative spatial saliency for image classification. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3506\u20133513. IEEE","DOI":"10.1109\/CVPR.2012.6248093"},{"key":"6947_CR71","doi-asserted-by":"crossref","unstructured":"Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201906), vol. 2, pp. 2169\u20132178. IEEE","DOI":"10.1109\/CVPR.2006.68"},{"key":"6947_CR72","doi-asserted-by":"crossref","unstructured":"Safaei M, Balouchian P, Foroosh H (2002) UCF-STAR: A large scale still image dataset for understanding human actions. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 2677\u20132684","DOI":"10.1609\/aaai.v34i03.5653"},{"key":"6947_CR73","unstructured":"Alraimi ASA (2019) Development of new models for vision-based human activity recognition. PhD thesis, Universitat Rovira i Virgili"},{"key":"6947_CR74","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.knosys.2018.05.002","volume":"156","author":"D Pandit","year":"2018","unstructured":"Pandit D, Zhang L, Chattopadhyay S, Lim CP, Liu C (2018) A scattering and repulsive swarm intelligence algorithm for solving global optimization problems. Knowl-Based Syst 156:12\u201342","journal-title":"Knowl-Based Syst"},{"key":"6947_CR75","doi-asserted-by":"crossref","unstructured":"Zhang L, Lim CP, Yu Y, Jiang M (2021) Sound classification using evolving ensemble models and Particle Swarm Optimization. Appl Soft Comput, p. 108322","DOI":"10.1016\/j.asoc.2021.108322"},{"key":"6947_CR76","doi-asserted-by":"publisher","first-page":"106328","DOI":"10.1016\/j.asoc.2020.106328","volume":"92","author":"L Zhang","year":"2020","unstructured":"Zhang L, Lim CP (2020) Intelligent optic disc segmentation using improved particle swarm optimization and evolving ensemble models. Appl Soft Comput 92:106328","journal-title":"Appl Soft Comput"},{"key":"6947_CR77","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/j.eswa.2017.10.001","volume":"93","author":"L Zhang","year":"2018","unstructured":"Zhang L, Srisukkham W, Neoh SC, Lim CP, Pandit D (2018) Classifier ensemble reduction using a modified firefly algorithm: An empirical evaluation. Exp Syst Appl 93:395\u2013422","journal-title":"Exp Syst Appl"},{"key":"6947_CR78","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neucom.2017.12.030","volume":"282","author":"DR Nayak","year":"2018","unstructured":"Nayak DR, Dash R, Majhi B (2018) Discrete ripplet-II transform and modified PSO based improved evolutionary extreme learning machine for pathological brain detection. Neurocomputing 282:232\u2013247","journal-title":"Neurocomputing"},{"key":"6947_CR79","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.asoc.2014.10.026","volume":"26","author":"AR Jordehi","year":"2015","unstructured":"Jordehi AR (2015) Enhanced leader PSO (ELPSO): a new PSO variant for solving global optimisation problems. Appl Soft Comput 26:401\u2013417","journal-title":"Appl Soft Comput"},{"key":"6947_CR80","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.ins.2012.04.028","volume":"209","author":"M Nasir","year":"2012","unstructured":"Nasir M, Das S, Maity D, Sengupta S, Halder U, Suganthan PN (2012) A dynamic neighborhood learning based particle swarm optimizer for global numerical optimization. Inform Sci 209:16\u201336","journal-title":"Inform Sci"},{"issue":"8","key":"6947_CR81","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.3390\/s16081204","volume":"16","author":"Q Chen","year":"2016","unstructured":"Chen Q, Chen Y, Jiang W (2016) Genetic particle swarm optimization-based feature selection for very-high-resolution remotely sensed imagery object change detection. Sensors 16(8):1204","journal-title":"Sensors"},{"issue":"4","key":"6947_CR82","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1007\/s00521-015-1920-1","volume":"27","author":"S Mirjalili","year":"2016","unstructured":"Mirjalili S (2016) Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput Appl 27(4):1053\u20131073","journal-title":"Neural Comput Appl"},{"key":"6947_CR83","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.advengsoft.2015.01.010","volume":"83","author":"S Mirjalili","year":"2015","unstructured":"Mirjalili S (2015) The ant lion optimizer. Adv Eng Softw 83:80\u201398","journal-title":"Adv Eng Softw"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-06947-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-06947-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-06947-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T16:25:59Z","timestamp":1726590359000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-06947-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,30]]},"references-count":83,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["6947"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-06947-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,30]]},"assertion":[{"value":"6 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2022","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 have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The proposed work has gained organisational ethical approval.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"The consent to participate has been obtained from all the co-authors for the proposed studies.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The consent for publication has been obtained from all the co-authors for the proposed studies.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}