A Comprehensive Survey of Vision-Based Human Action Recognition Methods
Open accessThe DOI matches its Crossref record; 119 of the 119 references it cites were found in a registry or an index.
Abstract
Although widely used in many applications, accurate and efficient human action recognition remains a challenging area of research in the field of computer vision. Most recent surveys have focused on narrow problems such as human action recognition methods using depth data, 3D-skeleton data, still image data, spatiotemporal interest point-based methods, and human walking motion recognition. However, there has been no systematic survey of human action recognition. To this end, we present a thorough review of human action recognition methods and provide a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human–object interaction recognition methods, and the current prominent research topic of action detection methods. Finally, we present several analysis recommendations for researchers. This survey paper provides an essential reference for those interested in further research on human action recognition.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“videobased activity recognition is naturally complementary to other sensing modalities Zhang et al. (2019);”
From Opportunity++: A Multimodal Dataset for Video- and Wearable, Object and Ambient Sensors-Based Human Activity Recognition (2021) · cites this paper as Zhang et al. (2019)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“Feature representation and selection is a classic problem in computer vision and machine learning [8].”
BackgroundLearning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593 · cited 4×
“Depending on the structure of the deep learning network, the main representative works can be summarized as discussing methods based on two-stream convolutional networks [19], those based on 3D convolutional networks [20], and those based on long short-term memory (LSTM) [83].”
BackgroundInfluentialQuo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
Cao, Z., Simon, T., Wei, S.-E., & Sheikh, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.143 · Cited by 7,539
Two-Stream Convolutional Networks for Action Recognition in Videos
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2199 · Cited by 6,756 · cited 4×
“Depending on the structure of the deep learning network, the main representative works can be summarized as discussing methods based on two-stream convolutional networks [19], those based on 3D convolutional networks [20], and those based on long short-term memory (LSTM) [83].”
BackgroundInfluentialSpatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410
Proceedings European Conference on Computer Vision 2002
Heyden, A., Sparr, G., Nielsen, M., & Johansen, P. (2002) · Lund University Publications (Lund University) · Cited by 5,153
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., & Van Gool, L. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_2 · Cited by 3,958
Action Recognition with Improved Trajectories
Wang, H., & Schmid, C. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.441 · Cited by 3,407
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Shahroudy, A., Liu, J., Ng, T.-T., & Wang, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.115 · Cited by 3,148 · cited 2×
“However, with the development of large-scale and challenging RGBD and skeleton datasets, for example, the NTU RGB+D dataset, deep-leaning-based methods for depth and skeleton data are becoming the primary research topic in the field of human action recognition.”
Research works printed but not linked: 9
- Yu, K., and Yun, F. (arXiv, 2018). Human Action Recognition and Prediction: A Survey, arXiv.
- Diba, A., Fayyaz, M., Sharma, V., Karami, A.H., Arzani, M.M., Yousefzadeh, R., and Van Gool, L. (arXiv, 2017). Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification, arXiv.
- Wang, P., Li, W., Gao, Z., Zhang, J., Tang, C., and Ogunbona, P. (arXiv, 2015). Deep Convolutional Neural Networks for Action Recognition Using Depth Map Sequences, arXiv.
- Zhu, Y., Lan, Z., Newsam, S., and Hauptmann, A.G. (arXiv, 2017). Hidden two-stream convolutional networks for action recognition, arXiv.
- Soomro, K., Zamir, A.R., and Shah, M. (arXiv, 2012). UCF101: A Dataset of 101 Human Actions Classes from Videos in The Wild, arXiv.
- Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., and Natsev, P. (arXiv, 2017). The Kinetics Human Action Video Dataset, arXiv.
- Gupta, S., and Malik, J. (arXiv, 2015). Visual Semantic Role Labeling, arXiv.
- Yu, G., Liu, Z., and Yuan, J. (2014). Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction, Springer.
- Gorban, A., Idrees, H., Jiang, Y., Zamir, A.R., Laptev, I., Shah, M., and Sukthankar, R. (2015, January 7–12). THUMOS challenge: Action recognition with a large number of classes. Proceedings of the CVPR Workshop, Boston, MA, USA.
Cited by
Items 201–300 of 512
Nguyen, V.-T., Nguyen, T.-N., Le, T., Pham, D., & Vu, H. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10866-4 · Cited by 10
“Comprehensive surveys of these methods as well as video datasets can be found in [1, 2, 8, 52, 53].”
BackgroundIto, Y., Morita, K., Kong, Q., & Yoshinaga, T. (2021) · IEEE Access · doi:10.1109/access.2021.3102671 · Cited by 10
Device-Free Multi-Location Human Activity Recognition Using Deep Complex Network
Ding, X., Hu, C., Xie, W., Zhong, Y., Yang, J., & Jiang, T. (2022) · Sensors · doi:10.3390/s22166178 · Cited by 12
“Owing to their superiority involving sensing accuracy and robustness, sensor-based [7,8] and camerabased [9,10] HAR methods have been widely used in various fields.”
MethodSkeleton Guided Conflict-Free Hand Gesture Recognition for Robot Control
Xu, J., Li, J., Zhang, S., Xie, C., & Dong, J. (2020) · International Conference on Awareness Science and Technology (iCAST) · doi:10.1109/icast51195.2020.9319483 · Cited by 10
Kim, J., & Cho, J. (2021) · Applied Sciences · doi:10.3390/app11114940 · Cited by 10
“…learn motion features from video and utilize the motion features extracted from different modalities of data to enhance the performance for action recognition according to modality of data perspective; action recognition models are largely divided into depth, skeleton, and vision-based HAR [25].”
MethodSarraf, S., & Kabia, M. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5040067 · Cited by 9
Kourbane, I., Papadakis, P., & Andries, M. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.104275 · Cited by 12
Skeleton-based multi-person action recognition towards real-world violence detection
Truong, M.-T., & Hoang, V.-D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111987 · Cited by 9
Machine learning for video event recognition
Avola, D., Cascio, M., Cinque, L., Foresti, G. L., & Pannone, D. (2021) · Integrated Computer-Aided Engineering · doi:10.3233/ica-210652 · Cited by 9
“In recent years, methods based on the visual recognition of events triggered by moving subjects have been proposed as well [26,27].”
A statistical framework for few-shot action recognition
Haddad, M., Ghassab, V. K., Najar, F., & Bouguila, N. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-10721-6 · Cited by 9
“Related comprehensive research works can be found in [3, 21, 34, 45].”
BackgroundApplication of artificial intelligence methods in the school educational process
Kataev, M. Y., Bulysheva, L., & Mosiaev, A. (2022) · Systems Research and Behavioral Science · doi:10.1002/sres.2873 · Cited by 10
Using machine learning approach to construct the people flow tracking system for smart cities
Yao, B., Liu, S., & Wang, L. (2023) · Computer Science and Information Systems · doi:10.2298/csis220813014y · Cited by 11
“As a result, the preprocessing process is more cumbersome [24].”
MethodReal-Time Cattle Interaction Recognition via Triple-stream Network
Yang, Y., Komatsu, M., Ohkawa, T., & Oyama, K. (2022) · International Conference on Machine Learning and Applications · doi:10.1109/icmla55696.2022.00016 · Cited by 14
“The study of recognizing action has achieved great success by deep learning approaches [5]– [7] and among these approaches, video based recognition is relatively well-established and well-studied area of research, whereas still image based recognition is less studied.”
Human Action Recognition Using Key-Frame Attention-Based LSTM Networks
Yang, C., Mei, F., Zang, T., Tu, J., Jiang, N., & Liu, L. (2023) · Electronics · doi:10.3390/electronics12122622 · Cited by 12
Ameen, M., & Stone, R. (2023) · International Journal of Network Security & Its Applications · doi:10.5121/ijnsa.2023.15307 · Cited by 12
“ Pattern recognition : plays a crucial role by identifying certain patterns within the data, such as movement patterns, to offer insights into crowd behavior[20].”
BackgroundForecasting influenza hemagglutinin mutations through the lens of anomaly detection
Garjani, A., Chegini, A. M., Salehi, M., Tabibzadeh, A., Yousefi, P., Razizadeh, M. H., Esghaei, M., Esghaei, M., & Rohban, M. H. (2023) · Scientific Reports · doi:10.1038/s41598-023-42089-y · Cited by 11
SFPD: Simultaneous Face and Person Detection in Real-Time for Human–Robot Interaction
Fiedler, M.-A., Werner, P., Khalifa, A., & Al-Hamadi, A. K. (2021) · Sensors · doi:10.3390/s21175918 · Cited by 11
“Furthermore, they are the first component for a large number of recognition systems in many applications, such as face recognition [1], facial expression analysis [2,3], body pose estimation [4], face attribute detection [5], human action recognition [6] and others.”
BackgroundIto, Y., Kong, Q., Morita, K., & Yoshinaga, T. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897250 · Cited by 11
“1, is regarded as a more complex and challenging task than recognizing actions performed by an individual [3, 16].”
BackgroundMulti-dimensional task recognition for human-robot teaming: literature review
Baskaran, P., & Adams, J. A. (2023) · Frontiers in Robotics and AI · doi:10.3389/frobt.2023.1123374 · Cited by 12
Skeleton-Split Framework using Spatial Temporal Graph Convolutional Networks for Action Recognition
Alsawadi, M. S., & Rio, M. (2021) · International Conference on Bio-engineering for Smart Technologies (BioSMART) · doi:10.1109/biosmart54244.2021.9677634 · Cited by 9
Uncertain Process Data with Probabilistic Knowledge: Problem Characterization and ChallengesPreprint
Cohen, I., & Gal, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.03324 · Cited by 9
“upon automatically recognizing simple activities from which the process is composed such as ‘walking’, ‘jumping’, ‘meeting’ and the temporal links between them; and this task poses a challenge for current machine learning techniques [16, 17].”
BackgroundHuman Activity Recognition with CNN in FastAI
Srinivasu, P. N., Bonu, R. K., Chaitanya, A., Bolliboiyna, S., Galinki, D., & Abbineni, V. S. K. (2024) · International Conference on Social and Sustainable Innovations in Technology and Engineering (SASI-ITE) · doi:10.1109/sasi-ite58663.2024.00020 · Cited by 8
Shah, H., & Holia, M. S. (2025) · Signal Processing Image Communication · doi:10.1016/j.image.2025.117308 · Cited by 8
A comprehensive review of on-board action recognition models in public transportation systems
Meurie, C., & Lézoray, O. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128311 · Cited by 10
SMOTE-Enhanced CNN-Bi-LSTM for wearable sensor-based human activity recognition
Arafa, A., Harfoush, H., El-Fishawy, N. A., & Radad, M. A. (2026) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2026.102161 · Cited by 8
RGB+2D skeleton: local hand-crafted and 3D convolution feature coding for action recognition
Zhang, Y., Zhang, H., Du, J., Lei, Q., Yang, L., & Zhong, B. (2021) · Signal Image and Video Processing · doi:10.1007/s11760-021-01868-8 · Cited by 8
Self-citationPairwise-Covariance Multi-view Discriminant Analysis for Robust Cross-View Human Action Recognition
Tran, H.-N., Nguyen, H.-Q., Doan, H.-G., Tran, T.-H., Le, T., & Vu, H. (2021) · IEEE Access · doi:10.1109/access.2021.3082142 · Cited by 8
“Action recognition has been an attractive research topic since the last decade [2].”
BackgroundTN-GAN-Based Pet Behavior Prediction through Multiple-Dimension Time-Series Augmentation
Kim, H., & Moon, N. (2023) · Sensors · doi:10.3390/s23084157 · Cited by 8
“Studies of behavioral prediction using image data have limitations because they are sensitive to shooting angle or image quality [1,2].”
BackgroundA multimodal fusion enabled ensemble approach for human activity recognition in smart homes
Ding, W., Wu, S., & Nugent, C. (2023) · Health Informatics Journal · doi:10.1177/14604582231171927 · Cited by 8
Action Recognition in Videos through a Transfer-Learning-Based Technique
López-Lozada, E., Sossa, H., Rubio-Espino, E., & Montiel-Pérez, J. Y. (2024) · Mathematics · doi:10.3390/math12203245 · Cited by 9
“Spatial features pertain to the appearance, posture, and motion of individuals [8].”
Gościewska, K., & Frejlichowski, D. (2020) · Applied Sciences · doi:10.3390/app10196728 · Cited by 8
Deep Skeleton Modeling and Hybrid Hand-crafted Cues over Physical Exercises
Akhter, I., Javeed, M., & Jalal, A. (2023) · International Conference on Communication, Computing and Digital Systems (C-CODE) · doi:10.1109/c-code58145.2023.10139863 · Cited by 8
“Generally, the physical exercise recognition (PER) requires the motion data, which is used to filter the noise and extract features [18-20].”
MethodA Literature Review of Current Vision Based Fall Detection Methods
Biswas, A., & Dey, B. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-4932-8_46 · Cited by 8
Deep Learning for Skeleton-Based Human Activity Segmentation: An Autoencoder Approach
Hossen, M. A., Naim, A. G., & Abas, P. E. (2024) · Technologies · doi:10.3390/technologies12070096 · Cited by 7
“The utilization of skeleton data, extracted from depth data, such as those acquired with the Kinect sensor, has garnered substantial attention in human activity recognition [8–12].”
BackgroundMethodZhang, X., Hu, Q., Xiao, Z., Sun, T., Zhang, J., Zhang, J., & Li, Z. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3462466 · Cited by 10
Ay, Ö., & Emel, E. (2025) · IEEE Access · doi:10.1109/access.2025.3554263 · Cited by 7
“Human action recognition has been widely studied since it has many application areas, such as visual surveillance, video retrieval, autonomous vehicles, human-computer interaction, human-robot interaction, and smart manufacturing [5], [6], [7], [8], [9].”
Cross-Environment Device-Free Human Action Recognition via Wi-Fi Signals
Zhang, S., Zhong, Y., Jia, H., Ding, X., & Jiang, T. (2025) · Electronics · doi:10.3390/electronics14112299 · Cited by 8
A Systematic Survey on Human Behavior Recognition Methods
Yuan, M., Wei, S., Zhao, J., & Sun, M. (2021) · SN Computer Science · doi:10.1007/s42979-021-00932-x · Cited by 8
A Neural Network Pruning Approach to Human Activity Identification Based on Deep Learning
Mahor, V. K., & Pandit, J. (2022) · IEEE International Conference on Current Development in Engineering and Technology (CCET) · doi:10.1109/ccet56606.2022.10079945 · Cited by 7
“Though cheaper to implement, vision-based HAR is more susceptible to outside influences such as camera angle, illumination, and human overlap [8][9].”
BackgroundA LIGHTWEIGHT MULTI-PERSON POSE ESTIMATION SCHEME BASED ON JETSON NANO
Liu, L., Blancaflor, E., & Abisado, M. (2023) · Applied Computer Science · doi:10.35784/acs-2023-01 · Cited by 7
SADY: Student Activity Detection Using YOLO-based Deep Learning Approach
Deshpande, A., & Warhade, K. K. (2023) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.13.4.18393 · Cited by 8
Analysis of Fisherman Exploitation in Taiwan Distant Water Fishing
Karthikeyan, P., Pratap, A., Chu, W. C., & Hsiung, P. (2023) · IEEE Technology and Society Magazine · doi:10.1109/mts.2023.3306539 · Cited by 7
A Review Work: Human Action Recognition in Video Surveillance Using Deep Learning Techniques
Gupta, N. S., Ramya, K., & Karnati, R. (2024) · Informatics and Automation · doi:10.15622/ia.23.2.5 · Cited by 7
Recognition of Human Activities Based on Ambient Audio and Vibration Data
Koch, M., Pfitzinger, T., Schlenke, F., Kohlmorgen, F., Groll, R., & Wöhrle, H. (2024) · IEEE Access · doi:10.1109/access.2024.3457912 · Cited by 8
Human Body Posture Recognition Approaches: A Review
Ali, M. A., Hussain, A. J., & Sadiq, A. T. (2022) · ARO-The Scientific Journal of Koya University · doi:10.14500/aro.10930 · Cited by 9
PanoSyn: immersive video synopsis for spherical surveillance video
Priyadharshini, S., & Mahapatra, A. (2022) · Sadhana · doi:10.1007/s12046-022-01937-9 · Cited by 7
“The methods for recognizing human actions were divided into three different levels: human detection (low-level), human tracking (intermediate-level), and methods of understanding behavior (high-level) [23].”
Compact global association based adaptive routing framework for personnel behavior understanding
Shi, L., Zhou, Y., Wang, J., Wang, Z., Chen, D., Zhao, H., Yang, W., & Szczerbicki, E. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.12.002 · Cited by 7
Self-citationComplete Video-Level Representations for Action Recognition
Li, M., Bai, R., Meng, B., Ren, J., Jiang, M., Yang, Y., Li, L., & Du, H. W. (2021) · IEEE Access · doi:10.1109/access.2021.3058998 · Cited by 7
“For 3D video data with spatial and temporal components, the performance of the model for activity recognition depends heavily on the ability to learn robust spatial–temporal features from the video and obtain spatial and temporal dependencies [1].”
BackgroundA Projection-Based Human Motion Recognition Algorithm Based on Depth Sensors
Su, M., Tai, P.-T., Chen, J., Hsieh, Y., Lee, S., & Yeh, Z.-F. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3079983 · Cited by 7
Incremental human action recognition with dual memory
Gutoski, M., Lazzaretti, A. E., & Lopes, H. S. (2021) · Image and Vision Computing · doi:10.1016/j.imavis.2021.104313 · Cited by 9
An Intelligent HealthCare Monitoring Framework for Daily Assistant Living
Ghadi, Y. Y., Khalid, N., Alsuhibany, S. A., Shloul, T. A., Jalal, A., & Park, J. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.024422 · Cited by 7
Using a Multilearner to Fuse Multimodal Features for Human Action Recognition
Tang, C., Hu, H., Wang, W., Li, W., Peng, H. F., & Wang, X. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/4358728 · Cited by 7
Qin, Y., Liu, S., & Yuan, C. Z. (2025) · Scientific Reports · doi:10.1038/s41598-025-18520-x · Cited by 6
“Human motion prediction 10 and action recognition have been extensively studied within computer vision and human-computer interaction, serving as fundamental tasks for enabling intelligent systems to understand and anticipate human behaviors in various real-world scenarios 11 .”
A vision-based framework and dataset for human behavior understanding in industrial assembly lines
Papoutsakis, K. E., Bakalos, N., Zacharia, A., Fragkoulis, K., Kapetadimitri, G., & Pateraki, M. (2025) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2025.104592 · Cited by 6
A Systematic Literature Review of Optimization Methods in Skeleton-Based Human Action Recognition
Chung, J.-L., Ong, L.-Y., & Leow, M.-C. (2025) · IEEE Access · doi:10.1109/access.2025.3586476 · Cited by 6
“References [35] and [36] reviewed HAR techniques for RGB, depth, and skeleton data, discussing both hand-crafted features and deep learning methods for each modality.”
Deep Learning based Human Action Recognition
Pandey, R., Chikhale, Y., Verma, R., & Patil, D. (2021) · ITM Web of Conferences · doi:10.1051/itmconf/20214003014 · Cited by 7
“They also included progress in hand-designed action features in RGB [17].”
BackgroundSpatio-temporal dual-attention network for view-invariant human action recognition
Gedamu, K., Yilma, G., Assefa, M., & Ayalew, M. (2022) · International Conference on Digital Image Processing · doi:10.1117/12.2643446 · Cited by 6
“, 𝑓 " via Eqn.”
BackgroundInfluentialAction Recognition and Detection Based on Deep Learning: A Comprehensive Summary
Li, Y., Liang, Q., Gan, B., & Cui, X. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.042494 · Cited by 10
Pu, Y., Gao, X., & Lv, W. (2024) · Optical and Quantum Electronics · doi:10.1007/s11082-024-06322-w · Cited by 6
RetractedInsights of Artificial Intelligence to Stop Spread of COVID-19
Sufian, A., Jat, D. S., & Banerjee, A. (2020) · Studies in big data · doi:10.1007/978-3-030-55258-9_11 · Cited by 6
Abnormal Human Behavior Recognition Based on Image Processing Technology
Zhao, R., Wang, Y., Jia, P., Li, C., Ma, Y., & Zhang, Z. (2021) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac50856.2021.9390762 · Cited by 6
“The centroid can not only show the position change and speed change of the target, but also is less affected by external factors such as non-moving target noise, contour rotation and stretching [15].”
BackgroundWearable magnetic induction-based approach toward 3D motion tracking
Golestani, N., & Moghaddam, M. (2021) · Scientific Reports · doi:10.1038/s41598-021-98346-5 · Cited by 9
“However, they inherit computer vision restrictions such as light dependency, coverage limitation, and high computational cost [14, 15].”
BackgroundEvaluation of 2D and 3D posture for human activity recognition
Hossen, M. A., Naim, A. G., & Abas, P. E. (2023) · AIP conference proceedings · doi:10.1063/5.0111224 · Cited by 6
Editorial: Artificial Intelligence and Human Movement in Industries and Creation
Dimitropoulos, K., Daras, P., Manitsaris, S., Leymarie, F. F., & Calinon, S. (2021) · Frontiers in Robotics and AI · doi:10.3389/frobt.2021.712521 · Cited by 6
“Thus, every single intelligent system will be able to capture human motions, analyze them (Zhang et al., 2019), detect poses and recognize gestures (Chatzis et al.”
BackgroundPolo-Rodríguez, A., Rotbei, S., Amador, S., Baños, O., Gil, D., & Medina-Quero, J. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-822822-7.00005-3 · Cited by 5
On the Relevance of Temporal Features for Medical Ultrasound Video Recognition
Smith, D. H., Lineberger, J. P., & Baker, G. H. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43895-0_70 · Cited by 5
“A large body of work has addressed video recognition tasks, including object tracking [14], temporal action localization [28], captioning [1], action recognition [30], and many others.”
BackgroundZhang, Y., & Wang, Z. (2023) · Optical and Quantum Electronics · doi:10.1007/s11082-023-05734-4 · Cited by 5
“R Literature research has shown that motion recognition technology can also be combined with virtual reality technology to provide dance learners with a more immersive learning experience and richer performance methods for dance performers (Zhang et al. 2019).”
Self-citationRetractedEnhancing Few-Shot Action Recognition Using Skeleton Temporal Alignment and Adversarial Training
Xu, Q., Yang, J., Zhang, H., Jie, X., & Bandara, D. (2024) · IEEE Access · doi:10.1109/access.2024.3365448 · Cited by 5
“By understanding human movements and behaviors in videos, computers can accomplish various downstream tasks, such as human-computer interaction systems, human behavior tracking, human behavior monitoring, etc. [4] Directly detecting human action from a video poses several challenges.”
BackgroundSelf-citationGuan, L., Zhang, X., Cong, X., Zhang, Z., Yang, Z., Li, N., & Noureldin, A. M. (2024) · Measurement · doi:10.1016/j.measurement.2024.115682 · Cited by 6
Lan, S., Xue, Y., Liu, H., & Yang, X. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108207 · Cited by 6
Vision skeleton trajectory based motion assessment system for healthcare rehabilitation
Shi, Q., Zhang, H., Dong, L., Lei, Q., & Hsiao, T. (2020) · The Journal of Engineering · doi:10.1049/joe.2019.1316 · Cited by 5
Self-citationCyllage City COVID-19 Outbreak Linked to Zubat Consumption
Joy, N. (2020) · American Journal of Biomedical Science & Research · doi:10.34297/ajbsr.2020.08.001256 · Cited by 5
A Table Tennis Motion Correction System Based on Human Motion Feature Recognition
Han, L. (2022) · Security and Communication Networks · doi:10.1155/2022/7049429 · Cited by 7
“'e vision-based human motion recognition method is to install the filming equipment in a fixed space and determine the humanmotion state by analyzing the human motion state in the filmed pictures and the comparison of the before and after pictures [18].”
MethodRetractedEfficient Augmentation of Human Action Recognition Datasets with Warped Windows
Warchoł, D., & Oszust, M. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.09.360 · Cited by 5
Zalameda, J. G., Kruse, B., Glandon, A., Witherow, M. A., Shetty, S. S., & Iftekharuddin, K. M. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892887 · Cited by 5
“Recent advances in deep learning have facilitated apposite processing of skeleton sequence data for tasks including fall detection [1], human action recognition [2], and human identity recognition [3].”
BackgroundGCG-Net: Graph Classification Geolocation Network
Zhang, Y., Bu, S., Hu, B., Han, P., Weng, L., & Xue, S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3293832 · Cited by 7
“For action recognition [36], [37], detecting the locations of human joints in video clips is one approach that has been used to recognize human actions.”
BackgroundSelf-citationChu, X., Kim, S., & Park, K.-S. (2023) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3584371.3612999 · Cited by 6
“Traditional image-based HAR using RGB data [1] encounter challenges like partial body occlusion, lighting interference, and feature extraction difficulties, affecting accuracy.”
MethodOvercomplete graph convolutional denoising autoencoder for noisy skeleton action recognition
Guo, J., Ji, Q., & Shan, G. (2023) · IET Image Processing · doi:10.1049/ipr2.12944 · Cited by 5
Vision-based action recognition for the human-machine interaction
Verma, A., Singh, V., Chouhan, A. P. S., Abhishek, & Rawat, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-29150-0.00011-1 · Cited by 5
Zheng, N., Xia, H., Liang, Z., & Du, Y. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131796 · Cited by 5
“Asthethird generation of neural networks [34], Spiking Neural Networks (SNN) originated from biomimetics and are renowned for their event-driven characteristics, which result in exceptionally low energy consumption [37, 46].”
Probabilistic Activity Recognition for Serious Games with Applications in Medicine
MARIA, E. D., L’Yvonnet, T., Moisan, S., & Rigault, J. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-46902-3_7 · Cited by 5
“A lot has been done, especially in computer vision, on simple action recognition [25], whereas we target complex activities , including several actions.”
BackgroundAt the Speed of Sound: Efficient Audio Scene Classification
Dong, B., Lumezanu, C., Chen, Y., Song, D., Mizoguchi, T., Chen, H., & Khan, L. R. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3390730 · Cited by 8
“While most smart sensing platforms primarily analyze video and sensor time series [23], recent studies demonstrate the benefit of audio classification not only as a complement but also as a replacement for video classification [1, 8].”
BackgroundPassive Observer of Activities for Aging in Place Using a Network of RGB-D Sensors
Payandeh, S., & Park, J. (2020) · International Journal of Telemedicine and Applications · doi:10.1155/2020/8867926 · Cited by 5
View Invariant Spatio-Temporal Descriptor for Action Recognition From Skeleton Sequences
Subbareddy, K. V., & Devi, L. N. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3213234 · Cited by 5
Quantifying Physical Activity in Young Children Using a Three-Dimensional Camera
McCullough, A. K., Rodríguez, M. M. D., & Garber, C. E. (2020) · Sensors · doi:10.3390/s20041141 · Cited by 5
Synthesizing mmWave range-doppler data from videos for privacy-preserving human activity recognition
Zhang, X., Wang, S., Cui, Z., Li, B.-R., Zhou, X., Xu, Z.-D., & Li, Z. (2026) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-025-00205-z · Cited by 3
Houssein, E. H., Mahdy, M. A., Kayed, M., Ouyang, H., & Mohamed, W. M. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10462-x · Cited by 4
Deep Learning to See: Towards New Foundations of Computer Vision
Betti, A., Gori, M., & Melacci, S. (2022) · SpringerBriefs in computer science · doi:10.1007/978-3-030-90987-1 · Cited by 8
Late feature supplement network for early action prediction
Li, Z., Zhang, H., Zhang, M., Lei, Q., & Du, J. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104519 · Cited by 4
Self-citationHuman Table Tennis Actions Recognition and Evaluation Method Based on Skeleton Extraction
Huang, W., Yang, J., Luo, H., & Zhang, H. (2023) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece58074.2023.10135318 · Cited by 4
Self-citationReview of Literature on Human Activity Detection and Recognition
Naik, P., & Kunte, S. R. (2023) · International Journal of Management Technology and Social Sciences · doi:10.47992/ijmts.2581.6012.0318 · Cited by 4
Towards Relevant Human-Vehicle Interaction Data for Perceptive Machine Learning
Rehmann, M., Brunner, M., & Curio, C. (2025) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv64158.2025.11097661 · Cited by 4
“[24], [25] are comprehensive studies which provide an extensive overview of these advancements, highlighting the shift towards video action recognition techniques.”
Cross Fusion for Egocentric Interactive Action Recognition
Jiang, H., Song, Y., Jiang, H., & Shu, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-37731-1_58 · Cited by 4
Maheswari, B. U., Sonia, R., Rajakumar, M. P., & Ramya, J. (2021) · Information Technology And Control · doi:10.5755/j01.itc.50.4.27845 · Cited by 4
2D Multi-Person Pose Estimation Combined with Face Detection
Li, Q., Xu, L., & Yang, X. (2021) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s021800142256002x · Cited by 6
Jackson, K. L., Đurić, Z., Engdahl, S. M., Santago, A. C., DeStefano, S., & Gerber, L. H. (2023) · Frontiers in Rehabilitation Sciences · doi:10.3389/fresc.2023.1130847 · Cited by 6
Marshalling Model Inference in Video Streams
Chao, D., Koudas, N., & Yu, X. (2023) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde55515.2023.00110 · Cited by 5
“The rapid advances in Deep Learning (DL) [1] have revolutionized numerous applications of vast practical significance such as various aspects of video analytics (including video object detection [2], event detection [3], action recognition [3] and classification [4] to name a few).”
BackgroundBao, F., Gao, F., & Li, W. (2024) · Measurement Sensors · doi:10.1016/j.measen.2024.101260 · Cited by 4
Kumar, M. T. K., Kishore, P. V. V., Madhav, B. T. P., Kumar, D. A., Kala, N. S., Rao, K. P. K., & Prasad, B. (2021) · IEEE Access · doi:10.1109/access.2021.3119455 · Cited by 4
“Over the years, a variety of features [21] were computed from raw skeletal joint positions for 3D action representation.”
BackgroundHuman Activity Recognition via Feature Extraction and Artificial Intelligence Techniques: A Review
Guerrero, J. C. E., España, E. M., & Muñoz-Añasco, M. (2022) · Tecnura · doi:10.14483/22487638.17413 · Cited by 5
“Considering the above studies and that proposed by H.-B. Zhang et al. (2019), local feature extraction does not require pre-processing activities such as background segmentation or human detection.”
Background
Metadata
- Authors
- Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S.
- Affiliations
- Department of Computer Science and Technology, Huaqiao University, Xiamen 361000, China
- Huaqiao University (CN)
- Corresponding author
- Du, Ji-Xiang
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2019-02-27
- Volume
- 19
- Issue
- 5
- Pages
- 1005
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC6427144
- OpenAlex
- W2917819557
- Cited by
- 503
- References
- 119
- Citations by year
- 2026: 33 · 2025: 55 · 2024: 79 · 2023: 97 · 2022: 71 · 2021: 93 · 2020: 62 · 2019: 12
- FWCI
- 6.84
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- human action recognition, depth information, 3D skeleton data, human-object interaction recognition, action detection
- MeSH terms
- Algorithms, Humans, Human Activities, Motion, Pattern Recognition, Automated, Surveys and Questionnaires, Skeleton, Vision, Ocular, Visual Perception
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
