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 401–500 of 512
A temporal Human Activity Recognition Based on Stacked Auto Encoder and Extreme Learning Machine
Gnouma, M., Ejbali, R., & Zaied, M. (2023) · International Conference on Control, Decision and Information Technologies (CoDIT) · doi:10.1109/codit58514.2023.10284218 · Cited by 1
“Accuracy Latah [14] 90.34% M Abdellaoui [28] 94.83% Zhang et al. [19] 95% Jaouedi, N. [29] 96.30% Our approach 98.47% Table 1 shows the performance comparison with other approaches on the KTH dataset.”
BackgroundResultInfluentialHFGCN-Based Action Recognition System for Figure Skating
Zhou, Y. J., Zhang, Y., & Wu, A. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8429-9_10 · Cited by 1
Self-citationUAV-Based IoT Applications for Action Recognition
Selmi, M., & Farah, I. R. (2023) · Advances in information security · doi:10.1007/978-3-031-47590-0_9 · Cited by 2
Human Action Recognition Classification Based on 3D CNN Deep Learning
Li, K., Zhu, T., & Cheng, H. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-4393-3_30 · Cited by 1
Hao, W., Han, M., Zhang, K., Zhang, L., Hao, W., Li, F., Liu, Z., & 3. Yongji Puzhou Old City Beimenwai Cattle Farm, Y. 0. (2024) · International journal of agricultural and biological engineering · doi:10.25165/j.ijabe.20241703.8202 · Cited by 1
A hybrid approach to context based human activity recognition in smart environment using ResBi-LSTM
Soman, S. V., & Angelina, J. J. R. (2024) · Intelligent Buildings International · doi:10.1080/17508975.2024.2437421 · Cited by 1
“It has been widely used in many applications, including gesture recognition (Tan et al. 2020), gait analysis (Wang et al. 2020), daily activity analysis (Bianchi et al. 2019), and video surveillance (Zhang et al. 2019).”
Knowledge-based Programming by Demonstration using semantic action models for industrial assembly
Ding, J., Zhang, H., Li, W., Zhou, L., & Perzylo, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802511 · Cited by 1
“Current vision-based action recognition methods require training on dedicated video datasets [6].”
Self-citationComparison of EfficientNet and VGGNet Using RGB Photos for Human Action Recognition
An, R. (2024) · International Signal Processing, Communications and Engineering Management Conference (ISPCEM) · doi:10.1109/ispcem64498.2024.00022 · Cited by 1
Neural Networks in Human Activity Recognition: Trends, Challenges, and Future Directions
Valli, C., & Amutha, R. (2025) · International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) · doi:10.1109/idciot64235.2025.10915132 · Cited by 1
“Zhang H B et al.[4](2019) A brief overview of human action feature encoding methods that encompass various data types, including hand-crafted action attributes and deep learning-based feature extraction techniques for RGB, depth, and skeleton data.”
HActiFi: Towards Practical ISAC for Human Activity Recognition via Smart TV Infrastructure
Kim, Y., Lee, K., Son, Y., & Bahk, S. (2025) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2025-fall65116.2025.11310362 · Cited by 1
“Nowadays, smart TVs are becoming the hub of smart homes, exemplified by vision-based games using sensors, but it still faces privacy concerns [11] and costly deployment.”
Template co-updating in multi-modal human activity recognition systems
Franco, A., Magnani, A., & Maio, D. (2020) · ACM Symposium on Applied Computing · doi:10.1145/3341105.3374085 · Cited by 1
“Interested readers can refer to [12] for a good recent survey.”
BackgroundLiang, Z., Shi, X., Zhang, Y., Liu, B., & Liu, B. (2020) · IEEE Access · doi:10.1109/access.2020.3035659 · Cited by 1
“Human action recognition has been widely applied in the areas of entertainment games, health care, remote video surveillance, smart home, and educational assistant [1]–[4].”
BackgroundSelf-citationWorrakantapon, A., Pongsena, W., Kerdprasop, K., & Kerdprasop, N. (2021) · International Journal of Electrical and Electronic Engineering & Telecommunications · doi:10.18178/ijeetc.10.1.29-35 · Cited by 1
On-board UAV Pilots Identification in Counter UAV Images
Cazzato, D., Cimarelli, C., & Voos, H. (2022) · Communications in computer and information science · doi:10.1007/978-3-030-94893-1_19 · Cited by 1
Driving Action Recognition Based on 3D Convolution
Duan, H., Zhang, C., & Lv, Z. (2021) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis54983.2021.00028 · Cited by 1
Multivariate Beta-Based Hidden Markov Models Applied to Human Activity Recognition
Manouchehri, N., Dalhoumi, O., Amayri, M., & Bouguila, N. (2012) · Unsupervised and semi-supervised learning · doi:10.1007/978-3-030-99142-5_9 · Cited by 1
Sequential Action Retrieval for Generating Narratives from Long Videos
Yamazaki, S., Liu, J., & Kankanhalli, M. (2023) · doi:10.1145/3607540.3617143 · Cited by 1
“One of the major task is action classification [27] that classifies video-level action labels.”
BackgroundAction Recognition Based on Dense Action Captioning
Zhang, C., Zhou, L. M., & Niu, C. (2023) · International Conference on Digital Image Processing · doi:10.1145/3604078.3604079 · Cited by 1
Context-Based Masking for Spontaneous Venous Pulsations Detection
Sheng, H., Yu, X., Li, X., & Golzan, M. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-8388-9_42 · Cited by 1
Towards Efficient Video-Based Action Recognition: Context-Aware Memory Attention NetworkPreprint
Koh, T. C., Yeo, C. K., & Jing, X. (2023) · Research Square · doi:10.21203/rs.3.rs-3174485/v1 · Cited by 1
Priyadharsini, S. (2024) · Wiley eBooks · doi:10.1002/9781394200733.ch1 · Cited by 1
A Wearable Sensors Based Elderly Activity Recognition Model Using Deep LearningPreprint
Arafa, A., Harfoush, H., El-Fishawy, N. A., & Radad, M. A. (2025) · Research Square · doi:10.21203/rs.3.rs-6944419/v1 · Cited by 1
Human Action Recognition in Videos
Tolety, K. (2020) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2020.31009
Proposta de um Ambiente Interacional baseado em um Espaço Inteligente Programável
Custodio, P. V. D. S., Queiroz, F. M. D., Almonfrey, D., Cotta, W. A. A., do Carmo, A. P., & Vassallo, R. F. (2020) · doi:10.5753/sbcup.2020.11224
Activity Detection of Untrimmed CCTV ATM Footage Using 3D Convolutional Neural Network
Ramadhani, A. H., & Chahyati, D. (2020) · International Conference on Advanced Computer Science and Information Systems · doi:10.1109/icacsis51025.2020.9263171
Hybridized Deep Learning Architectures for Human Activity Recognition
Pillay, B. J., Pillay, A. W., & Jembere, E. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-66151-9_11
Local Trajectory Occurrence Patterns for Partial Action and Gesture Recognition
Garzón, G., & Martínez, F. (2021) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.11.1.9286
“Recognizing human actions is a fundamental task in many areas and applications, such as surveillance and crowd control [1], automatic annotation of human actions in videos [2] and video indexing [3], analysis of sports videos [4], HCI applications [5] and gesture-based video games interaction [6], among other examples…”
BackgroundZhong, Z., Lin, C., Kanai‐Pak, M., Maeda, J., Kitajima, Y., Nakamura, M., Kuwahara, N., Ogata, T., & Ota, J. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3075477 · Cited by 1
Probabilistic Model Checking for Activity Recognition in Medical Serious Games
L’Yvonnet, T., MARIA, E. D., Moisan, S., & Rigault, J. (2021) · IEEE/ACM International Workshop on Software Engineering for Healthcare (SEH) · doi:10.1109/seh52539.2021.00019
Activity recognition and bioinspired approaches for robotics in intelligent environments
Ranieri, C. M. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.55.2021.tde-11082021-112227 · Cited by 1
Relevant multichannel time series representation based on functional measures in RKHS
Giraldo, P., & Diego, J. (2020)
Exploiting Egocentric Cues for Action Recognition for Ambient Assisted Living Applications
Núñez-Marcos, A., Azkune, G., & Arganda‐Carreras, I. (2021) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-030-14647-4_10
Action Recognition Based on Hierarchical Graph Recurrent Networks with 2D Skeleton
Li, G., & Wang, S. (2020) · International Conference on Information Science and Control Engineering · doi:10.1109/icisce50968.2020.00046
Hierarchical Graph Sparse Attention Network for Online Action Tracking
Li, G., & Wang, S. (2021) · International Conference on Information Technology and Biomedical Engineering (ICITBE) · doi:10.1109/icitbe54178.2021.00029
Human-Robot Collaborations in Industrial Automation
Schmitz, A. (2022) · MDPI eBooks · doi:10.3390/books978-3-0365-5214-9
Image Recognition Applied to Security Systems: The Case of Burkina Faso
Tiendrebeogo, A. (2022) · New Media and Mass Communication · doi:10.7176/nmmc/102-04
S, N. P., Pandith, K., Koti, M. S., Thinakaran, R., & Pawar, S. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.01309121 · Cited by 1
“Some of them are used in sequential tasks to highlight key input frames [28], while others are used to simply focus on spatial regions of relevance [10, 9, 2].”
BackgroundMethodOn the Importance of Temporal Features in Domain Adaptation Methods for Action Recognition
Conte, D., Fioretti, G. G., & Sansone, C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23028-8_27
Action Recognition of Human Skeletal Data Using CNN and LSTM
Asghar, Z., Moin, S., Qutab, I., & Aqeel, M. (2023) · International Journal of Innovations in Science and Technology · doi:10.33411/ijist/2023050102
Spatio-Temporal Human Action Recognition Model using Deep Learning Techniques
Sarabu, A., & Santra, A. K. (2022) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v10i2s.5932
Action Recognition for Solo-Militant Based on ResNet and Rule Matching
Tong, L., Feng, J., Zhao, H., & Liu, K. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-9297-1_15
On Flexible Trajectory Description for Effective Rigid Body Motion Reproduction and Recognition
Yang, J., & Guo, Y. (2023) · Journal of Shanghai Jiaotong University (Science) · doi:10.1007/s12204-023-2604-0
Hand Sign Recognition To Structured Sentences
Harchandani, R., Nanjundan, P., & George, J. P. (2023) · International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs57279.2023.10112706
A Survey of Computer Vision-Based Fall Detection and Technology Perspectives
Yang, M., Li, X., Liu, J., Wang, S., & Liu, L. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-2385-4_45 · Cited by 1
VISION BASED SURVEILLANCE SYSTEM FOR THEFT DETECTION IN SUPERMARKETS
(2023) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets40312
Driver behaviour recognition based on eye gaze
Zhao, Y., Lv, C., & Yang, L. (2023) · Elsevier eBooks · doi:10.1016/b978-0-443-18997-5.00009-4
Self-citationRequirements for a Vision Based System for Detecting Epileptic Seizures
Stephen, O. O. (2023) · American Journal of Biomedical Science & Research · doi:10.34297/ajbsr.2023.18.002458
Design and implementation of an optimization human pose estimation scheme
Liu, L., Blancaflor, E., Sun, Y., & Wang, S. (2023) · International Conference on Computer Vision and Pattern Analysis (ICCPA) · doi:10.1117/12.2684163
“chnology has ording to rese e of 82 billio includes an A is new fitnes uman action hnology [3].”
BackgroundQuan, K. J., Sani, Z. M., Izzuddin, T. A., Azizan, A., & Ghani, H. A. (2023) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v12.i4.pp1534-1542
Skeleton Action Recognition Based on Spatio-Temporal Features
Huang, Q., Xie, M., Li, X., & Wang, S. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10223086
“Action recognition[1, 2, 3] based on skeletons has been widely studied in applications such as healthcare, education and surveillance by encoding the three-dimensional joint positions of human bodies.”
BackgroundBatool, M., Jalal, A., Alazeb, A., Mudawi, N. A., Alshehri, M. S., Almakdi, S., Almujally, N. A., Alotaibi, S. S., & Algarni, A. M. (2023) · Research Square · doi:10.21203/rs.3.rs-3337380/v1
Skeleton-Based Recognition of Traditional Greek Dance Steps using Machine Learning Algorithms
Tragiannis, K., Balafoutis, T., Balaska, V. E., & Gasteratos, A. C. (2023) · IEEE International Conference on Imaging Systems and Techniques (IST) · doi:10.1109/ist59124.2023.10355702
“Several data types can be utilized for this purpose, including RGB, depth-based, and skeleton-based data [5].”
BackgroundWei, S., & Li, X. (2023) · Optical and Quantum Electronics · doi:10.1007/s11082-023-05996-y
“In traditional sports training, it often relies on the coach’s experience and visual observation, which is easily influenced by subjective factors and cannot accurately analyze the movements and postures of athletes (Poppe 2010; Zhang et al. 2019).”
RetractedSeparable ConvNet Spatiotemporal Mixer for Action Recognition
Cheng, H.-Y., Yu, C.-C., & Li, C. (2024) · Electronics · doi:10.3390/electronics13030496
Deep Learning Model for Behavioral Image Data Annotation
Wang, B., He, W. P., Jiang, C., Ru, X., & Du, C. (2024) · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI) · doi:10.1109/icmcsi61536.2024.00064
“Developed over several decades, human action recognition [5]-[8] has become the prominent branch of computer vision, machine learning, and pattern recognition theory.”
BackgroundREAL-TIME HAND GESTURE DETECTION AND INTERPRETATION ON ANDROID
(2024) · International Research Journal of Modernization in Engineering Technology and Science · doi:10.56726/irjmets53026
Naaraju, P. (2024) · Journal of Electrical Systems · doi:10.52783/jes.3238
“Consequently, imposing particular technological specifications about the sensor's performance, size, and battery life, among other things [8].”
BackgroundFundamentals of proactive human–robot collaboration
Li, S., Zheng, P., & Wang, L. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-313943-7.00010-7
Multi-class and Multi-label Classification of an Assembly Task in Manufacturing
García-Domínguez, M., Heras, J., Marani, R., & D’Orazio, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-62799-6_21
Detection of Abnormal Behavior of Train Drivers Based on Skeleton Data
朱, 高. (2024) · Computer Science and Application · doi:10.12677/csa.2024.147162
Zhang, S., Yin, J., & Dang, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4898102
Data Augmentation Method Using Generative Model for Skeleton-based Human Action Recognition
Hamabe, S., & Yamada, K. (2024) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.144.1209
Human Activity Recognition Using Machine Learning Models
Balamurali, R., Mishra, P., Reddy, V., & Ganesh, B. R. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-8422-6_20
KITHAR: a Knowledge Informed Tree based Neural Network for Interpretable Human Activity Recognition
Zhang, G., Zhang, H., Szczerbicki, E., & Zhang, X. (2024) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbd-ai65562.2024.00018
“HAR [1] is a rapidly evolving field that aims to automatically identify and classify human activity data collected through various mechanisms, such as wireless signals [2], cameras [3], sensors [4,5], and micro-Doppler radar [6].”
Self-citationMultiplayer Interaction Feature Extraction for Skeleton-Based Action Recognition
Shi, W., Pan, Y., Li, D., Wen, Y., & Liu, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-4279-3_7
A Review of Deep Learning Based Human Activity Recognition System
Thomas, A. L., & Judith, J. E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-031-88992-9_12
Research on the Recognition and Evaluation Method of Sparring Movements Based on Skeletal Keypoints
Liu, Y., & Guo-qing, Z. (2025) · IEEE International Conference on Electronics, Energy Systems and Power Engineering (EESPE) · doi:10.1109/eespe63401.2025.10987112
“Skeletal key point detection technology is the foundation of this field, and its accuracy and robustness directly affect subsequent recognition and evaluation [1].”
Krishna, N. V., & Manikavelan, D. (2025) · AIP conference proceedings · doi:10.1063/5.0266019
Spatio-Temporal Deviation Calibration for Skeleton-Based Human Action Recognition
Freixas, G. M., Feng, Z., Han, K. T. Z., Jin, C., Hu, J., Lei, J., & Wu, X. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-6963-9_13
Shahar, N., As’ari, M. A., Zainal, N., Zulkifley, M. A., Ibrahim, A. A., & Ghazali, M. H. M. (2025) · Research Square · doi:10.21203/rs.3.rs-6763631/v1
Cao, Y., Wang, F., & Zheng, Q. (2025) · MATEC Web of Conferences · doi:10.1051/matecconf/202541306003
Soujanya, K. L. S. (2025) · Journal of Propulsion Technology · doi:10.52783/tjjpt.v46.i03.10110
Leveraging Deep Learning Approach for the Detection of Human Activities from Video Sequences
Preethi Salian, K., & Karthik, K. (2025) · International Journal of Image Graphics and Signal Processing · doi:10.5815/ijigsp.2025.06.05
Human action recognition in video data based on deep learning methods
Shaker, S. H., Mahdi, A. F., Hasan, R. F., & Azeez, R. A. (2025) · AIP conference proceedings · doi:10.1063/5.0301806
Privacy Aware Human-Object Interaction in the Wild Novel Dataset
Fredenslund, L. L., Ismiroglou, V., Moeslund, T. B., & Nasrollahi, K. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-07343-3_10
Wang, X., Pirasteh, S., Varshosaz, M., & Fang, Z. (2026) · Geomatics Natural Hazards and Risk · doi:10.1080/19475705.2026.2621550 · Cited by 1
Real-time human activity recognition on edge devices using quantized deep neural networks
Gou, H., & Huang, M. (2026) · International Conference on Communication, Information, and Digital Technologies (CIDT) · doi:10.1117/12.3089273
“These techniques significantly reduce memory usage and inference latency while maintaining high classification accuracy [3].”
Compressed action matrix: one-shot human action recognition using skeleton path data structure
Ranjbar, M. H., Abdi, A., & Park, J. H. (2026) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02218-8
“One of the earliest path-based methods is the motion history image (MHI) method, which represents each motion as a 2D image by accumulating the differences between consecutive frames [15].”
Liu, G., & Sun, D. (2025) · IEEE International Conference on Network Infrastructure and Digital Content (IC-NIDC) · doi:10.1109/ic-nidc67200.2025.11390258
“Recently, skeleton-based meth-ods [4, 5, 6, 7, 8] have gained prominence.”
Alghasham, N., & Albattah, W. (2026) · PLoS ONE · doi:10.1371/journal.pone.0343132
Wen, J., Zhang, X., & Chew, J. Y. (2026) · Advanced Robotics · doi:10.1080/01691864.2026.2626369
SOP-Guided Co-Enhanced CLIP for Action Recognition in Logistics Warehouse Packaging
Qi, W., Zhang, K., Sun, Y., Zhang, H., Xu, X., & Qin, H. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11402227
“Conventional action recognition models are mainly based on visual features of frames or videos to infer actions by detecting subjects or analyzing gestures [5], [6].”
Self-citationImpact of Background Removal and Pose on Deep Learning Industrial Action Recognition
Yang, C.-L., Liang, S.-H., Lin, P. T., Hsiao, Z.-S., & Yen, T.-Y. (2026) · International Conference on Knowledge and Smart Technology · doi:10.1109/kst67832.2026.11432375
“RGB-based methods retain contextual and environmental detail, making them suitable for complex scenarios but often susceptible to background noise [15]–[18].”
Event-based Human Action Recognition: Rehabilitation Monitoring Dataset and Models
Hafiz, M., Hassan, M. S., Gener, S., Mack, J., & Akoglu, A. (2025) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds67896.2025.00103
Look2React: Making VR NPCs Come Alive with Dynamic Vision-Guided Reactions
Vatsal, R., Huang, X., & Xiao, R. (2026) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2026.3679121 · Cited by 1
“However, skeleton-based activity recognition means that items equipped in the environment are omitted, which can misclassify contextually distinct behaviors [67].”
Human Action Recognition in Videos with Shallow and Deep Learning
Phan, T. H. H. (2019) · theses.fr (ABES) · doi:10.70675/fa813329z9321z4fc2za918zd4282f6ec3ac
Devineau, G. (2020) · theses.fr (ABES) · doi:10.70675/f79154a4z5b19z4ca7zaad7zbaea74138b63
Shicen, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-49320-6
“…methods, while adept at modeling long-range temporal dependencies through self-attention, tend to produce holistic feature embeddings that resist decomposition into physically meaningful components—a characteristic that renders them opaque to coaches and athletes seeking actionable feedback 34 .”
MagiaPose: Pose Recognition and Quality Assessment with ViViT
Zhou, H., Wu, Z., Wang, J., Zhang, J. L., Sun, H., & Wang, T. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487683
“It serves as a foundational component for higher-level tasks such as action recognition [4], [5] and human-computer interaction [6].”
Hu, Z., Yang, Y., Wang, K., Chen, X., & Chao, W. (2026) · Electronics · doi:10.3390/electronics15102100
Child-Centered AI-Assisted Autism Diagnosis and Treatment
Wang, Z., Wang, X., Chen, B., Nie, W., Zhang, H., & Liu, H. (2026) · Springer eBooks · doi:10.1007/978-981-95-5585-7_24
Self-citationViolenceVIT-TM: A Hybrid EfficientViT–LSTM Architecture for Video-Based Violence Detection
Limantara, R., Wibisono, D., Rafi, A. A., Andreas, C., Nugraha, S. A., & Yuwono, D. H. (2026) · International Conference on Current Research in Artificial Intelligence and Data Science (ICCRAIDS) · doi:10.1109/iccraids67816.2026.11519662
“Traditional methods for detecting violence relied heavily on handcrafted visual features such as motion magnitude, optical flow, and spatio-temporal interest points [5], [6].”
TATS: toolbox for time series data augmentation
Warchoł, D., & Oszust, M. (2026) · PeerJ Computer Science · doi:10.7717/peerj-cs.3944
Identifying weapon-carrying actions in video surveillance systems through self-attention
Ruiz-Santaquiteria, J., Déniz, Ó., & Bueno, G. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106087
Human Activity Recognition Using CNN and LSTM-Based Deep Learning Algorithms
Nagaraj, P., Muralidharan, B., Uma, P. S., Prabakaran, R. P., Ramakrishnan, M., & Virumapandi, V. (2026) · International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE) · doi:10.1109/iccrtee68719.2026.11566207
VideoAlign: A Toolkit to Make Video Analysis Accessible EICS013
Belo, J. M. E., Oei, K., & Feit, A. M. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3816765
“Therefore, we do not cover them here and instead refer readers to surveys on the topic [7, 64].”
A New Geometric Framework for 3D Skeletal Action Representation in Kendall Space
Gual-Arnau, X., & Monterde, J. (2026) · SIAM Journal on Imaging Sciences · doi:10.1137/25m1787938
Abdulrahman, B., Zhu, Z., & Conway, A. J. (2026) · Electronics · doi:10.3390/electronics15143139
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.
