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 301–400 of 512
Learning dictionaries of kinematic primitives for action classification
Vignolo, A., Noceti, N., Sciutti, A., Odone, F., & Sandini, G. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412363 · Cited by 4
“on already trimmed video sequences [29], the detection task remains a challenge and at the same time an essential element for fully automatic motion recognition systems.”
BackgroundHigh-Accuracy Early Recognition of Upper-Limb Motions for Exoskeleton-Assisted Mirror Rehabilitation
Wang, H., Yao, Y., Lei, H., Shi, Y., & Pei, S. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3534684 · Cited by 3
“However,theyrequire highdatavolume,high-performancecomputers,longtraining cycles,andpoorperformanceonsmallsampledatasets[11], [15].”
Mimicker-in-the-Browser: A Novel Interaction Using Mimicry to Augment the Browsing Experience
Arakawa, R., & Yakura, H. (2020) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3382507.3418811 · Cited by 4
“In this respect, with the development of deep learning techniques, we can now estimate a human pose with a high degree of accuracy using only a single RGB camera [62].”
BackgroundAugmentation of Human Action Datasets with Suboptimal Warping and Representative Data Samples
Warchoł, D., & Oszust, M. (2022) · Sensors · doi:10.3390/s22082947 · Cited by 3
“In recent years, many methods for human action recognition have been developed [1].”
BackgroundShort-term path signature for skeleton-based action recognition
Zhang, H., Ren, H., Liang, J.-Y., Song, Z.-J., & Zhang, M. (2022) · Signal Image and Video Processing · doi:10.1007/s11760-022-02404-y · Cited by 3
“These methods can be divided into several categories based on their data types, including RGB-based methods, depthbased methods and skeleton-based methods [44].”
MethodSelf-citationFCTNet: Fusion of 3D CNN and transformer dance action recognition network
Ning, T., Zhang, T., & Huang, G. (2024) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-235302 · Cited by 3
RetractedEmbedding Task Structure for Action Detection
Peven, M., & Hager, G. D. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00647 · Cited by 4
“Likewise, complex spatio-temporal patterns in videos can be learned from sufficiently large data sets as evidenced by the fact that the performance of video classification models have become commensurate to their image classification counterparts [71].”
BackgroundEfficient reconfigurable system for home monitoring of the elderly via action recognition
Deniz, D., Isern, J., Solanti, J., Jääskeläinen, P., Hnětynka, P., Bulej, L., Ros, E., & Barranco, F. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111383 · Cited by 3
Chen, Z., Wang, G., & Jiang, W. (2025) · International Conference on Data Science and Information System (ICDSIS) · doi:10.1109/icdsis65355.2025.11070879 · Cited by 3
“Zhang et al. [18] comprehensive review of vision-based human action recognition techniques, from handcrafted feature to deep learning.”
Zhao, B., Wang, Y., Su, K., Ren, H., & Sun, H. (2021) · Sensors · doi:10.3390/s21062217 · Cited by 4
Patient’s actions recognition in hospital’s recovery department based on RGB-D dataset
Mollaei, H., Sepehri, M. M., & Khatibi, T. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14200-4 · Cited by 3
Hou, J., Chen, G., Zhou, Q., Liu, C., Zuo, X., Tang, Y., & Cheng, C. (2023) · Physical Communication · doi:10.1016/j.phycom.2023.102037 · Cited by 3
Hossen, M. A., & Abas, P. E. (2023) · International Journal of Computing and Digital Systems · doi:10.12785/ijcds/1401110 · Cited by 3
Enhancing Virtual Yoga Training: A Real Time Pose Assessment with Voice-Guided Accuracy Feedback
Kamra, V., Singh, B. P., Srivastava, S., & Kumar, V. (2024) · International Conference on Intelligent Systems for Cybersecurity (ISCS) · doi:10.1109/iscs61804.2024.10581367 · Cited by 3
“These models learn patterns from large datasets, capturing nuances like intonation, pitch, and rhythm to create more human-like speech [24].”
BackgroundHuman Action Recognition Based on Bag-of-Words
Ameer, R. S. A., & Altaei, M. S. M. (2020) · Iraqi Journal of Science · doi:10.24996/ijs.2020.61.5.27 · Cited by 3
Joefrie, Y. Y., & Aono, M. (2020) · IEEE Access · doi:10.1109/access.2020.3025931 · Cited by 3
“A study in [10] explained very well the progress”
BackgroundZhang, H., Zhou, Y., Dong, L., Lei, Q., & Du, J. (2021) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2021.3116227 · Cited by 3
Self-citationApplication of Fuzzy Clustering Model in the Classification of Sports Training Movements
Song, B. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4308283 · Cited by 3
Oszust, M., & Warchoł, D. (2022) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai56018.2022.00108 · Cited by 3
Nenosaban, S. J., & Tari, E. (2023) · Journal of Scientific Research Education and Technology (JSRET) · doi:10.58526/jsret.v2i3.238 · Cited by 6
“Where the relationship between humans and information has changed the nature of society, about what is thought and how thought develops, so that human digital culture experiences the effects of change from the ongoing digital revolution (Zhang et al., 2019).”
Human Event Recognition in Smart Classrooms Using Computer Vision: A Systematic Literature Review
Córdoba-Tlaxcalteco, M. L., & Benítez–Guerrero, E. (2023) · Programming and Computer Software · doi:10.1134/s0361768823080066 · Cited by 4
Segregating and Recognizing Human Actions from Video Footages Using LRCN Technique
Pandya, M., Pillai, A., & Rupani, H. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-3383-9_1 · Cited by 3
Human Pose Estimation Applying ANN While RGB-D Cameras Video Handling
Korovin, I., & Ivanov, D. Y. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-51971-1_47 · Cited by 3
EVALUATING SECTOR RING HISTOGRAM OF ORIENTED GRADIENTS FILTER IN LOCATING HUMANS WITHIN UAV IMAGES
Ghasemi, M., Varshosaz, M., & Pirasteh, S. (2020) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2020-23-2020 · Cited by 3
“…on human detection using photos has concentrated mostly on pedestrian detection (Mihçioğlu et al., 2019, ZhangSr et at., 2019, Karg et al.,2020), study of human movement (Bahri et al., 2019, Zhang et al., 2019) and facial recognition (Zhang et al. , 2019, Ding et al., 2019, Prasad et al., 2020).”
BackgroundHuman Activity Recognition by Utilizing Local Ternary Pattern and Histogram of Oriented Gradients
Kushwaha, A., & Khare, A. (2020) · Lecture notes in networks and systems · doi:10.1007/978-981-15-8377-3_27 · Cited by 3
Early-stopped learning for action prediction in videos
Saremi, M., & Yaghmaee, F. (2021) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-021-00216-3 · Cited by 3
“detection and pose estimation techniques [38].”
Gaussian Mixture Model in Dynamic Background of Video Sequences for Human Detection
Setyoko, B. H., Noersasongko, E., Shidik, G. F., Budiman, F., Soeleman, M. A., Andono, P. N., & Pujiono, P. (2022) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti56927.2022.10052825 · Cited by 3
“Because of the many benefits that can be obtained from HAR, it makes HAR still become one of the research trend topics in Computer Vision [7].”
BackgroundKamada, S., & Ichimura, T. (2019) · IEEE International Workshop on Computational Intelligence and Applications (IWCIA) · doi:10.1109/iwcia47330.2019.8955036 · Cited by 4
Unsupervised Action Proposals Using Support Vector Classifiers for Online Video Processing
Baptista-Ríos, M., López-Sastre, R. J., Acevedo-Rodríguez, F. J., Martin-Martin, P., & Maldonado-Bascón, S. (2020) · Sensors · doi:10.3390/s20102953 · Cited by 3
“For a recent survey on the topic, we refer the reader to [10].”
BackgroundConsistent constraint-based video-level learning for action recognition
Shi, Q., Zhang, H., Ren, H., Du, J., & Lei, Q. (2020) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-020-00519-1 · Cited by 3
Self-citationChakraborty, S., & Pradhan, B. (2024) · Sensors · doi:10.3390/s24092874 · Cited by 3
Shang, X., Song, W., Chen, Z., & Zhang, C. (2022) · IET Image Processing · doi:10.1049/ipr2.12608 · Cited by 2
Artificial Intelligence (AI) – based strategies for point cloud data and digital twins
Aftab, I., Dowajy, M., Kapitány, K., & Lovas, T. (2023) · Nova Geodesia · doi:10.55779/ng33138 · Cited by 2
FPGA-QHAR: Throughput-Optimized for Quantized Two-Stream Human Action Recognition on the Edge
Alhussain, A., & Lin, M. (2023) · IEEE International Conference on Smart Communities: Improving Quality of Life using AI, Robotics and IoT (HONET) · doi:10.1109/honet59747.2023.10374852 · Cited by 2
Disassembly Plan Representation by Hypergraph
Verkuilen, A., Zijderveld, M., de Buck, N., & Coenen, J. (2025) · Automation · doi:10.3390/automation6010010 · Cited by 2
From Body Parts to Holistic Action: A Fine-Grained Teacher-Student CLIP for Action Recognition
Ou, Y., Shi, X., Chen, J., He, R., & Liu, C. (2025) · IEEE Signal Processing Letters · doi:10.1109/lsp.2025.3548448 · Cited by 2
Mikami, K., Huang, W., Chen, Y., & Nakazawa, J. (2025) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3715014.3722047 · Cited by 2
Multi-Dimensional Assessment of Rehabilitation Exercises with Multi-gate Mixture-of-Experts
He, T. C., Wang, L., & Cheng, H. (2025) · doi:10.1145/3730436.3730498 · Cited by 4
“Graph convolutional networks (GCNs) have demonstrated greater potential compared to standard CNN [55].”
Baker, S., Kilcullen, M., & Kandasamy, Y. (2025) · Acta Paediatrica · doi:10.1111/apa.70319 · Cited by 2
“Vision-based approaches are the most prevalent for motion capture, commonly utilising RGB, RGB-D or infrared cameras [12, 24, 29].”
Song, Q., Kuwano, M., Obo, T., & Kubota, N. (2025) · Applied Sciences · doi:10.3390/app152212144 · Cited by 2
Hyperbolic Transformers with LLMs for Multimodal Human Activity Recognition
Soleimani, F., Khodabandelou, G., Chibani, A., & Amirat, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247069 · Cited by 2
“Examples include fusing video with wearable sensors [4] or pairing audio with inertial readings [5], both of which enhance precision by capturing extended temporal patterns.”
Wang, C., & Mohamed, A. S. A. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03000-z · Cited by 3
“…action recognition method based on 3D labeled dataset 5 H.B Zhang et al A Comprehensive Survey of Vision-Based Human Action Recognition Methods [ 45] 2020 Comprehensive analysis of human motion-recognition methods 6 Bin Ren et al A survey on 3d skeleton-based action recognition using the…”
Wang, S., Wang, X., Jiang, B., Zhu, L., Li, G., Wang, Y., Tian, Y., & Tang, J. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02936-7 · Cited by 5
“Extended author information available on the last page of the article Ahmad et al., 2021; Zhang et al., 2019; Ji et al., 2012; Yao et al., 2011; Varol et al., 2021), most researchers rely on the mature technology of RGB cameras to achieve effective activity classification.”
Learning Human-Human Interactions in Images from Weak Textual Supervision
Alper, M., & Averbuch‐Elor, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00270 · Cited by 6
“[85] Hong-Bo Zhang, Yi-Xiang Zhang, Bineng Zhong, Qing Lei, Lijie Yang, Ji-Xiang Du, and Duan-Sheng Chen.”
BackgroundSriLakshmi, N. V., & Radha, N. (2024) · International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) · doi:10.1109/iitcee59897.2024.10467910 · Cited by 2
“Human action recognition, a vital task in the fields of computer vision and artificial intelligence, shows a essential role in enabling machines to understand and interpret human behaviour from visual data [1].”
BackgroundDeshpande, M. M., Agarwal, A., & Kamathe, R. S. (2024) · Innovations in Sustainable Technologies and Computing · doi:10.1007/978-981-97-1111-6_1 · Cited by 2
Assembly Action Recognition based on Dual Stream Fusion of Skeleton and Video Data
Zhao, C., Jin, T., Su, N., & Yan, Y. (2024) · International Conference on Image and Graphics Processing (ICIGP) · doi:10.1145/3647649.3647676 · Cited by 2
Córdoba-Tlaxcalteco, M. L., & Benítez–Guerrero, E. (2024) · Proceedings of the Institute for System Programming of RAS · doi:10.15514/ispras-2024-36(1)-11 · Cited by 4
“In [10], deep learning methods with automatic feature extraction for vision-based human event recognition are reviewed.”
MethodMan, K., Chahl, J., Mayer, W., & Perera, A. G. (2024) · IEEE Access · doi:10.1109/access.2024.3423344 · Cited by 3
“There are a wide range of methods to achieve human action recognition including depth sequence and feature fusion methodologies [16], but the model used here is a skeleton based model uses a deep neural network classifier to predict actions based on 2D human poses extracted from consecutive video…”
MethodPrivacy-preserving Human Activity Recognition via Video-based Range-Doppler Synthesis
Cui, Z., Mei, L., Pei, S., Li, B., & Zhou, X. (2024) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd61410.2024.10580232 · Cited by 2
“According to the work [18], state-of-the-art vision-based methods can achieve efficient and accurate multi-person pose estimation in complex scenes.”
A Bottom-Up Human Pose Estimation Correction Method Based on Object Detection
Zhang, X., Meng, X., Chu, K.-F., & Wang, L. (2024) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls61622.2024.10606772 · Cited by 2
“Human pose estimation is a fundamental task in the fields of computer vision and robotics, and also has extensive applications in motion capture[1], animation[2], motion analysis[3], healthcare[4], etc.”
BackgroundMulti-Scale Temporal Relations and Segmented Channel Attention for Video Anomaly Detection
Sun, Y., Nie, X., Scotney, B. W., Zhang, S., & Liu, X. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650111 · Cited by 2
“Therefore, a new method was proposed by Zhang et al. [15], which is based on video frame prediction.”
MethodContext-Aware Action Recognition: Introducing a Comprehensive Dataset for Behavior Contrast
Sasaki, T., Ito, Y., & Kondo, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73229-4_15 · Cited by 2
Chen, X., Han, X., & Cui, Y. H. (2024) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec60942.2024.10732925 · Cited by 2
“Therefore, early methods were based on RGB video or depth sequence maps [4].”
MethodShahar, N., As’ari, M. A., Ghazali, M. H. M., Zainal, N., Zulkifley, M. A., Ibrahim, A. A., Omar, Z., Rahmat, M. S., Gan, K. B., & Moubark, A. M. (2025) · Sensors · doi:10.3390/s25247615 · Cited by 2
“Moreover, these systems typically necessitate sophisticated processing techniques and costly camera setups to ensure optimal performance [1].”
Visual Methods for Sign Language Recognition: A Modality-Based Review
Seddik, B., & Amara, N. E. B. (2021) · Smart sensors, measurement and instrumentation · doi:10.1007/978-3-030-81982-8_9 · Cited by 6
Weakly supervised temporal action localization: a survey
Li, R., Zhang, T., & Zhang, R. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18554-9 · Cited by 4
Enhanced Depth Motion Maps for Improved Human Action Recognition from Depth Action Sequences
Rao, D. S., Rao, L. K., Bhagyaraju, V., & Meng, G. K. (2024) · Traitement du signal · doi:10.18280/ts.410334 · Cited by 2
“Notably, a depth-based camera possesses the capability to capture high-resolution videos even under extremely low illumination conditions [6-8].”
Ha, M., Bae, W.-G., Bae, G., & Lee, J. T. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0960-4_2 · Cited by 5
“Existing methods for action recognition under low-light settings can be broadly categorized into two approaches: two-stage and two-stream [50,59].”
Cross-attention multi branch for Vietnamese sign language recognition: CrossViViT
Chu, M. H., Nguyen, H. D., Nguyễn, T. N. A., & Vu, H. N. (2025) · Discover Computing · doi:10.1007/s10791-025-09669-0 · Cited by 2
“Computer vision involves analyzing video data from digital cameras situated within the activity environment [3].”
Early Stopping for Two-Stream Fusion Applied to Action Recognition
Maia, H. D. A., Souza, M. R. E., Santos, A., Bobadilla, J. C. M., Vieira, M. B., & Pedrini, H. (2022) · Communications in computer and information science · doi:10.1007/978-3-030-94893-1_14 · Cited by 2
Deep Learning in Taekwondo Techniques Recognition System: A Preliminary Approach
Barbosa, P., Cunha, P., Carvalho, V. H., & Soares, F. (2022) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-09385-2_25 · Cited by 2
Human Activity Recognition with Video Classification
Nath, R. K., Rasool, A., Gangwar, N., & Jha, H. (2022) · International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) · doi:10.1109/icac3n56670.2022.10074309 · Cited by 2
Indoor person behavior recognition based on deep learning and knowledge graph
Cheng, L., Gou, X., Tang, C., Li, Y., Jiang, X., & Zuo, H. (2023) · International Conference on Digital Society and Intelligent Systems (DSInS) · doi:10.1117/12.2673563 · Cited by 2
“According to the structure of deep neural networks, the main representative works can be summarized into three kinds: based on dual-stream convolutional neural networks [4], based on 3D convolutional neural networks [5], and based on Long Short-Term Memory networks (LSTM) [6].”
Guo, Y., Bai, Y., Shi, D., Cai, Y., & Bian, W. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00373 · Cited by 2
“Human pose estimation (HPE) [2, 19, 34] is a fundamental task for human-centered relevant studies, i.e. , human behavior study [3, 23], action interaction [39, 46] and anomaly event recognition [18, 22, 31], etc.”
BackgroundEarly Childhood Action Monitoring and Analytics System (ECAMS)
Andarage, I. S. N., Fernando, D., Lokuarachchi, B. A., Athuluwage, M. G., & Wijewickrama, P. (2023) · IEEE Pacific Rim International Symposium on Dependable Computing (PRDC) · doi:10.1109/prdc59308.2023.00056 · Cited by 4
“Human action recognition is also a widely explored task on estimated human pose in video data [34].”
BackgroundTransNet: A Transfer Learning-Based Network for Human Action Recognition
Alomar, K., & Cai, X. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00277 · Cited by 2
“In fact, real-world action recognition methods involving semantic segmentation of video content are still in their infancy phase [30].”
BackgroundA Case Study on Human Activity Detection and Recognition
Prabhu, G. N., & Salins, M. (2024) · International Journal of Management Technology and Social Sciences · doi:10.47992/ijmts.2581.6012.0349 · Cited by 4
A Dempster-Shafer Evidence Theory Based Multimodal Human Gesture Recognition Method
Tian, Z., & Zhang, Y. (2020) · International Conference on Computing and Data Engineering (ICCDE) · doi:10.1145/3379247.3379288 · Cited by 2
“2 Depth-based Recognition Methods The depth-based recognition methods have been rapidly developed due to the fact that depth data are stable with respect to changes in environment and background and can quickly segment objects [11].”
BackgroundSelf-citationA Novel Human Action Recognition and Behaviour Analysis Technique using SWFHOG
Jahagirdar, A., & Nagmode, M. S. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110475 · Cited by 2
“SIFT, SURF, LBP, BRISK, MSER and FREAK are some examples of local features used for action recognition [1] The emphasis of this related work is to review various methods that use salient point detection, wavelet transform as a feature and latest trends in action recognition.”
MethodVision-Based Human Activity Recognition
Mahmud, T., & Hasan, M. (2021) · Intelligent systems reference library · doi:10.1007/978-3-030-68590-4_1 · Cited by 5
FASSD-Net Model for Person Semantic Segmentation
Garcia-Ortiz, L. B., Portillo-Portillo, J., Hernandez-Suarez, A., Olivares-Mercado, J., Sánchez-Pérez, G., Toscano, K., Perez-Meana, H. M., & Benítez-García, G. (2021) · Electronics · doi:10.3390/electronics10121393 · Cited by 2
“in video, human pose estimation, human tracking analysis and understanding of time series data [4].”
BackgroundDeep Saliency Map Generators for Multispectral Video Classification
Bayer, J., Münch, D., & Arens, M. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9955639 · Cited by 2
“…following section only covers selected work on human action recognition and saliency map generators in the deep learning domain, the reader is referred to a survey paper on human action recognition [17], [18] or explainable AI methods [15], [19], [20] for a comprehensive overview of shallow models.”
BackgroundAn HMM-Based Approach for Human Interaction Using Multiple Feature DescriptorsPreprint
Zaib, M. H., & Khan, M. J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4656240 · Cited by 4
Deep Multimodal Habit Tracking System: A User-adaptive Approach for Low-power Embedded Systems
Deniz, D., Jimenez-Perera, G., Nolasco, R., Corral, J., & Barranco, F. (2023) · Journal of Signal Processing Systems · doi:10.1007/s11265-023-01840-4 · Cited by 1
Pedestrian Abnormal U-turn Behavior Recognition Model Based on Baidu AI
Zhu, W., Zhao, R., Dong, C., Zhang, H., Li, C., Ma, Y., & Jia, P. (2022) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3573428.3573707 · Cited by 1
Self-citationDong, X. (2023) · Applied Mathematics and Nonlinear Sciences · doi:10.2478/amns.2023.2.00468 · Cited by 1
Shi, M. (2024) · Optical and Quantum Electronics · doi:10.1007/s11082-023-06167-9 · Cited by 1
“…a method of action recognition is proposed, which uses the dynamic time warping method to match the features of the image contour after wavelet transform, extract the spatio-temporal interest points of each frame in the image sequence, and match the different interest points (Zhang et al. 2019).”
RetractedAn Optimized Deep LSTM Model for Human Action Recognition
Jandhyam, L. A., Ragupathy, R., & Satyala, N. (2024) · Revue d intelligence artificielle · doi:10.18280/ria.380102 · Cited by 2
“This complexity hugely limited the efficiency of video-assisted human actions [4].”
Fang, X., & Guo, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3437371 · Cited by 2
“This review systematically summarized recent research methods and explored the progress of different meth-ods in HMR research [9].”
MethodMulti-Task Diffusion Learning for Time Series Classification
Zheng, S., Liu, Z., Tian, L., Ye, L., Zheng, S., Peng, P., & Chu, W. (2024) · Electronics · doi:10.3390/electronics13204015 · Cited by 1
“Time series data serve as a common means to depict temporal phenomena and have widespread applications across various industries, including medical diagnosis [1], weather forecasting [2], human action recognition [3], and power system monitoring [4,5].”
Saffari, M., Singh, Y. P., & Khodayar, M. (2025) · IEEE International Conference on Electro Information Technology · doi:10.1109/eit64391.2025.11103603 · Cited by 1
“Vision-based approaches use image or video sequences captured by cameras to recognize actions based on visual cues [3].”
Research on Privacy Protection Video Behavior Recognition Method Based on Improved SlowFast
Shao, Y., Li, M., & Wang, L. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70225 · Cited by 1
“Behavior recognition technology plays an important role [9].”
Navigating the GenAI Revolution: A Call to Advance Academic Excellence in Kinesiology and Beyond
Oliveira, M. A. (2025) · Kinesiology Review · doi:10.1123/kr.2025-0040 · Cited by 1
Pose attention and object semantic representation-based human-object interaction detection network
Deng, W.-M., Zhang, H., Lei, Q., Du, J., & Huang, M. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13146-x · Cited by 1
“Compared with common action recognition [39], for a video surveillance scene, action recognition can recognize only a walking person, while HOI detection [4, 12] can identify a walking person holding a knife to give an early warning.”
BackgroundSelf-citationSuggestion new monitoring system by depending on the human activity recognition videos
Al-siraj, M. N. I., Çevik, M., & Ibrahim, S. M. (2022) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit56059.2022.9932751 · Cited by 1
“• Using MaxPooling3D layers to reduce the size of the frames and do away with pointless calculations, dropout layers to prevent the model from being overfit to the data[11].”
XAI in human motion recognition and analysis for envisioning society: A systematic review
Chaudhari, P., & Kale, G. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95315-3.00007-3 · Cited by 3
Research on Event Target Recognition Based on DRUNet and Multi-scale Attention
Liu, Z., & Tan, B. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11551-x · Cited by 1
“Target recognition techniques based on traditional cameras have been applied in enter-tainment, video surveillance [1] , etc , however, the disadvantages of high latency, motion blur and low dynamic range of traditional cameras make the task processing difficult at night, or in high-speed motion.”
Zhu, W., Shi, D., Hu, T., & Wu, B. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650370 · Cited by 2
“Action recognition is a research focused issue at the intersection of multiple fields such as computer vision, video processing, and pattern recognition [1].”
BackgroundPOET: Prompt Offset Tuning for Continual Human Action Adaptation
Garg, P., Joseph, K. J., Balasubramanian, V. N., Camgöz, N. C., Wan, C., Kin, K., Si, W., Ma, S., & la Torre, F. D. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73039-9_25 · Cited by 4
“While there have been a wide variety of efforts in skeleton-based human action recognition over the years [36, 52, 53], there have been fewer efforts on adapting such models to newer user categories.”
BackgroundDeep Learning-Based Temporal Fusion Networks for Dynamic Anomaly Detection in Surveillance Video
Biswas, D., Maddula, S., Pandey, A., Dinesh, N., Chopra, J., & Upreti, S. (2025) · Smart innovation, systems and technologies · doi:10.1007/978-981-96-2182-8_45 · Cited by 1
Toward Wearable Sensor-Based Human Activity Recognition: A Survey
Zou, H., Chen, Z., Pan, Y., & Li, J. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3702134 · Cited by 3
“Driven by widespread cameras and CV progress, VHAR has been a decade-long research hotspot, enabling easy data acquisition and complex activity recognition [6], [7].”
Modeling Human Motion: A Task at the Crossroads of Neuroscience, Computer Vision and Robotics
Noceti, N., Sciutti, A., & Rea, F. (2020) · Springer eBooks · doi:10.1007/978-3-030-46732-6_1 · Cited by 1
Child Activity Recognition using Deep Learning
Suthar, B., & Gadhia, B. U. (2020) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.e9563.069520 · Cited by 2
Action Recognition of Excavator with Data Augmentation of Simulator-Generated Training Data
Kasahara, J. Y. L., Sim, J., Komatsu, R., Chikushi, S., Nagatani, K., Chiba, T., Yamamoto, S., Chayama, K., Yamashita, A., & Asama, H. (2022) · Journal of the Japan Society for Precision Engineering · doi:10.2493/jjspe.88.162 · Cited by 1
Abnormality Detection in Human Action Using Thermal Videos
Soundararajan, K., Soundararajan, A., & SaiRamesh, L. (2022) · Advances in parallel computing · doi:10.3233/apc220063 · Cited by 1
Mehak, S., Leva, M. C., Kelleher, J. D., & Guilfoyle, M. (2023) · International Conference on Machine Learning Technologies (ICMLT) · doi:10.1145/3589883.3589916 · Cited by 1
Human Activity Recognition Using Deep Learning : A Survey
Nanche, B. M., Dand, H., & Tingare, B. A. (2023) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2390379 · Cited by 1
Motion Recognition System in VR Training System for Train Attendants
Yun, C., Su, H., & Han, E. (2023) · International Conference on Virtual Reality · doi:10.1109/icvr57957.2023.10169529 · Cited by 1
“Human motion recognition is one of the important topics in the field of video understanding, which has a wide range of applications in video surveillance, human-computer interaction, motion analysis, video information retrieval and other aspects [1], and the action recognition method can be divided into action recogni…”
BackgroundVideo Classification-Based Action Recognition with Enhanced Convolutional Neural Networks
Mei, B. (2023) · International Conference on Advances in Computing and Information Technologies (ACITY) · doi:10.5121/csit.2023.131506 · Cited by 1
“To perform action recognition, algorithms typically process video footage frame by frame, using techniques like feature extraction and machine learning to identify and classify various actions.[12] [13] [14] However, accurately identifying and classifying complex actions, such as multiple individuals interacting or ob…”
Method
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.
