The DOI matches its Crossref record; 119 of the 119 references it cites were found in a registry or an index.
A Comprehensive Survey of Vision-Based Human Action Recognition Methods
Open accessAbstract
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.”
The recognition of human movement using temporal templates
Bobick, A. F., & Davis, J. W. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.910878 · Cited by 2,811 · cited 1×
“[54], who proposed the motion energy image (MEI) and motion history image (MHI) for representing action; Zhang et al.”
BackgroundConvolutional Two-Stream Network Fusion for Video Action Recognition
Feichtenhofer, C., Pinz, A., & Zisserman, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.213 · Cited by 2,684 · cited 1×
“[84] changed the process of spatial and temporal information fusion from the original final classification layer to the middle of the network, further improving the action recognition accuracy.”
BackgroundLaptev, I. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-1838-7 · Cited by 2,629
ActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578 · cited 1×
“The ActivityNet dataset [126] is a large-scale video benchmark for human activity understanding, which contains 200 action classes and 100 untrimmed videos per class, yielding a total of 648 hours.”
Beyond short snippets: Deep networks for video classification
Ng, J. Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., & Toderici, G. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299101 · Cited by 2,062 · cited 4×
“[91] proposed a recurrent neural network to recognize human action that connects the LSTM cell with the output of the underlying CNN.”
BackgroundMethodInfluentialHuman activity analysis: A review
Aggarwal, J. K., & Ryoo, M. S. (2011) · ACM Computing Surveys · doi:10.1145/1922649.1922653 · Cited by 2,056 · cited 2×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundReal-time human pose recognition in parts from single depth images
Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., & Moore, R. (2013) · Communications of the ACM · doi:10.1145/2398356.2398381 · Cited by 2,044 · cited 1×
“[77] proposed a real-time pose estimation method from depth images, which allows rapid human segmentation according to depth.”
MethodDeep learning for sensor-based activity recognition: A survey
Wang, J., Chen, Y., Hao, S., Peng, X., & Hu, L. (2019) · Pattern Recognition Letters · doi:10.1016/j.patrec.2018.02.010 · Cited by 2,014 · cited 1×
“[35] summarized existing literature in the context of three aspects: sensor modality, deep models, and application.”
BackgroundRMPE: Regional Multi-person Pose Estimation
Fang, H.-S., Xie, S., Tai, Y.-W., & Lu, C. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.256 · Cited by 1,884
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
Qiu, Z., Yao, T., & Mei, T. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.590 · Cited by 1,874 · cited 4×
“The image and optical flow sequence are respectively used as the input to the two convolutional neural networks (CNNs) during the model training process.”
MethodInfluentialA Spatio-Temporal Descriptor Based on 3D-Gradients
Klaeser, A., Marszalek, M., & Schmid, C. (2008) · Procedings of the British Machine Vision Conference 2008 · doi:10.5244/c.22.99 · Cited by 1,846 · cited 1×
“[56], who extended the histogram of gradients (HOG) feature of an image to the space-time dimension and proposed the 3DHOG feature to describe human actions in video; and Somasundaram et al.”
BackgroundLong-Term Recurrent Convolutional Networks for Visual Recognition and Description
Donahue, J., Hendricks, L. A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2599174 · Cited by 1,547
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group
Vemulapalli, R., Arrate, F., & Chellappa, R. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.82 · Cited by 1,517
Mining actionlet ensemble for action recognition with depth cameras
Wang, J., Liu, Z., Wu, Y., & Yuan, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6247813 · Cited by 1,512
View invariant human action recognition using histograms of 3D joints
Xia, L., Chen, C.-C., & Aggarwal, J. K. (2012) · 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops · doi:10.1109/cvprw.2012.6239233 · Cited by 1,452 · cited 1×
“[72] used a 3D joint point histogram to represent the human pose, and modeled the action through a discrete hidden Markov model.”
MethodAction recognition based on a bag of 3D points
Li, W., Zhang, Z., & Liu, Z. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops · doi:10.1109/cvprw.2010.5543273 · Cited by 1,428 · cited 1×
“Hollywood2 [97] √ × × 1707 12 HMDB51 [98] √ × × 6766 51 Olympic Sports [99] √ × × 783 16 UCF50 [100] √ × × 6618 50 UCF101 [101] √ × × 13,320 101 Kinetics [102] √ × × 306,245 400 MSR-Action3D [103] × √ √ 567 20 MSR-Daily Activity [104] √ √ √ 320 16 Northwestern-UCLA [105] √ √ √ 1475 10 UTD-MHAD [106] √ √ √ 861 27 RGBD-…”
DensePose: Dense Human Pose Estimation in the Wild.
Güler, R. A., Neverova, N., & Kokkinos, I. (2018) · UCL Discovery (University College London) · Cited by 1,421
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition
Liu, J., Shahroudy, A., Xu, D., & Wang, G. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_50 · Cited by 1,351
Action recognition with trajectory-pooled deep-convolutional descriptors
Wang, L., Qiao, Y., & Tang, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299059 · Cited by 1,194 · cited 2×
“Many deep learning-based action representation methods have been proposed in the field of human action recognition [19,20,42,45,46,82].”
BackgroundTemporal Relational Reasoning in Videos
Zhou, B., Andonian, A., Oliva, A., & Torralba, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01246-5_49 · Cited by 1,067
Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs
Shou, Z., Wang, D., & Chang, S.-F. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.119 · Cited by 968 · cited 1×
“[123] used three 3D convolutional networks to detect action.”
MethodHON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences
Oreifej, O., & Liu, Z. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.98 · Cited by 956 · cited 1×
“[16] extended the HOG feature to the spatiotemporal depth structure, and proposed an orientation histogram feature of the four-dimensional normal vector to represent the appearance information of a three-dimensional spatiotemporal depth structure.”
BackgroundTemporal Action Detection with Structured Segment Networks
Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., & Lin, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.317 · Cited by 892
Chen, C., Jafari, R., & Kehtarnavaz, N. (2015) · 2015 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2015.7350781 · Cited by 765 · cited 1×
“Hollywood2 [97] √ × × 1707 12 HMDB51 [98] √ × × 6766 51 Olympic Sports [99] √ × × 783 16 UCF50 [100] √ × × 6618 50 UCF101 [101] √ × × 13,320 101 Kinetics [102] √ × × 306,245 400 MSR-Action3D [103] × √ √ 567 20 MSR-Daily Activity [104] √ √ √ 320 16 Northwestern-UCLA [105] √ √ √ 1475 10 UTD-MHAD [106] √ √ √ 861 27 RGBD-…”
Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification
Niebles, J. C., Chen, C.-W., & Fei-Fei, L. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15552-9_29 · Cited by 700 · cited 1×
“Hollywood2 [97] √ × × 1707 12 HMDB51 [98] √ × × 6766 51 Olympic Sports [99] √ × × 783 16 UCF50 [100] √ × × 6618 50 UCF101 [101] √ × × 13,320 101 Kinetics [102] √ × × 306,245 400 MSR-Action3D [103] × √ √ 567 20 MSR-Daily Activity [104] √ √ √ 320 16 Northwestern-UCLA [105] √ √ √ 1475 10 UTD-MHAD [106] √ √ √ 861 27 RGBD-…”
Learning human activities and object affordances from RGB-D videos
Koppula, H. S., Gupta, R., & Saxena, A. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913478446 · Cited by 683 · cited 2×
“[116] used a Markov random field to model the interaction, where the graph nodes represent the object and the human motion and the edges represent the relationship.”
BackgroundMethodBag of visual words and fusion methods for action recognition: Comprehensive study and good practice
Peng, X., Wang, L., Wang, X., & Qiao, Y. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.03.013 · Cited by 677
Cross-View Action Modeling, Learning, and Recognition
Wang, J., Nie, X., Xia, Y., Wu, Y., & Zhu, S.-C. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.339 · Cited by 659 · cited 1×
“Hollywood2 [97] √ × × 1707 12 HMDB51 [98] √ × × 6766 51 Olympic Sports [99] √ × × 783 16 UCF50 [100] √ × × 6618 50 UCF101 [101] √ × × 13,320 101 Kinetics [102] √ × × 306,245 400 MSR-Action3D [103] × √ √ 567 20 MSR-Daily Activity [104] √ √ √ 320 16 Northwestern-UCLA [105] √ √ √ 1475 10 UTD-MHAD [106] √ √ √ 861 27 RGBD-…”
Recognizing 50 human action categories of web videos
Reddy, K. K., & Shah, M. (2013) · Machine Vision and Applications · doi:10.1007/s00138-012-0450-4 · Cited by 655 · cited 1×
“Hollywood2 [97] √ × × 1707 12 HMDB51 [98] √ × × 6766 51 Olympic Sports [99] √ × × 783 16 UCF50 [100] √ × × 6618 50 UCF101 [101] √ × × 13,320 101 Kinetics [102] √ × × 306,245 400 MSR-Action3D [103] × √ √ 567 20 MSR-Daily Activity [104] √ √ √ 320 16 Northwestern-UCLA [105] √ √ √ 1475 10 UTD-MHAD [106] √ √ √ 861 27 RGBD-…”
Going deeper into action recognition: A survey
Herath, S., Harandi, M., & Porikli, F. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.01.010 · Cited by 634
Detecting and Recognizing Human-Object Interactions
Gkioxari, G., Girshick, R., Dollar, P., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00872 · Cited by 602
Efficient Human Pose Estimation from Single Depth Images
Shotton, J., Girshick, R., Fitzgibbon, A., Sharp, T., Cook, M., Finocchio, M., Moore, R., Kohli, P., Criminisi, A., Kipman, A., et al. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.241 · Cited by 576
Modeling video evolution for action recognition
Fernando, B., Gavves, E., Jose Oramas, M., Ghodrati, A., & Tuytelaars, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299176 · Cited by 569
Recognizing actions using depth motion maps-based histograms of oriented gradients
Yang, X., Zhang, C., & Tian, Y. (2012) · Proceedings of the 20th ACM international conference on Multimedia · doi:10.1145/2393347.2396382 · Cited by 564 · cited 1×
“[68] proposed a depth motion map (DMM) to project and compress the spatiotemporal depth structure from the front, side, and upper views to form three motion history maps.”
BackgroundA Hierarchical Deep Temporal Model for Group Activity Recognition
Ibrahim, M. S., Muralidharan, S., Deng, Z., Vahdat, A., & Mori, G. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.217 · Cited by 523
Learning to Detect Human-Object Interactions
Chao, Y.-W., Liu, Y., Liu, X., Zeng, H., & Deng, J. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00048 · Cited by 520
A survey on activity recognition and behavior understanding in video surveillance
Vishwakarma, S., & Agrawal, A. (2013) · The Visual Computer · doi:10.1007/s00371-012-0752-6 · Cited by 418 · cited 1×
“[34] provided a comprehensive survey of human action recognition methods developed from 2008 to 2012.”
Background3D skeleton-based human action classification: A survey
Lo Presti, L., & La Cascia, M. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2015.11.019 · Cited by 397 · cited 3×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
Super Normal Vector for Activity Recognition Using Depth Sequences
Yang, X., & Tian, Y. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.108 · Cited by 388 · cited 6×
“In an RGBD video, the depth data can be seen as a space-time structure composed of depth information.”
BackgroundMethodInfluentialRobust human activity recognition from depth video using spatiotemporal multi-fused features
Jalal, A., Kim, Y.-H., Kim, Y.-J., Kamal, S., & Kim, D. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2016.08.003 · Cited by 384 · cited 1×
“[80] merged spatiotemporal features in RGB data and depth data, and Ni et al.”
BackgroundHMDB51: A Large Video Database for Human Motion Recognition
Kuehne, H., Jhuang, H., Stiefelhagen, R., & Serre, T. (2013) · High Performance Computing in Science and Engineering ‘12 · doi:10.1007/978-3-642-33374-3_41 · Cited by 377
Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition
Liu, A.-A., Su, Y.-T., Nie, W.-Z., & Kankanhalli, M. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2537337 · Cited by 375
Multi-region Two-Stream R-CNN for Action Detection
Peng, X., & Schmid, C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_45 · Cited by 354 · cited 1×
“[29] proposed multiregion two-stream R-CNN networks to locate action in the time dimension, while Shou et al.”
BackgroundEffective 3D action recognition using EigenJoints
Yang, X., & Tian, Y. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.03.001 · Cited by 340 · cited 2×
“on depth information [14–16], and action features based on human pose changes [17,18].”
BackgroundMethodAction Recognition with Stacked Fisher Vectors
Peng, X., Zou, C., Qiao, Y., & Peng, Q. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_38 · Cited by 338 · cited 1×
“[64] used stacked Fisher vectors to represent human actions based on iDT features, resulting in one of the more successful methods for improving iDT.”
MethodA Robust and Efficient Video Representation for Action Recognition
Wang, H., Oneata, D., Verbeek, J., & Schmid, C. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0846-5 · Cited by 317 · cited 1×
“[63] fused the results of human detection into iDT features, thereby reducing the interference of background trajectories.”
BackgroundReal-time human action recognition based on depth motion maps
Chen, C., Liu, K., & Kehtarnavaz, N. (2016) · Journal of Real-Time Image Processing · doi:10.1007/s11554-013-0370-1 · Cited by 314 · cited 7×
“In an RGBD video, the depth data can be seen as a space-time structure composed of depth information.”
BackgroundMethodInfluentialRGBD-HuDaAct: A color-depth video database for human daily activity recognition
Ni, B., Wang, G., & Moulin, P. (2011) · 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops) · doi:10.1109/iccvw.2011.6130379 · Cited by 304
Learning discriminative representations from RGB-D video data
Liu, L., & Shao, L. (2013) · UEA Digital Repository (University of East Anglia) · Cited by 302
HICO: A Benchmark for Recognizing Human-Object Interactions in Images
Chao, Y.-W., Wang, Z., He, Y., Wang, J., & Deng, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.122 · Cited by 290 · cited 1×
“[27] released the HOIC dataset in 2015, including more than 600 interactions across 47,774 images.”
BackgroundRGB-D-based action recognition datasets: A survey
Zhang, J., Li, W., Ogunbona, P. O., Wang, P., & Tang, C. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.05.019 · Cited by 283
Learning to Track for Spatio-Temporal Action Localization
Weinzaepfel, P., Harchaoui, Z., & Schmid, C. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.362 · Cited by 278 · cited 1×
“[125] calculated the relevance scores between each frame and action based on CNN features of appearance and motion, and tracked the spatiotemporal motion histograms to locate human action.”
BackgroundBeyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognition
Lan, Z., Lin, M., Li, X., Hauptmann, A. G., & Raj, B. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298616 · Cited by 264
Spatio-Temporal Attention-Based LSTM Networks for 3D Action Recognition and Detection
Song, S., Lan, C., Xing, J., Zeng, W., & Liu, J. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2818328 · Cited by 257 · cited 1×
“[93] constructed the action recognition model on top of the RNN with LSTM, which used different levels of attention to learn the discriminative joints of the skeleton within each input frame.”
MethodA survey on still image based human action recognition
Guo, G., & Lai, A. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.04.018 · Cited by 256 · cited 2×
“Because objects and poses provide rich action features for interaction recognition, many methods are based on image data [25].”
BackgroundMethodReview of constraints on vision‐based gesture recognition for human–computer interaction
Chakraborty, B. K., Sarma, D., Bhuyan, M. K., & MacDorman, K. F. (2018) · IET Computer Vision · doi:10.1049/iet-cvi.2017.0052 · Cited by 243 · cited 1×
“According to the complexity of the human action, previous techniques can be categorized into the following four classes of action semantics [1] from low to high: primitive action recognition [52], single-person action recognition [6,9], interaction recognition [26], and group action recognition [53].”
BackgroundSemantic human activity recognition: A literature review
Ziaeefard, M., & Bergevin, R. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.03.006 · Cited by 221 · cited 1×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundSpatio-Temporal Laplacian Pyramid Coding for Action Recognition
Shao, L., Zhen, X., Tao, D., & Li, X. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2273174 · Cited by 219
Temporal Localization of Actions with Actoms
Gaidon, A., Harchaoui, Z., & Schmid, C. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.65 · Cited by 217 · cited 1×
“Building on the strong performance of dense trajectories (DT) in action classification, researchers have used DT features to locate actions in the time dimension [51,111,122].”
BackgroundYao, B., & Fei-Fei, L. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.67 · Cited by 217
A Survey on Human Motion Analysis from Depth Data
Ye, M., Zhang, Q., Wang, L., Zhu, J., Yang, R., & Gall, J. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-44964-2_8 · Cited by 213 · cited 1×
“[15], who summarized human action recognition methods using depth data and Presti et al.”
MethodAction Recognition from Depth Sequences Using Depth Motion Maps-Based Local Binary Patterns
Chen, C., Jafari, R., & Kehtarnavaz, N. (2015) · 2015 IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.150 · Cited by 202 · cited 1×
“[66] used local binary pattern features to describe human action based on DMMs.”
MethodFast action proposals for human action detection and search
Yu, G., & Yuan, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298735 · Cited by 192 · cited 1×
“[124] calculated the similarity scores of each region and action using appearance and motion features.”
MethodReal-Time Action Recognition With Deeply Transferred Motion Vector CNNs
Zhang, B., Wang, L., Wang, Z., Qiao, Y., & Wang, H. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2791180 · Cited by 178 · cited 2×
“Many deep learning-based action representation methods have been proposed in the field of human action recognition [19,20,42,45,46,82].”
BackgroundDas Dawn, D., & Shaikh, S. H. (2016) · The Visual Computer · doi:10.1007/s00371-015-1066-2 · Cited by 177 · cited 3×
“Many action features have been proposed for RGB data, such as spatiotemporal volume-based features [10,43], spatiotemporal interesting point features [9,44], and joint trajectory features [12,13].”
BackgroundGowayyed, M. A., Torki, M., Hussein, M. E., & El-Saban, M. (2013) · Cited by 172
Motion Context: A New Representation for Human Action Recognition
Zhang, Z., Hu, Y., Chan, S., & Chia, L.-T. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88693-8_60 · Cited by 148 · cited 1×
“[55], who used polar coordinates to divide the central region of the human body in MHI and a Motion Context descriptor based on SIFT to represent the action; Klaser et al.”
MethodReal-Time Skeleton-Tracking-Based Human Action Recognition Using Kinect Data
Papadopoulos, G. T., Αξενόπουλος, Α., & Daras, P. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-04114-8_40 · Cited by 148 · cited 3×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundAPT: Action localization proposals from dense trajectories
van Gemert, J. C., Jain, M., Gati, E., & Snoek, C. G. M. (2015) · British Machine Vision Conference (BMVC) · doi:10.5244/c.29.177 · Cited by 142 · cited 2×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundMethodSelective spatio-temporal interest points
Chakraborty, B., Holte, M. B., Moeslund, T. B., & Gonzàlez, J. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.09.010 · Cited by 140 · cited 1×
“Popular STIP methods include 3D-Harris spatiotemporal feature points [58] and similar or improved techniques [59].”
MethodHuman activity recognition using multi-features and multiple kernel learning
Althloothi, S. R., Mahoor, M. H., Zhang, X., & Voyles, R. M. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.11.032 · Cited by 134 · cited 1×
“[78] calculated a spherical harmonics representation of depth information in the frequency domain, and fused this with position information of the skeleton joints through a multikernel learning method to model human actions.”
MethodLearning Models for Actions and Person-Object Interactions with Transfer to Question Answering
Mallya, A., & Lazebnik, S. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46448-0_25 · Cited by 132 · cited 1×
“[120] calculated human and object features from pretrained CNNs, and merged them with pretrained human and object relationship models learned from the HIOC dataset to detect interactions.”
MethodActivity representation with motion hierarchies
Gaidon, A., Harchaoui, Z., & Schmid, C. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0677-1 · Cited by 126 · cited 1×
“[62] used split clustering to analyze local motion trajectories, and used the clustering results to represent different motion levels in calculating human action features.”
MethodMoFAP: A Multi-level Representation for Action Recognition
Wang, L., Qiao, Y., & Tang, X. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0859-0 · Cited by 126
Explicit Modeling of Human-Object Interactions in Realistic Videos
Prest, A., Ferrari, V., & Schmid, C. (2012) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.175 · Cited by 123
Multilevel Depth and Image Fusion for Human Activity Detection
Ni, B., Pei, Y., Moulin, P., & Yan, S. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2013.2276433 · Cited by 122 · cited 1×
“[81] proposed a multilevel fusion of RGB and depth data features.”
BackgroundReal time action recognition using histograms of depth gradients and random decision forests
Rahmani, H., Mahmood, A., Huynh, D. Q., & Mian, A. S. (2014) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2014.6836044 · Cited by 122 · cited 2×
“Research results [5,24,67] show that the methods based on depth information achieve real-time action recognition and better recognition performance than RGB-based methods.”
BackgroundMethodDeep Local Video Feature for Action Recognition
Lan, Z., Zhu, Y., Hauptmann, A. G., & Newsam, S. D. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.161 · Cited by 121 · cited 2×
“In addition, Lan [86] and Zhou [87] also enhanced the recognition results of TSN. Similarly, based on the idea of 3D (Three Dimension) convolutional networks, many researchers have attempted to extend different 2D convolutional networks to 3D spatiotemporal structures for the learning and recognition of human action f…”
BackgroundBenchmarking a Multimodal and Multiview and Interactive Dataset for Human Action Recognition
Liu, A.-A., Xu, N., Nie, W., Su, Y., Wong, Y., & Kankanhalli, M. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2582918 · Cited by 111
Marszałek, M., Ivan Laptev, A., & Schmid, C. (2009) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvprw.2009.5206557 · Cited by 109
Motion analysis: Action detection, recognition and evaluation based on motion capture data
Patrona, F., Chatzitofis, A., Zarpalas, D., & Daras, P. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.12.007 · Cited by 107 · cited 1×
“At the same time, depth sensors have a natural advantage in human location and skeleton extraction, so action detection based on depth sensors is simpler and more effective than that using RGB data [31].”
BackgroundEnd-to-end Video-level Representation Learning for Action Recognition
Zhu, J., Zhu, Z. D., & Zou, W. (2018) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2018.8545710 · Cited by 102
Fusion of Skeletal and Silhouette-Based Features for Human Action Recognition with RGB-D Devices
Chaaraoui, A. A., Padilla-López, J. R., & Flórez‐Revuelta, F. (2013) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2013.19 · Cited by 97 · cited 2×
“As a result, most human action recognition methods can be divided into depth sequence-based methods [14,16,24,65–68], skeletonbased methods [5,18,69–73], and feature fusion methods [17,41,74,75].”
BackgroundA survey on human activity recognition from videos
Subetha, T., & Chitrakala, S. (2016) · International Conference on Information Communication and Embedded Systems · doi:10.1109/icices.2016.7518920 · Cited by 95
STAP: Spatial-Temporal Attention-Aware Pooling for Action Recognition
Nguyen, T., Zheng, S., & Yan, S. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2333151 · Cited by 83 · cited 2×
“Many action features have been proposed for RGB data, such as spatiotemporal volume-based features [10,43], spatiotemporal interesting point features [9,44], and joint trajectory features [12,13].”
BackgroundMethodEfficient Action Localization with Approximately Normalized Fisher Vectors
Oneaţă, D., Verbeek, J. J., & Schmid, C. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.326 · Cited by 72 · cited 1×
“Building on the strong performance of dense trajectories (DT) in action classification, researchers have used DT features to locate actions in the time dimension [51,111,122].”
BackgroundTORNADO: A Spatio-Temporal Convolutional Regression Network for Video Action Proposal
Zhu, H., Vial, R., & Lu, S. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.619 · Cited by 68 · cited 2×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundA comparative study of data fusion for RGB-D based visual recognition
Sànchez-Riera, J., Hua, K., Hsiao, Y.-S., Lim, T., Hidayati, S. C., & Cheng, W.-H. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.12.006 · Cited by 65 · cited 1×
“In addition to the fusion of depth information and skeletal features, some researchers have attempted to fuse features in RGB data with features in depth data [79].”
Learning Spatial and Temporal Extents of Human Actions for Action Detection
Zhou, Z., Shi, F., & Wu, W. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2404779 · Cited by 65
Joint movement similarities for robust 3D action recognition using skeletal data
Pazhoumand-Dar, H., Lam, C., & Mašek, M. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.03.002 · Cited by 63 · cited 1×
“[69] used the longest common subsequence algorithm to select high-discriminative power features from the relative motion trajectories of the skeleton to describe the associated action.”
Multi-Modality Multi-Task Recurrent Neural Network for Online Action Detection
Liu, J., Li, Y., Song, S., Xing, J., Lan, C., & Zeng, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2799968 · Cited by 62 · cited 1×
“[30] proposed a multimodality multitask recurrent neural network to model action in RGB and skeleton data, and integrated action classification and localization into a unified network to recognize action.”
BackgroundEvaluating a bag-of-visual features approach using spatio-temporal features for action recognition
Nazir, S., Yousaf, M. H., & Velastín, S. A. (2018) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2018.01.037 · Cited by 60 · cited 1×
“[61] integrated the 3D-Harris spatiotemporal features and 3D scale-invariance feature transform detection methods to extract the key regions of a video, and used traditional visual word histograms to represent human actions.”
MethodAction recognition using global spatio-temporal features derived from sparse representations
Somasundaram, G., Cherian, A., Morellas, V., & Papanikolopoulos, N. P. (2014) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2014.01.002 · Cited by 56
TUHOI: Trento Universal Human Object Interaction Dataset
Le, D.-T., Uijlings, J., & Raffaella Bernardi, B. (2014) · Workshop on Vision and Language (VL) · doi:10.3115/v1/w14-5403 · Cited by 35 · cited 1×
“[28] provided the first large interaction recognition dataset named TUHIO.”
TriViews: A general framework to use 3D depth data effectively for action recognition
Chen, W., & Guo, G. (2014) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2014.11.008 · Cited by 31 · cited 1×
“[76] also analyzed the spatiotemporal depth structure in the front, side, and upper directions.”
BackgroundHuman action recognition via skeletal and depth based feature fusion
Li, M., Leung, H. W. H., & Shum, H. P. H. (2016) · Motion in Games · doi:10.1145/2994258.2994268 · Cited by 30 · cited 9×
“In an RGBD video, the depth data can be seen as a space-time structure composed of depth information.”
BackgroundMethodInfluentialDistances evolution analysis for online and off-line human object interaction recognition
Meng, M., Drira, H., & Boonært, J. (2017) · Image and Vision Computing · doi:10.1016/j.imavis.2017.12.003 · Cited by 28 · cited 3×
“[26] constructed a new video-based human object interaction recognition dataset in 2018, called Lille Douai.”
BackgroundBurghouts, G. J., Klamer Schutte, B., ten Hove, R. J. M., van den Broek, S. P., Baan, J., Rajadell, O., van Huis, J. R., van Rest, J., Hanckmann, P., Bouma, H., et al. (2014) · Signal Image and Video Processing · doi:10.1007/s11760-014-0672-1 · Cited by 25 · cited 2×
“Many action features have been proposed for RGB data, such as spatiotemporal volume-based features [10,43], spatiotemporal interesting point features [9,44], and joint trajectory features [12,13].”
BackgroundEmbedding Sequential Information into Spatiotemporal Features for Action Recognition
Ye, Y., & Tian, Y. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.142 · Cited by 24 · cited 1×
“[95] used 3D convolutional networks to embed time series information into dense motion trajectories to model action.”
MethodSurvey on Video Analysis of Human Walking Motion
Paul, S., & Singh, Y. J. (2014) · International Journal of Signal Processing Image Processing and Pattern Recognition · doi:10.14257/ijsip.2014.7.3.10 · Cited by 21 · cited 1×
“Human action recognition has a wide range of applications, such as intelligent video surveillance and environmental home monitoring [1,2], video storage and retrieval [3,4], intelligent human–machine interfaces [5,6], and identity recognition [7].”
BackgroundRECOGNITION OF BASIC HUMAN ACTIONS USING DEPTH INFORMATION
Keçeli, A. S., & Can, A. B. (2014) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001414500049 · Cited by 18 · cited 1×
“[73] used the Kinect sensor to obtain depth and human skeleton information, and then extracted human action features based on the angle and displacement information of the skeleton joint points.”
MethodMulti-dimensional human action recognition model based on image set and group sparisty
Gao, Z., Zhang, Y., Zhang, H., Xue, Y., & Xu, G. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.01.113 · Cited by 17
Self-citationAction Detection with Improved Dense Trajectories and Sliding Window
Shu, Z., Yun, K., & Samaras, D. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16178-5_38 · Cited by 15 · cited 1×
“In early research, action detection mainly used object tracking and sliding windows to locate the action position [50].”
Mu, J., Liang, Q., Wang, W., Zhang, B., & Pi, Y. (2015) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-08991-1 · Cited by 14
Human Action Recognition using Salient Region Detection in Complex Scenes
Zhang, Z., Liu, S., Liu, S., Han, L., 邵允学, & Zhou, W. (2015) · Lecture notes in electrical engineering · doi:10.1007/978-3-319-08991-1_58 · Cited by 13 · cited 1×
“Many action features have been proposed for RGB data, such as spatiotemporal volume-based features [10,43], spatiotemporal interesting point features [9,44], and joint trajectory features [12,13].”
BackgroundMeng, M., Drira, H., Daoudi, M., & Boonært, J. (2016) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.128 · Cited by 13 · cited 2×
“[115] expressed the interaction based on the joint points detected in the depth information, the relative position changes between these joint points,”
BackgroundEfficient action recognition from compressed depth maps
Miao, J., Jia, X., Mathew, R. K., Xu, X., Taubman, D., & Qing, C. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532310 · Cited by 8 · cited 1×
“[65] used the discrete cosine variation to compress the depth map and construct action features using transform coefficients.”
MethodMulti-surface analysis for human action recognition in video
Zhang, H., Lei, Q., Zhong, B., Du, J., Peng, J., Hsiao, T., & Chen, D. (2016) · SpringerPlus · doi:10.1186/s40064-016-2876-z · Cited by 7 · cited 1×
“Many action features have been proposed for RGB data, such as spatiotemporal volume-based features [10,43], spatiotemporal interesting point features [9,44], and joint trajectory features [12,13].”
Self-citationLocating and recognizing multiple human actions by searching for maximum score subsequences
Zhang, H., Li, S., Chen, S., Su, S., Lin, X., & Cao, D. (2013) · Signal Image and Video Processing · doi:10.1007/s11760-013-0501-y · Cited by 2
Self-citation
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
Vision-based human activity recognition: a survey
Beddiar, D. R., Nini, B., Sabokrou, M., & Hadid, A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09004-3 · Cited by 505
Synthetic Data for Deep Learning
Nikolenko, S. I. (2021) · Springer Optimization and Its Applications · doi:10.1007/978-3-030-75178-4 · Cited by 423
“Moving from still images to videos, we begin with human action recognition [460, 688].”
BackgroundSkeleton-based action recognition via spatial and temporal transformer networks
Plizzari, C., Cannici, M., & Matteucci, M. (2021) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2021.103219 · Cited by 409
“Nevertheless, several aspects of skeleton-based action recognition still remain open (Zhang et al. (2019); Aggarwal and Ryoo (2011); Ren et al. (2020)).”
BackgroundDeep Learning for Time Series Classification and Extrinsic Regression: A Current Survey
Mohammadi Foumani, N., Miller, L., Tan, C. W., Webb, G. I., Forestier, G., & Salehi, M. (2024) · ACM Computing Surveys · doi:10.1145/3649448 · Cited by 268
“For reviews of vision-based HAR, refer to Kong and Fu [190] or Zhang et al. [191].”
MethodKhan, M. A., Javed, K., Khan, S. A., Saba, T., Habib, U., Khan, J. A., & Abbasi, A. A. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08806-9 · Cited by 277
“Moreover, it is extensively used in various industrial applications [9, 44].”
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.
