16.7.4.6.9 Human Action Recognition and Detection Using Depth, RGB-D, Kinect

Chapter Contents (Back)
Action Recognition. 3-D Recognition. Depth. Kinect. RGB-D.

Darby, J.[John], Li, B.H.[Bai-Hua], Costen, N.P.[Nicholas P.],
Tracking human pose with multiple activity models,
PR(43), No. 9, September 2010, pp. 3042-3058.
Elsevier DOI 1006
BibRef
Earlier:
Behaviour based particle filtering for human articulated motion tracking,
ICPR08(1-4).
IEEE DOI 0812
BibRef
Earlier:
Tracking a walking person using activity-guided annealed particle filtering,
FG08(1-6).
IEEE DOI 0809
BibRef
And:
Human Activity Tracking from Moving Camera Stereo Data,
BMVC08(xx-yy).
PDF File. 0809
Human motion analysis; 3D human tracking; Generative model; Particle filter; Annealing BibRef

Leightley, D.[Daniel], Li, B.H.[Bai-Hua], McPhee, J.S.[Jamie S.], Yap, M.H.[Moi Hoon], Darby, J.[John],
Exemplar-Based Human Action Recognition with Template Matching from a Stream of Motion Capture,
ICIAR14(II: 12-20).
Springer DOI 1410
BibRef

Darby, J.[John], Li, B.H.[Bai-Hua], Costen, N.P.[Nicholas P.], Fleet, D.J.[David J.], Lawrence, N.D.[Neil D.],
Backing Off: Hierarchical Decomposition of Activity for 3d Novel Pose Recovery,
BMVC09(xx-yy).
PDF File. 0909
BibRef

Yan, S.C.[Shui-Cheng], Zhang, Z.Q.[Zhen-Qiu], Fu, Y.[Yun], Hu, Y.X.[Yu-Xiao], Tu, J.L.[Ji-Lin], Huang, T.S.[Thomas S.],
Learning a Person-Independent Representation for Precise 3D Pose Estimation,
MTPH07(xx-yy).
Springer DOI 0705
BibRef

Ni, B.B.[Bing-Bing], Pei, Y.[Yong], Moulin, P.[Pierre], Yan, S.,
Multilevel Depth and Image Fusion for Human Activity Detection,
Cyber(43), No. 5, 2013, pp. 1383-1394.
IEEE DOI 1309
Accuracy BibRef

Ni, B.B.[Bing-Bing], Paramathayalan, V.R.[Vignesh R.], Li, T.[Teng], Moulin, P.[Pierre],
Multiple Granularity Modeling: A Coarse-to-Fine Framework for Fine-grained Action Analysis,
IJCV(120), No. 1, October 2016, pp. 28-43.
Springer DOI 1609
BibRef
Earlier: A1, A2, A4, Only:
Multiple Granularity Analysis for Fine-Grained Action Detection,
CVPR14(756-763)
IEEE DOI 1409
action detection; interaction tracking; multiple granularity BibRef

Pei, Y.[Yong], Ni, B.B.[Bing-Bing], Atmosukarto, I.[Indriyati],
Mixture of Heterogeneous Attribute Analyzers for Human Action Detection,
ChaLearn14(528-540).
Springer DOI 1504
BibRef

Zhou, Y.[Yang], Ni, B.B.[Bing-Bing], Yan, S.C.[Shui-Cheng], Moulin, P.[Pierre], Tian, Q.[Qi],
Pipelining Localized Semantic Features for Fine-Grained Action Recognition,
ECCV14(IV: 481-496).
Springer DOI 1408
BibRef

Ni, B.B.[Bing-Bing], Pei, Y.[Yong], Liang, Z.J.[Zhu-Jin], Lin, L.[Liang], Moulin, P.[Pierre],
Integrating multi-stage depth-induced contextual information for human action recognition and localization,
FG13(1-8)
IEEE DOI 1309
computer vision. With depth sensor. BibRef

Liu, L.[Li], Shao, L.[Ling], Zheng, F.[Feng], Li, X.L.[Xue-Long],
Realistic action recognition via sparsely-constructed Gaussian processes,
PR(47), No. 12, 2014, pp. 3819-3827.
Elsevier DOI 1410
Action recognition BibRef

Shao, L.[Ling], Liu, L.[Li], Yu, M.Y.[Meng-Yang],
Kernelized Multiview Projection for Robust Action Recognition,
IJCV(118), No. 2, June 2016, pp. 115-129.
Springer DOI 1606
See also Learning Short Binary Codes for Large-scale Image Retrieval. BibRef

Yu, M.Y.[Meng-Yang], Liu, L.[Li], Shao, L.[Ling],
Structure-Preserving Binary Representations for RGB-D Action Recognition,
PAMI(38), No. 8, August 2016, pp. 1651-1664.
IEEE DOI 1608
BibRef
Earlier: A2, A1, A3:
Local Feature Binary Coding for Approximate Nearest Neighbor Search,
BMVC15(xx-yy).
DOI Link 1601
binary codes See also Multiview Alignment Hashing for Efficient Image Search. BibRef

Vieira, A.W.[Antonio W.], Nascimento, E.R.[Erickson R.], Oliveira, G.L.[Gabriel L.], Liu, Z.C.[Zi-Cheng], Campos, M.F.M.[Mario F.M.],
On the improvement of human action recognition from depth map sequences using Space-Time Occupancy Patterns,
PRL(36), No. 1, 2014, pp. 221-227.
Elsevier DOI 1312
BibRef
Earlier:
Stop: Space-time Occupancy Patterns for 3d Action Recognition from Depth Map Sequences,
CIARP12(252-259).
Springer DOI 1209
Pattern recognition BibRef

Oliveira, G.L., Nascimento, E.R., Vieira, A.W., Campos, M.F.M.,
Sparse Spatial Coding: A Novel Approach to Visual Recognition,
IP(23), No. 6, June 2014, pp. 2719-2731.
IEEE DOI 1406
Accuracy BibRef

Vasconcelos, L.O.[Levi O.], Nascimento, E.R.[Erickson R.], Campos, M.F.M.[Mario F.M.],
KVD: Scale invariant keypoints by combining visual and depth data,
PRL(86), No. 1, 2017, pp. 83-89.
Elsevier DOI 1702
Keypoint detector BibRef

Nascimento, E.R.[Erickson R.], Schwartz, W.R.[William Robson], Campos, M.F.M.[Mario F.M.],
EDVD: Enhanced descriptor for visual and depth data,
ICPR12(2776-2779).
WWW Link. 1302
BibRef

Yuan, C.F.[Chun-Feng], Li, X.[Xi], Hu, W.M.[Wei-Ming], Ling, H.B.[Hai-Bin], Maybank, S.J.[Stephen J.],
Modeling Geometric-Temporal Context With Directional Pyramid Co-Occurrence for Action Recognition,
IP(23), No. 2, February 2014, pp. 658-672.
IEEE DOI 1402
BibRef
Earlier:
3D-R Transform on Spatio-temporal Interest Points for Action Recognition,
CVPR13(724-730)
IEEE DOI 1309
geometry BibRef

Yuan, C.F.[Chun-Feng], Hu, W.M.[Wei-Ming], Li, X.[Xi], Maybank, S.J.[Stephen J.], Luo, G.[Guan],
Human Action Recognition under Log-Euclidean Riemannian Metric,
ACCV09(I: 343-353).
Springer DOI 0909
BibRef

Cao, X.C.[Xiao-Chun], Zhang, H.[Hua], Deng, C.[Chao], Liu, Q.[Qiguang], Liu, H.[Hanyu],
Action recognition using 3D DAISY descriptor,
MVA(25), No. 1, January 2014, pp. 159-171.
Springer DOI 1402
BibRef

Deng, C.[Chao], Cao, X.C.[Xiao-Chun], Liu, H.[Hanyu], Chen, J.[Jian],
A Global Spatio-Temporal Representation for Action Recognition,
ICPR10(1816-1819).
IEEE DOI 1008
BibRef

Wang, J.[Jiang], Liu, Z.C.[Zi-Cheng], Wu, Y.[Ying],
Human Action Recognition with Depth Cameras,

Springer2014. ISBN 978-3-319-04560-3.
WWW Link. 1404
See also Action Search by Example Using Randomized Visual Vocabularies. BibRef

Wang, J.[Jiang], Liu, Z.C.[Zi-Cheng], Wu, Y.[Ying], Yuan, J.S.[Jun-Song],
Learning Actionlet Ensemble for 3D Human Action Recognition,
PAMI(36), No. 5, May 2014, pp. 914-927.
IEEE DOI 1405
BibRef
Earlier:
Mining actionlet ensemble for action recognition with depth cameras,
CVPR12(1290-1297).
IEEE DOI 1208
Feature extraction See also Abnormal Event Detection in Crowded Scenes Using Sparse Representation. BibRef

Song, Y., Tang, J.H., Liu, F., Yan, S.,
Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos,
CirSysVideo(24), No. 6, June 2014, pp. 952-964.
IEEE DOI 1407
Context BibRef

Song, Y.[Yan], Liu, S.[Shi], Tang, J.H.[Jin-Hui],
Describing Trajectory of Surface Patch for Human Action Recognition on RGB and Depth Videos,
SPLetters(22), No. 4, April 2015, pp. 426-429.
IEEE DOI 1411
feature extraction BibRef

Liu, X.R.[Xin-Ran], Song, Y.[Yan], Tang, J.H.[Jin-Hui],
Effective Action Detection Using Temporal Context and Posterior Probability of Length,
MMMod18(II:106-117).
Springer DOI 1802
Find action in untrimmed video. Consider length. BibRef

Luo, J.J.[Jia-Jia], Wang, W.[Wei], Qi, H.R.[Hai-Rong],
Spatio-temporal feature extraction and representation for RGB-D human action recognition,
PRL(50), No. 1, 2014, pp. 139-148.
Elsevier DOI 1410
Human action recognition BibRef

Chen, L.[Lulu], Wei, H.[Hong], Ferryman, J.M.[James M.],
ReadingAct RGB-D action dataset and human action recognition from local features,
PRL(50), No. 1, 2014, pp. 159-169.
Elsevier DOI 1410
Human action recognition BibRef

Peng, X.J.[Xiao-Jiang], Qiao, Y.[Yu], Peng, Q.A.[Qi-Ang], Wang, Q.,
Large Margin Dimensionality Reduction for Action Similarity Labeling,
SPLetters(21), No. 8, August 2014, pp. 1022-1025.
IEEE DOI 1406
BibRef

Peng, X.J.[Xiao-Jiang], Qiao, Y.[Yu], Peng, Q.A.[Qi-Ang],
Motion boundary based sampling and 3D co-occurrence descriptors for action recognition,
IVC(32), No. 9, 2014, pp. 616-628.
Elsevier DOI 1408
Dense trajectory BibRef

Peng, X.J.[Xiao-Jiang], Zou, C.Q.[Chang-Qing], Qiao, Y.[Yu], Peng, Q.A.[Qi-Ang],
Action Recognition with Stacked Fisher Vectors,
ECCV14(V: 581-595).
Springer DOI 1408
BibRef

Peng, X.J.[Xiao-Jiang], Qiao, Y.[Yu], Peng, Q.A.[Qi-Ang], Qi, X.B.[Xian-Biao],
Exploring Motion Boundary based Sampling and Spatial-Temporal Context Descriptors for Action Recognition,
BMVC13(xx-yy).
DOI Link 1402
BibRef

Wang, L.M.[Li-Min], Wang, Z.[Zhe], Qiao, Y.[Yu], Van Gool, L.J.[Luc J.],
Transferring Deep Object and Scene Representations for Event Recognition in Still Images,
IJCV(126), No. 2-4, April 2018, pp. 390-409.
Springer DOI 1804
BibRef

Wang, L.M.[Li-Min], Wang, Z., Guo, S., Qiao, Y.[Yu],
Better Exploiting OS-CNNs for Better Event Recognition in Images,
ChaLearnDec15(287-294)
IEEE DOI 1602
Computer vision BibRef

Wang, L.M.[Li-Min], Wang, Z.[Zhe], Du, W.B.[Wen-Bin], Qiao, Y.[Yu],
Object-Scene Convolutional Neural Networks for event recognition in images,
ChaLearn15(30-35)
IEEE DOI 1510
Computer architecture BibRef

Slama, R.[Rim], Wannous, H.[Hazem], Daoudi, M.[Mohamed], Srivastava, A.[Anuj],
Accurate 3D action recognition using learning on the Grassmann manifold,
PR(48), No. 2, 2015, pp. 556-567.
Elsevier DOI 1411
Human action recognition See also 3D human motion analysis framework for shape similarity and retrieval. BibRef

Chen, C.[Chen], Jafari, R.[Roozbeh], Kehtarnavaz, N.[Nasser],
Improving Human Action Recognition Using Fusion of Depth Camera and Inertial Sensors,
HMS(45), No. 1, February 2015, pp. 51-61.
IEEE DOI 1502
BibRef
And:
Action Recognition from Depth Sequences Using Depth Motion Maps-Based Local Binary Patterns,
WACV15(1092-1099)
IEEE DOI 1503
Feature extraction BibRef

Chen, C.[Chen], Liu, K.[Kui], Kehtarnavaz, N.[Nasser],
Real-time human action recognition based on depth motion maps,
RealTimeIP(12), No. 1, June 2016, pp. 155-163.
WWW Link. 1606
BibRef

Dawar, N., Kehtarnavaz, N.[Nasser],
Continuous detection and recognition of actions of interest among actions of non-interest using a depth camera,
ICIP17(4227-4231)
IEEE DOI 1803
Continuous action detection, continuous action recognition, continuous detection and recognition of actions of interest among actions of non-interest BibRef

Hu, M., Chen, C., Cheng, W., Chang, C., Lai, J., Wu, J.,
Real-Time Human Movement Retrieval and Assessment With Kinect Sensor,
Cyber(45), No. 4, April 2015, pp. 742-753.
IEEE DOI 1503
Cameras BibRef

Stückler, J.[Jörg], Behnke, S.[Sven],
Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video,
IJCV(113), No. 3, July 2015, pp. 233-245.
Springer DOI 1506
BibRef
Earlier:
Efficient Dense 3D Rigid-Body Motion Segmentation in RGB-D Video,
BMVC13(xx-yy).
DOI Link 1402
BibRef

Cosar, S.[Serhan], Çetin, M.[Müjdat],
Sparsity-Driven Bandwidth-Efficient Decentralized Tracking in Visual Sensor Networks,
CVIU(139), No. 1, 2015, pp. 40-58.
Elsevier DOI 1509
BibRef
Earlier:
A group sparsity-driven approach to 3-D action recognition,
VS11(1904-1911).
IEEE DOI 1201
Camera networks See also Sparsity-Driven Approach to Multi-Camera Tracking in Visual Sensor Networks, A. BibRef

Koppula, H.S.[Hema S.], Saxena, A.[Ashutosh],
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response,
PAMI(38), No. 1, January 2016, pp. 14-29.
IEEE DOI 1601
BibRef
Earlier:
Physically Grounded Spatio-temporal Object Affordances,
ECCV14(III: 831-847).
Springer DOI 1408
Context. The associated objects. BibRef

Jiang, Y.[Yun], Koppula, H.S.[Hema S.], Saxena, A.[Ashutosh],
Modeling 3D Environments through Hidden Human Context,
PAMI(38), No. 10, October 2016, pp. 2040-2053.
IEEE DOI 1609
BibRef
Earlier:
Hallucinated Humans as the Hidden Context for Labeling 3D Scenes,
CVPR13(2993-3000)
IEEE DOI 1309
Computational modeling. hallucinated humans; scene labeling in context of human use. (e.g. spatial relation of keyboard and monitor) BibRef

Zhang, H.[Hao], Parker, L.E.[Lynne E.],
CoDe4D: Color-Depth Local Spatio-Temporal Features for Human Activity Recognition From RGB-D Videos,
CirSysVideo(26), No. 3, March 2016, pp. 541-555.
IEEE DOI 1603
Cameras BibRef

Zhang, H.[Hao], Zhou, W.J.[Wen-Jun], Reardon, C.[Christopher], Parker, L.E.[Lynne E.],
Simplex-Based 3D Spatio-temporal Feature Description for Action Recognition,
CVPR14(2067-2074)
IEEE DOI 1409
Feature description BibRef

Rahmani, H.[Hossein], Huynh, D.Q.[Du Q.], Mahmood, A.[Arif], Mian, A.[Ajmal],
Discriminative human action classification using locality-constrained linear coding,
PRL(72), No. 1, 2016, pp. 62-71.
Elsevier DOI 1604
BibRef
Earlier: A1, A3, A2, A4:
Action Classification with Locality-Constrained Linear Coding,
ICPR14(3511-3516)
IEEE DOI 1412
BibRef
Earlier: A1, A3, A2, A4:
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition,
ECCV14(II: 742-757).
Springer DOI 1408
Human action classification BibRef

Rahmani, H.[Hossein], Mahmood, A.[Arif], Huynh, D.Q.[Du Q.], Mian, A.[Ajmal],
Histogram of Oriented Principal Components for Cross-View Action Recognition,
PAMI(38), No. 12, December 2016, pp. 2430-2443.
IEEE DOI 1609
Detectors BibRef

Rahmani, H.[Hossein], Mian, A.[Ajmal],
3D Action Recognition from Novel Viewpoints,
CVPR16(1506-1515)
IEEE DOI 1612
BibRef
Earlier:
Learning a non-linear knowledge transfer model for cross-view action recognition,
CVPR15(2458-2466)
IEEE DOI 1510
BibRef

Rahmani, H.[Hossein], Mahmood, A.[Arif], Huynh, D.Q.[Du Q.], Mian, A.[Ajmal],
Real time action recognition using histograms of depth gradients and random decision forests,
WACV14(626-633)
IEEE DOI 1406
Feature extraction BibRef

Brun, L.[Luc], Percannella, G.[Gennaro], Saggese, A.[Alessia], Vento, M.[Mario],
Action recognition by using kernels on aclets sequences,
CVIU(144), No. 1, 2016, pp. 3-13.
Elsevier DOI 1604
BibRef
Earlier:
HAck: A system for the recognition of human actions by kernels of visual strings,
AVSS14(142-147)
IEEE DOI 1411
Human action recognition. Computer hacking BibRef

Foggia, P.[Pasquale], Saggese, A.[Alessia], Strisciuglio, N.[Nicola], Vento, M.[Mario],
Exploiting the deep learning paradigm for recognizing human actions,
AVSS14(93-98)
IEEE DOI 1411
Computer architecture BibRef

Carletti, V.[Vincenzo], Foggia, P.[Pasquale], Percannella, G.[Gennaro], Saggese, A.[Alessia], Vento, M.[Mario],
Recognition of Human Actions from RGB-D Videos Using a Reject Option,
SBA13(436-445).
Springer DOI 1309
BibRef

Lin, L.[Liang], Wang, K.[Keze], Zuo, W.M.[Wang-Meng], Wang, M.[Meng], Luo, J.B.[Jie-Bo], Zhang, L.[Lei],
A Deep Structured Model with Radius-Margin Bound for 3D Human Activity Recognition,
IJCV(118), No. 2, June 2016, pp. 256-273.
Springer DOI 1606
BibRef

Le, C.Q.[Chien-Quang], Phan, S.[Sang], Ngo, T.D.[Thanh Duc], Le, D.D.[Duy-Dinh], Satoh, S.[Shin'ichi], Duong, D.A.[Duc Anh],
Human Action Recognition from Depth Videos Using Pool of Multiple Projections with Greedy Selection,
IEICE(E99-D), No. 8, August 2016, pp. 2161-2171.
WWW Link. 1608
BibRef

Liang, C., Chen, E., Qi, L., Guan, L.,
Improving Action Recognition Using Collaborative Representation of Local Depth Map Feature,
SPLetters(23), No. 9, September 2016, pp. 1241-1245.
IEEE DOI 1609
gesture recognition BibRef

Liang, C., Qi, L., Guan, L.,
Motion energy guided multi-scale heterogeneous features for 3D action recognition,
VCIP17(1-4)
IEEE DOI 1804
feature extraction, image classification, image motion analysis, image representation, image sequences, sub-action segmentation BibRef

El Din El Madany, N.[Nour], He, Y.F.[Yi-Feng], Guan, L.[Ling],
Information Fusion for Human Action Recognition via Biset/Multiset Globality Locality Preserving Canonical Correlation Analysis,
IP(27), No. 11, November 2018, pp. 5275-5287.
IEEE DOI 1809
BibRef
Earlier:
Human action recognition by fusing deep features with Globality Locality Preserving Canonical Correlation Analysis,
ICIP17(2871-2875)
IEEE DOI 1803
BibRef
Earlier:
Human action recognition via multiview discriminative analysis of canonical correlations,
ICIP16(4170-4174)
IEEE DOI 1610
feature extraction, image fusion, image motion analysis, image recognition, image sensors, image sequences, globality locality preserving canonical correlation analysis. Correlation, Laplace equations, Matrix decomposition, Optical imaging, Multimodal Fusion. Accelerometers BibRef

Shahroudy, A.[Amir], Ng, T.T.[Tian-Tsong], Yang, Q.X.[Qing-Xiong], Wang, G.[Gang],
Multimodal Multipart Learning for Action Recognition in Depth Videos,
PAMI(38), No. 10, October 2016, pp. 2123-2129.
IEEE DOI 1609
Feature extraction BibRef

Shahroudy, A.[Amir], Ng, T.T.[Tian-Tsong], Gong, Y., Wang, G.[Gang],
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos,
PAMI(40), No. 5, May 2018, pp. 1045-1058.
IEEE DOI 1804
Correlation, Feature extraction, Robustness, Sensors, Skeleton, Three-dimensional displays, Videos, Multimodal analysis, RGB+D, structured sparsity BibRef

Shahroudy, A.[Amir], Liu, J., Ng, T.T.[Tian-Tsong], Wang, G.,
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis,
CVPR16(1010-1019)
IEEE DOI 1612
Dataset, Human Activity. BibRef

Hsu, Y.P.[Yen-Pin], Liu, C.[Chengyin], Chen, T.Y.[Tzu-Yang], Fu, L.C.[Li-Chen],
Online view-invariant human action recognition using RGB-D spatio-temporal matrix,
PR(60), No. 1, 2016, pp. 215-226.
Elsevier DOI 1609
Action recognition BibRef

Zhang, J.[Jing], Li, W.Q.[Wan-Qing], Ogunbona, P.O.[Philip O.], Wang, P.[Pichao], Tang, C.[Chang],
RGB-D-based action recognition datasets: A survey,
PR(60), No. 1, 2016, pp. 86-105.
Elsevier DOI 1609
Dataset, Action Recognition. Action recognition BibRef

Zhou, L.J.[Li-Juan], Li, W.Q.[Wan-Qing], Ogunbona, P.O.[Philip O.], Zhang, Z.Y.[Zheng-You],
Semantic action recognition by learning a pose lexicon,
PR(72), No. 1, 2017, pp. 548-562.
Elsevier DOI 1708
Lexicon BibRef

Jia, C., Fu, Y.,
Low-Rank Tensor Subspace Learning for RGB-D Action Recognition,
IP(25), No. 10, October 2016, pp. 4641-4652.
IEEE DOI 1610
gesture recognition BibRef

Jia, C., Shao, M., Fu, Y.,
Sparse Canonical Temporal Alignment With Deep Tensor Decomposition for Action Recognition,
IP(26), No. 2, February 2017, pp. 738-750.
IEEE DOI 1702
decomposition BibRef

Vemulapalli, R.[Raviteja], Arrate, F.[Felipe], Chellappa, R.[Rama],
R3DG features: Relative 3D geometry-based skeletal representations for human action recognition,
CVIU(152), No. 1, 2016, pp. 155-166.
Elsevier DOI 1609
BibRef
Earlier:
Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group,
CVPR14(588-595)
IEEE DOI 1409
Action Recognition;Lie Groups;Special Euclidean Group Action recognition BibRef

Vemulapalli, R.[Raviteja], Chellappa, R.[Rama],
Rolling Rotations for Recognizing Human Actions from 3D Skeletal Data,
CVPR16(4471-4479)
IEEE DOI 1612
BibRef

Salih, A.A.A.[Al Alwani Adnan], Youssef, C.[Chahir],
Spatiotemporal representation of 3D skeleton joints-based action recognition using modified spherical harmonics,
PRL(83, Part 1), No. 1, 2016, pp. 32-41.
Elsevier DOI 1609
Spherical harmonics BibRef

Wang, W.[Wei], Yan, Y.[Yan], Zhang, L.M.[Lu-Ming], Hong, R., Sebe, N.[Nicu],
Collaborative Sparse Coding for Multiview Action Recognition,
MultMedMag(23), No. 4, October 2016, pp. 80-87.
IEEE DOI 1612
Collaboration BibRef

Wang, W.[Wei], Yan, Y.[Yan], Nie, L.Q.[Li-Qiang], Zhang, L.M.[Lu-Ming], Winkler, S.[Stefan], Sebe, N.[Nicu],
Sparse Code Filtering for Action Pattern Mining,
ACCV16(II: 3-18).
Springer DOI 1704
BibRef

Liu, Z.[Zhi], Zhang, C.Y.[Chen-Yang], Tian, Y.[Yingli],
3D-based Deep Convolutional Neural Network for action recognition with depth sequences,
IVC(55, Part 2), No. 1, 2016, pp. 93-100.
Elsevier DOI 1612
Action recognition BibRef

Zhang, C.Y.[Chen-Yang], Tian, Y.[Yingli], Guo, X.[Xiaojie], Liu, J.G.[Jin-Gen],
DAAL: Deep activation-based attribute learning for action recognition in depth videos,
CVIU(167), 2018, pp. 37-49.
Elsevier DOI 1804
Attribute learning, Action recognition, Depth camera BibRef

Perez, A.[Alexandre], Tabia, H.[Hedi], Declercq, D.[David], Zanotti, A.[Alain],
Using the conflict in Dempster-Shafer evidence theory as a rejection criterion in classifier output combination for 3D human action recognition,
IVC(55, Part 2), No. 1, 2016, pp. 149-157.
Elsevier DOI 1612
Human action recognition BibRef

Perez, A.[Alexandre], Tabia, H.[Hedi], Declercq, D.[David], Zanotti, A.[Alain],
Feature covariance for human action recognition,
IPTA16(1-5)
IEEE DOI 1703
covariance matrices BibRef

Lillo, I.[Ivan], Niebles, J.C.[Juan Carlos], Soto, A.[Alvaro],
Sparse composition of body poses and atomic actions for human activity recognition in RGB-D videos,
IVC(59), No. 1, 2017, pp. 63-75.
Elsevier DOI 1704
BibRef
And: Corrigendum: IVC(66), No. 1, 2017, pp. 48-.
Elsevier DOI 1710
BibRef
And:
A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets,
CVPR16(1981-1990)
IEEE DOI 1612
Activity recognition BibRef

Guo, Y.[Yanan], Tao, D.P.[Da-Peng], Liu, W., Cheng, J.[Jun],
Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition,
SMCS(47), No. 4, April 2017, pp. 617-627.
IEEE DOI 1704
Cameras BibRef

Huang, M.[Min], Su, S.Z.[Song-Zhi], Cai, G.R.[Guo-Rong], Zhang, H.B.[Hong-Bo], Cao, D.L.[Dong-Lin], Li, S.Z.[Shao-Zi],
Meta-action descriptor for action recognition in RGBD video,
IET-CV(11), No. 4, June 2017, pp. 301-308.
DOI Link 1705
BibRef

Gao, Z., Li, S.H., Zhu, Y.J., Wang, C., Zhang, H.,
Collaborative sparse representation leaning model for RGBD action recognition,
JVCIR(48), No. 1, 2017, pp. 442-452.
Elsevier DOI 1708
RGBD, action, recognition BibRef

Hao, T.[Tong], Wu, D.[Dan], Wang, Q.[Qian], Sun, J.S.[Jin-Sheng],
Multi-view representation learning for multi-view action recognition,
JVCIR(48), No. 1, 2017, pp. 453-460.
Elsevier DOI 1708
Multi-view, learning BibRef

Liang, B., Zheng, L.,
Specificity and Latent Correlation Learning for Action Recognition Using Synthetic Multi-View Data From Depth Maps,
IP(26), No. 12, December 2017, pp. 5560-5574.
IEEE DOI 1710
stereo image processing, action recognition, dictionary learning framework, latent correlation learning, view-specific information, Correlation, Dictionaries, BibRef

Liang, B., Zheng, L.,
A Survey on Human Action Recognition Using Depth Sensors,
DICTA15(1-8)
IEEE DOI 1603
feature extraction BibRef

Han, Y.M.[Ya-Min], Zhang, P.[Peng], Zhuo, T.[Tao], Huang, W.[Wei], Zhang, Y.N.[Yan-Ning],
Going deeper with two-stream ConvNets for action recognition in video surveillance,
PRL(107), 2018, pp. 83-90.
Elsevier DOI 1805
Deeper, Two-stream, ConvNets, Action recognition, Video surveillance BibRef

Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Chen, C.[Chen],
3D Action Recognition Using Multiscale Energy-Based Global Ternary Image,
CirSysVideo(28), No. 8, August 2018, pp. 1824-1838.
IEEE DOI 1808
Skeleton, Shape, Robustness, Cameras, Histograms, Transforms, Action recognition, depth sequence, human-computer interaction BibRef

Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Chen, C.[Chen],
Robust 3D Action Recognition Through Sampling Local Appearances and Global Distributions,
MultMed(20), No. 8, August 2018, pp. 1932-1947.
IEEE DOI 1808
Shape, Cameras, Solid modeling, Clutter, Detectors, Robustness, Depth data, 3-D action recognition BibRef

Liu, M.Y.[Meng-Yuan], Liu, H.[Hong], Chen, C.[Chen], Najafian, M.[Maryam],
Energy-Based Global Ternary Image for Action Recognition Using Sole Depth Sequences,
3DV16(47-55)
IEEE DOI 1701
Encoding. Changes in depth pixels. BibRef

Keçeli, A.S.[Ali Seydi], Kaya, A.[Aydin], Can, A.B.[Ahmet Burak],
Combining 2D and 3D deep models for action recognition with depth information,
SIViP(12), No. 6, September 2018, pp. 1197-1205.
WWW Link. 1808
BibRef


Li, C.[Chao], Zhao, Z.[Zheheng], Guo, X.[Xiaohu],
ArticulatedFusion: Real-Time Reconstruction of Motion, Geometry and Segmentation Using a Single Depth Camera,
ECCV18(VIII: 324-340).
Springer DOI 1810
BibRef

Bui, M., Duong, V., Tai, T., Wang, J.,
Depth Human Action Recognition Based on Convolution Neural Networks and Principal Component Analysis,
ICIP18(1543-1547)
IEEE DOI 1809
Videos, Feature extraction, Principal component analysis, Heuristic algorithms, Convolution, Image recognition, feature representation BibRef

Heidarivincheh, F.[Farnoosh], Mirmehdi, M.[Majid], Damen, D.[Dima],
Beyond Action Recognition: Action Completion in RGB-D Data,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Liu, J., Akhtar, N., Mian, A.,
Viewpoint Invariant RGB-D Human Action Recognition,
DICTA17(1-8)
IEEE DOI 1804
Fourier analysis, convolution, feature extraction, gesture recognition, image colour analysis, Videos BibRef

Rong, T.[Tao], Yang, R.[Rui], Yang, R.[Ruoyu],
Continuous Motion Recognition in Depth Camera Based on Recurrent Neural Networks and Grid-based Average Depth,
PSIVT17(212-221).
Springer DOI 1802
BibRef

Wei, L.L.[Liang-Lei], Wu, Y.R.[Yi-Rui], Wang, W.H.[Wen-Hai], Lu, T.[Tong],
A Novel 3D Human Action Recognition Framework for Video Content Analysis,
MMMod18(I:42-53).
Springer DOI 1802
BibRef

Wang, P., Wang, S., Gao, Z., Hou, Y., Li, W.,
Structured Images for RGB-D Action Recognition,
CEFR-LCV17(1005-1014)
IEEE DOI 1802
Aggregates, Benchmark testing, Dynamics, Image recognition, Periodic structures, Skeleton, BibRef

Asadi-Aghbolaghi, M., Bertiche, H., Roig, V., Kasaei, S., Escalera, S.,
Action Recognition from RGB-D Data: Comparison and Fusion of Spatio-Temporal Handcrafted Features and Deep Strategies,
EmotionComp17(3179-3188)
IEEE DOI 1802
Cameras, Computational modeling, Machine learning, Optical imaging, Trajectory, Videos BibRef

Roegiers, S.[Sanne], Allebosch, G.[Gianni], Veelaert, P.[Peter], Philips, W.[Wilfried],
Body Related Occupancy Maps for Human Action Recognition,
ACIVS17(15-27).
Springer DOI 1712
BibRef

Cipolla, E.[Emanuele], Infantino, I.[Ignazio], Maniscalco, U.[Umberto], Pilato, G.[Giovanni], Vella, F.[Filippo],
Indoor Actions Classification Through Long Short Term Memory Neural Networks,
CIAP17(I:435-444).
Springer DOI 1711
RGB-D and IR. BibRef

Luo, Z.L.[Ze-Lun], Peng, B.Y.[Bo-Ya], Huang, D.A.[De-An], Alahi, A.[Alexandre], Fei-Fei, L.[Li],
Unsupervised Learning of Long-Term Motion Dynamics for Videos,
CVPR17(7101-7110)
IEEE DOI 1711
Activity recognition, Hidden Markov models, Image reconstruction, Semantics, Videos BibRef

Awwad, S., Piccardi, M.[Massimo],
Local depth patterns for fine-grained activity recognition in depth videos,
ICVNZ16(1-6)
IEEE DOI 1701
Activity recognition BibRef

Li, J., Chen, J., Sun, L.,
Joint Motion Similarity (JMS)-Based Human Action Recognition Using Kinect,
DICTA16(1-8)
IEEE DOI 1701
Feature extraction BibRef

Wang, Q.[Qian], Jin, W.[Wei], Wang, G.[Gang],
Gathering Event Detection by Stereo Vision,
ISVC16(II: 431-442).
Springer DOI 1701
BibRef

Ling, J.[Jiaxu], Tian, L.H.[Li-Hua], Li, C.[Chen],
3D Human Activity Recognition Using Skeletal Data from RGBD Sensors,
ISVC16(II: 133-142).
Springer DOI 1701
BibRef

Gupta, K., Bhavsar, A.,
Scale Invariant Human Action Detection from Depth Cameras Using Class Templates,
PBVS16(304-311)
IEEE DOI 1612
BibRef

Lan, Z., Zhu, Y.[Yi], Hauptmann, A.G., Newsam, S.[Shawn],
Deep Local Video Feature for Action Recognition,
ActionCh17(1219-1225)
IEEE DOI 1709
Feature extraction, Neural networks, Noise measurement, Pattern recognition, Streaming media, Training BibRef

Zhu, Y.[Yi], Newsam, S.[Shawn],
Efficient Action Detection in Untrimmed Videos via Multi-task Learning,
WACV17(197-206)
IEEE DOI 1609
BibRef
Earlier:
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition,
WebScale16(I: 668-684).
Springer DOI 1611
Computational modeling, Proposals, Three-dimensional displays, Training, Training data, Videos BibRef

Hu, J.F.[Jian-Fang], Zheng, W.S.[Wei-Shi], Ma, L.[Lianyang], Wang, G.[Gang], Lai, J.H.[Jian-Huang],
Real-Time RGB-D Activity Prediction by Soft Regression,
ECCV16(I: 280-296).
Springer DOI 1611
BibRef

Cippitelli, E.[Enea], Gambi, E.[Ennio], Spinsante, S.[Susanna], Florez-Revuelta, F.[Francisco],
Human Action Recognition Based on Temporal Pyramid of Key Poses Using RGB-D Sensors,
ACIVS16(510-521).
Springer DOI 1611
BibRef

Nguyen, X.S.[Xuan Son], Nguyen, T.P.[Thanh Phuong], Charpillet, F.,
Effective surface normals based action recognition in depth images,
ICPR16(817-822)
IEEE DOI 1705
BibRef
And:
Improving surface normals based action recognition in depth images,
AVSS16(109-114)
IEEE DOI 1611
Computational modeling, Encoding, Feature extraction, Histograms, Image recognition, Shape, Three-dimensional, displays BibRef

Miao, J., Jia, X., Mathew, R., Xu, X., Taubman, D., Qing, C.,
Efficient action recognition from compressed depth maps,
ICIP16(16-20)
IEEE DOI 1610
Decision support systems BibRef

Khan, M.H., Helsper, J., Boukhers, Z., Grzegorzek, M.,
Automatic recognition of movement patterns in the vojta-therapy using RGB-D data,
ICIP16(1235-1239)
IEEE DOI 1610
Cameras BibRef

Antunes, M., Aouada, D., Ottersten, B.,
A revisit to human action recognition from depth sequences: Guided SVM-sampling for joint selection,
WACV16(1-8)
IEEE DOI 1606
Cameras BibRef

Liu, Z.[Zhi], Feng, X.[Xin], Tian, Y.L.[Ying-Li],
An effective view and time-invariant action recognition method based on depth videos,
VCIP15(1-4)
IEEE DOI 1605
Cameras BibRef

Li, W.B.[Wen-Bo], Wen, L.Y.[Long-Yin], Chang, M.C.[Ming-Ching], Lim, S.N., Lyu, S.W.[Si-Wei],
Adaptive RNN Tree for Large-Scale Human Action Recognition,
ICCV17(1453-1461)
IEEE DOI 1802
image motion analysis, image recognition, image representation, learning (artificial intelligence), recurrent neural nets, BibRef

Li, X., Chuah, M.C.,
ReHAR: Robust and Efficient Human Activity Recognition,
WACV18(362-371)
IEEE DOI 1806
feature extraction, image motion analysis, image representation, image sequences, object tracking, NCAA Basketball Dataset, ReHAR, Task analysis BibRef

Li, W.B.[Wen-Bo], Wen, L.Y.[Long-Yin], Chuah, M.C.[Mooi Choo], Lyu, S.W.[Si-Wei],
Category-Blind Human Action Recognition: A Practical Recognition System,
ICCV15(4444-4452)
IEEE DOI 1602
Feature extraction BibRef

Tachos, S.[Stavros], Avgerinakis, K.[Konstantinos], Briasouli, A.[Alexia], Kompatsiaris, I.[Ioannis],
Appearance and Depth for Rapid Human Activity Recognition in Real Applications,
BMVC15(xx-yy).
DOI Link 1601
BibRef

Chen, C.[Chen], Hou, Z.J.[Zhen-Jie], Zhang, B.C.[Bao-Chang], Jiang, J.J.[Jun-Jun], Yang, Y.[Yun],
Gradient Local Auto-Correlations and Extreme Learning Machine for Depth-Based Activity Recognition,
ISVC15(I: 613-623).
Springer DOI 1601
BibRef

Liu, H.[Hong], Tian, L.[Lu], Liu, M.Y.[Meng-Yuan], Tang, H.[Hao],
SDM-BSM: A fusing depth scheme for human action recognition,
ICIP15(4674-4678)
IEEE DOI 1512
Bag of Words BibRef

Chen, C.[Chen], Jafari, R.[Roozbeh], Kehtarnavaz, N.[Nasser],
UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor,
ICIP15(168-172)
IEEE DOI 1512
Multimodal human action dataset BibRef

Yang, R.[Rui], Yang, R.[Ruoyu],
DMM-Pyramid Based Deep Architectures for Action Recognition with Depth Cameras,
ACCV14(V: 37-49).
Springer DOI 1504
BibRef

Lee, A.R.[A-Reum], Suk, H.I.[Heung-Il], Lee, S.W.[Seong-Whan],
View-Invariant 3D Action Recognition Using Spatiotemporal Self-Similarities from Depth Camera,
ICPR14(501-505)
IEEE DOI 1412
Computer vision BibRef

Keceli, A.S.[Ali Seydi], Can, A.B.[Ahmet Burak],
A Multimodal Approach for Recognizing Human Actions Using Depth Information,
ICPR14(421-426)
IEEE DOI 1412
Accuracy BibRef

Lin, Y.Y.[Yen-Yu], Hua, J.H.[Ju-Hsuan], Tang, N.C.[Nick C.], Chen, M.H.[Min-Hung], Liao, H.Y.M.[Hong-Yuan Mark],
Depth and Skeleton Associated Action Recognition without Online Accessible RGB-D Cameras,
CVPR14(2617-2624)
IEEE DOI 1409
BibRef

Lu, C.[Cewu], Jia, J.Y.[Jia-Ya], Tang, C.K.[Chi-Keung],
Range-Sample Depth Feature for Action Recognition,
CVPR14(772-779)
IEEE DOI 1409
Action Recognition;Binary Feature;Depth;Sampling BibRef

Hadfield, S.[Simon], Lebeda, K.[Karel], Bowden, R.[Richard],
Natural Action Recognition Using Invariant 3D Motion Encoding,
ECCV14(II: 758-771).
Springer DOI 1408
BibRef

Zanfir, M.[Mihai], Leordeanu, M.[Marius], Sminchisescu, C.[Cristian],
The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection,
ICCV13(2752-2759)
IEEE DOI 1403
RGB-D cameras BibRef

Luo, J.J.[Jia-Jia], Wang, W.[Wei], Qi, H.R.[Hai-Rong],
Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps,
ICCV13(1809-1816)
IEEE DOI 1403
BibRef

Körner, M.[Marco], Denzler, J.[Joachim],
JAR-Aibo: A Multi-view Dataset for Evaluation of Model-Free Action Recognition Systems,
SBA13(527-535).
Springer DOI 1309
BibRef
And:
Temporal Self-Similarity for Appearance-Based Action Recognition in Multi-View Setups,
CAIP13(163-171).
Springer DOI 1308
BibRef
Earlier:
Analyzing the Subspaces Obtained by Dimensionality Reduction for Human Action Recognition from 3d Data,
AVSS12(130-135).
IEEE DOI 1211
BibRef

Wang, H.J.[Hao-Jen], Lin, Y.L.[Yen-Liang], Huang, C.Y.[Cheng-Yu], Hou, Y.L.[Yu-Lin], Hsu, W.[Winston],
Full body human attribute detection in indoor surveillance environment using color-depth information,
AVSS13(383-388)
IEEE DOI 1311
Color BibRef

Negin, F.[Farhood], Özdemir, F.[Flrat], Akgül, C.B.[Ceyhun Burak], Yüksel, K.A.[Kamer Ali], Erçil, A.[Aytül],
A Decision Forest Based Feature Selection Framework for Action Recognition from RGB-Depth Cameras,
ICIAR13(648-657).
Springer DOI 1307
BibRef

Oreifej, O.[Omar], Liu, Z.C.[Zi-Cheng],
HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences,
CVPR13(716-723)
IEEE DOI 1309
3D BibRef

Seidenari, L.[Lorenzo], Varano, V.[Vincenzo], Berretti, S.[Stefano], del Bimbo, A.[Alberto], Pala, P.[Pietro],
Weakly Aligned Multi-part Bag-of-Poses for Action Recognition from Depth Cameras,
SBA13(446-455).
Springer DOI 1309
BibRef
And:
Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses,
HAU3D13(479-485)
IEEE DOI 1309
RGB-D;action recognition;depth cameras BibRef

Azary, S.[Sherif], Savakis, A.E.[Andreas E.],
Grassmannian Spectral Regression for Action Recognition,
ISVC13(II:189-198).
Springer DOI 1311
BibRef
And:
Grassmannian Sparse Representations and Motion Depth Surfaces for 3D Action Recognition,
HAU3D13(492-499)
IEEE DOI 1309
BibRef

Yumiba, R.[Ryo], Agata, Y.[Yoshiki], Fujiyoshi, H.[Hironobu],
A Compensation Method of Motion Features with Regression for Deficient Depth Image,
HAU3D13(558-565)
IEEE DOI 1309
Action Recognition; Depth Image BibRef

Avola, D.[Danilo], Cinque, L.[Luigi], Levialdi, S.[Stefano], Placidi, G.[Giuseppe],
Human Body Language Analysis: A Preliminary Study Based on Kinect Skeleton Tracking,
SBA13(465-473).
Springer DOI 1309
BibRef

Wang, J.[Jiang], Liu, Z.C.[Zi-Cheng], Chorowski, J.[Jan], Chen, Z.Y.[Zhuo-Yuan], Wu, Y.[Ying],
Robust 3D Action Recognition with Random Occupancy Patterns,
ECCV12(II: 872-885).
Springer DOI 1210
BibRef

Chen, L.J.[Lu-Jun], Yao, H.X.[Hong-Xun], Sun, X.S.[Xiao-Shuai],
Action retrieval based on generalized dynamic depth data matching,
VCIP12(1-4).
IEEE DOI 1302
BibRef

Li, W.Q.[Wan-Qing], Zhang, Z.Y.[Zheng-You], Liu, Z.C.[Zi-Cheng],
Action recognition based on a bag of 3D points,
CVPR4HB10(9-14).
IEEE DOI 1006
BibRef

Minhas, R.[Rashid], Baradarani, A.[Aryaz], Seifzadeh, S.[Sepideh], Wu, Q.M.J.[Q. M. Jonathan],
Human Action Recognition Using Non-separable Oriented 3D Dual-Tree Complex Wavelets,
ACCV09(III: 226-235).
Springer DOI 0909
BibRef

Hahn, M.[Markus], Krüger, L.[Lars], Wöhler, C.[Christian],
3D Action Recognition and Long-Term Prediction of Human Motion,
CVS08(xx-yy).
Springer DOI 0805
BibRef

Grundmann, M.[Matthias], Meier, F.[Franziska], Essa, I.A.[Irfan A.],
3D Shape Context and Distance Transform for action recognition,
ICPR08(1-4).
IEEE DOI 0812
BibRef

Klaeser, A., Marszalek, M., Schmid, C.,
A Spatio-Temporal Descriptor Based on 3D-Gradients,
BMVC08(xx-yy).
PDF File. 0809
BibRef

Marszalek, M.[Marcin], Laptev, I.[Ivan], Schmid, C.[Cordelia],
Actions in context,
CVPR09(2929-2936).
IEEE DOI 0906
See: See also Hollywood2 Human Actions and Scenes Dataset. BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Viewpoint invariant, View Invariant, Human Action Detection, Human Action Recognition .


Last update:Oct 15, 2018 at 09:19:25