16.7.4.6.3 Learning for Human Action Recognition and Detection

Chapter Contents (Back)
Action Recognition. Human Actions. Human Motion. Learning. See also Human Action Detection, Human Action Recognition.

Laptev, I.[Ivan], Caputo, B.[Barbara], Schuldt, C.[Christian], Lindeberg, T.[Tony],
Local velocity-adapted motion events for spatio-temporal recognition,
CVIU(108), No. 3, December 2007, pp. 207-229.
WWW Link. 0711
BibRef
Earlier: A3, A1, A2, Only:
Recognizing human actions: a local SVM approach,
ICPR04(III: 32-36).
IEEE DOI 0409
Dataset, Actions.
WWW Link. Motion; Local features; Motion descriptors; Matching; Velocity adaptation; Action recognition; Learning; SVM BibRef

Niebles, J.C.[Juan Carlos], Wang, H.C.[Hong-Cheng], Fei-Fei, L.[Li],
Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words,
IJCV(79), No. 3, September 2008, pp. xx-yy.
Springer DOI 0806
BibRef BMVC06(III:1249).
PDF File. 0609
BibRef

Huang, D.A.[De-An], Fei-Fei, L.[Li], Niebles, J.C.[Juan Carlos],
Connectionist Temporal Modeling for Weakly Supervised Action Labeling,
ECCV16(IV: 137-153).
Springer DOI 1611
BibRef

Niebles, J.C.[Juan Carlos], Fei-Fei, L.[Li],
A Hierarchical Model of Shape and Appearance for Human Action Classification,
CVPR07(1-8).
IEEE DOI 0706
BibRef

Niebles, J.C.[Juan Carlos], Chen, C.W.[Chih-Wei], Fei-Fei, L.[Li],
Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification,
ECCV10(II: 392-405).
Springer DOI 1009
BibRef

Lillo, I.[Ivan], Soto, A.[Alvaro], Niebles, J.C.[Juan Carlos],
Discriminative Hierarchical Modeling of Spatio-temporally Composable Human Activities,
CVPR14(812-819)
IEEE DOI 1409
action classification; composable actions; hierarchical modelling BibRef

Savarese, S.[Silvio], del Pozo, A.[Andrey], Niebles, J.C.[Juan Carlos], Fei-Fei, L.[Li],
Spatial-Temporal correlatons for unsupervised action classification,
Motion08(1-8).
IEEE DOI 0801
BibRef

Liang, Y.M.[Yu-Ming], Shih, S.W.[Sheng-Wen], Shih, C.C.[Chun-Chieh], Liao, H.Y.M., Lin, C.C.[Cheng-Chung],
Learning Atomic Human Actions Using Variable-Length Markov Models,
SMC-B(39), No. 1, February 2009, pp. 268-280.
IEEE DOI 0902
BibRef

Patricio, M.A.[Miguel A.], García, J.[Jesús], Berlanga, A.[Antonio], Molina, J.M.[José M.],
Visual data association for real-time video tracking using genetic and estimation of distribution algorithms,
IJIST(19), No. 3, September 2009, pp. 208-220.
DOI Link 0909
BibRef

Loza, A., Patricio, M.A.[Miguel A.], García, J.[Jesús], Molina, J.M.[José M.],
Advanced algorithms for real-time video tracking with multiple targets,
ICARCV08(125-131).
IEEE DOI 1109
BibRef

Perez Concha, O.[Oscar], Xu, R.Y.D.[Richard Yi Da], Piccardi, M.[Massimo],
Robust Dimensionality Reduction for Human Action Recognition,
DICTA10(349-356).
IEEE DOI 1012
BibRef

Pérez, Ó.[Óscar], Piccardi, M.[Massimo], García, J.[Jesús], Patricio, M.Á.[Miguel Ángel], Molina, J.M.[José Manuel],
Comparison Between Genetic Algorithms and the Baum-Welch Algorithm in Learning HMMs for Human Activity Classification,
EvoIASP07(399-406).
Springer DOI 0704
BibRef

Piccardi, M.[Massimo], Perez, O.[Oscar],
Hidden Markov Models with Kernel Density Estimation of Emission Probabilities and their Use in Activity Recognition,
VS07(1-8).
IEEE DOI 0706
BibRef

Liu, C.[Chang], Yuen, P.C.[Pong C.],
Human action recognition using boosted EigenActions,
IVC(28), No. 5, May 2010, pp. 825-835.
Elsevier DOI 1003
BibRef
Earlier:
Boosting EigenActions: A new algorithm for human action categorization,
FG08(1-6).
IEEE DOI 0809
Human action recognition; Salient action unit; Adaboost BibRef

Liu, C.[Chang], Yuen, P.C.[Pong C.],
A Boosted Co-Training Algorithm for Human Action Recognition,
CirSysVideo(21), No. 9, September 2011, pp. 1203-1213.
IEEE DOI 1109
BibRef

Ma, A.J., Yuen, P.C., Zou, W.W.W., Lai, J.H.,
Supervised Spatio-Temporal Neighborhood Topology Learning for Action Recognition,
CirSysVideo(23), No. 8, 2013, pp. 1447-1460.
IEEE DOI 1307
Context BibRef

Ma, J.H.[Jin-Hua], Yuen, P.C.[Pong C.], Zou, W.W.[Wei-Wen], Lai, J.H.[Jian-Huang],
Supervised Neighborhood Topology Learning for Human Action Recognition,
MLMotion09(476-481).
IEEE DOI 0910
BibRef

Han, L.[Lei], Wu, X.X.[Xin-Xiao], Liang, W.[Wei], Hou, G.M.[Guang-Ming], Jia, Y.D.[Yun-De],
Discriminative human action recognition in the learned hierarchical manifold space,
IVC(28), No. 5, May 2010, pp. 836-849.
Elsevier DOI 1003
BibRef
Earlier: A1, A3, A2, A5, Only:
Human action recognition using discriminative models in the learned hierarchical manifold space,
FG08(1-6).
IEEE DOI 0809
Human action recognition; Discriminative model; Hierarchical manifold learning; Mutual invariant; Motion pattern See also Action recognition feedback-based framework for human pose reconstruction from monocular images. BibRef

Wu, X.X.[Xin-Xiao], Jia, Y.D.[Yun-De], Liang, W.[Wei],
Incremental discriminant-analysis of canonical correlations for action recognition,
PR(43), No. 12, December 2010, pp. 4190-4197.
Elsevier DOI 1003
BibRef
Earlier: A1, A3, A2:
Incremental discriminative-analysis of canonical correlations for action recognition,
ICCV09(2035-2041).
IEEE DOI 0909
Human action recognition; Incremental discriminant-analysis; Computer vision BibRef

Song, Y., Zheng, Y.T., Tang, S., Zhou, X., Zhang, Y., Lin, S., Chua, T.S.,
Localized Multiple Kernel Learning for Realistic Human Action Recognition in Videos,
CirSysVideo(21), No. 9, September 2011, pp. 1193-1202.
IEEE DOI 1109
BibRef

Gilbert, A.[Andrew], Illingworth, J.[John], Bowden, R.[Richard],
Action Recognition Using Mined Hierarchical Compound Features,
PAMI(33), No. 1, January 2011, pp. 883-897.
IEEE DOI 1104
BibRef
Earlier:
Fast realistic multi-action recognition using mined dense spatio-temporal features,
ICCV09(925-931).
IEEE DOI 0909
BibRef
Earlier:
Scale Invariant Action Recognition Using Compound Features Mined from Dense Spatio-temporal Corners,
ECCV08(I: 222-233).
Springer DOI 0810
Start from basic feature points as in 2D recognition. BibRef

Gilbert, A.[Andrew], Bowden, R.[Richard],
Data Mining for Action Recognition,
ACCV14(V: 290-303).
Springer DOI 1504
BibRef

Seo, H.J.[Hae Jong], Milanfar, P.[Peyman],
Action Recognition from One Example,
PAMI(33), No. 1, January 2011, pp. 867-882.
IEEE DOI 1104
BibRef
Earlier:
Detection of human actions from a single example,
ICCV09(1965-1970).
IEEE DOI 0909
Single example as query to find others BibRef

Oshin, O.[Olusegun], Gilbert, A.[Andrew], Bowden, R.[Richard],
Capturing relative motion and finding modes for action recognition in the wild,
CVIU(125), No. 1, 2014, pp. 155-171.
Elsevier DOI 1406
BibRef
Earlier:
There Is More Than One Way to Get Out of a Car: Automatic Mode Finding for Action Recognition in the Wild,
IbPRIA11(41-48).
Springer DOI 1106
BibRef
And:
Capturing the relative distribution of features for action recognition,
FG11(111-116).
IEEE DOI 1103
Action recognition BibRef

Oshin, O.[Olusegun], Gilbert, A.[Andrew], Illingworth, J.[John], Bowden, R.[Richard],
Action recognition using Randomised Ferns,
ObjectEvent09(530-537).
IEEE DOI 0910
BibRef
Earlier:
Spatio-temporal feature recognition using randomised Ferns,
MLMotion08(xx-yy). 0810
BibRef

Liu, J.G.[Jin-Gen], Yang, Y.[Yang], Saleemi, I.[Imran], Shah, M.[Mubarak],
Learning semantic features for action recognition via diffusion maps,
CVIU(116), No. 3, March 2012, pp. 361-377.
Elsevier DOI 1201
BibRef
Earlier: A1, A2, A4, Only:
Learning semantic visual vocabularies using diffusion distance,
CVPR09(461-468).
IEEE DOI 0906
Action recognition; Bag of video words; Semantic visual vocabulary; Diffusion Maps; Pointwise Mutual Information BibRef

Yang, Y.[Yang], Shah, M.[Mubarak],
Learning discriminative features and metrics for measuring action similarity,
ICIP14(1555-1559)
IEEE DOI 1502
Accuracy BibRef

Sultani, W.[Waqas], Saleemi, I.[Imran],
Human Action Recognition across Datasets by Foreground-Weighted Histogram Decomposition,
CVPR14(764-771)
IEEE DOI 1409
action recognition BibRef

Reddy, K.K.[Kishore K.], Liu, J.G.[Jin-Gen], Shah, M.[Mubarak],
Incremental action recognition using feature-tree,
ICCV09(1010-1017).
IEEE DOI 0909
BibRef

Liu, J.G.[Jin-Gen], Luo, J.B.[Jie-Bo], Shah, M.[Mubarak],
Recognizing realistic actions from videos 'in the wild',
CVPR09(1996-2003).
IEEE DOI 0906
BibRef

Liu, J.G.[Jin-Gen], Ali, S.[Saad], Shah, M.[Mubarak],
Recognizing human actions using multiple features,
CVPR08(1-8).
IEEE DOI 0806
BibRef

Ali, S.[Saad], Basharat, A.[Arslan], Shah, M.[Mubarak],
Chaotic Invariants for Human Action Recognition,
ICCV07(1-8).
IEEE DOI 0710
BibRef

Guha, T.[Tanaya], Ward, R.K.[Rabab K.],
Learning Sparse Representations for Human Action Recognition,
PAMI(34), No. 8, August 2012, pp. 1576-1588.
IEEE DOI 1206
BibRef
Earlier:
Action recognition by learnt class-specific overcomplete dictionaries,
FG11(143-148).
IEEE DOI 1103
sparse representation from dictionary in action recognition. Human movement, facial expressions. 3 frameworks. Each descriptor is linear combination of dictionary elements. BibRef

Guha, T.[Tanaya], Ward, R.K.[Rabab K.],
Image Similarity Using Sparse Representation and Compression Distance,
MultMed(16), No. 4, June 2014, pp. 980-987.
IEEE DOI 1407
Approximation methods BibRef

Ji, S.W.[Shui-Wang], Xu, W.[Wei], Yang, M.[Ming], Yu, K.[Kai],
3D Convolutional Neural Networks for Human Action Recognition,
PAMI(35), No. 1, January 2013, pp. 221-231.
IEEE DOI 1212
BibRef

Yang, M.[Ming], Lv, F.J.[Feng-Jun], Xu, W.[Wei], Yu, K.[Kai], Gong, Y.H.[Yi-Hong],
Human action detection by boosting efficient motion features,
ObjectEvent09(522-529).
IEEE DOI 0910
BibRef

Yang, M.[Ming], Lv, F.J.[Feng-Jun], Xu, W.[Wei], Gong, Y.H.[Yi-Hong],
Detection Driven Adaptive Multi-cue Integration for Multiple Human Tracking,
ICCV09(1554-1561).
IEEE DOI 0909
BibRef

Lu, Z.W.[Zhi-Wu], Peng, Y.X.[Yu-Xin],
Latent semantic learning with structured sparse representation for human action recognition,
PR(46), No. 7, July 2013, pp. 1799-1809.
Elsevier DOI 1303
Human action recognition; Latent semantic learning; Spectral embedding; Structured sparse representation; L 1 - norm hypergraph regularization BibRef

Lu, Z.W.[Zhi-Wu], Peng, Y.X.[Yu-Xin], Ip, H.H.S.[Horace H.S.],
Spectral learning of latent semantics for action recognition,
ICCV11(1503-1510).
IEEE DOI 1201
See also Contextual Kernel and Spectral Methods for Learning the Semantics of Images. BibRef

Zhang, J.G.[Jian-Gen], Yao, B.[Benjamin], Wang, Y.T.[Yong-Tian],
Auto learning temporal atomic actions for activity classification,
PR(46), No. 7, July 2013, pp. 1789-1798.
Elsevier DOI 1303
Activity classification; Atomic action; Temporal-HDP BibRef

Wang, L.[Liang], Wang, Y.Z.[Yi-Zhou], Jiang, T.T.[Ting-Ting], Zhao, D.B.[De-Bin], Gao, W.[Wen],
Learning discriminative features for fast frame-based action recognition,
PR(46), No. 7, July 2013, pp. 1832-1840.
Elsevier DOI 1303
Frame-based action recognition; Feature mining BibRef

Gaidon, A.[Adrien], Harchaoui, Z.[Zaid], Schmid, C.[Cordelia],
Temporal Localization of Actions with Actoms,
PAMI(35), No. 11, 2013, pp. 2782-2795.
IEEE DOI 1309
BibRef
Earlier:
Recognizing activities with cluster-trees of tracklets,
BMVC12(30).
DOI Link 1301
BibRef
Earlier:
A time series kernel for action recognition,
BMVC11(xx-yy).
HTML Version. 1110
BibRef
And:
Actom sequence models for efficient action detection,
CVPR11(3201-3208).
IEEE DOI 1106
Action recognition;actoms;temporal localization;video analysis BibRef

Gaidon, A.[Adrien], Harchaoui, Z.[Zaid], Schmid, C.[Cordelia],
Activity representation with motion hierarchies,
IJCV(107), No. 3, May 2014, pp. 219-238.
Springer DOI 1404
Complex activities, example: pole vault. BibRef

Gaidon, A.[Adrien], Marszalek, M.[Marcin], Schmid, C.[Cordelia],
Mining visual actions from movies,
BMVC09(xx-yy).
PDF File. 0909
BibRef

Weinzaepfel, P., Harchaoui, Z.[Zaid], Schmid, C.[Cordelia],
Learning to Track for Spatio-Temporal Action Localization,
ICCV15(3164-3172)
IEEE DOI 1602
Detectors BibRef

Laptev, I.[Ivan], Marszalek, M.[Marcin], Schmid, C.[Cordelia], Rozenfeld, B.[Benjamin],
Learning realistic human actions from movies,
CVPR08(1-8).
IEEE DOI 0806
See also Structured Learning of Human Interactions in TV Shows. BibRef

Laptev, I.[Ivan], Perez, P.[Patrick],
Retrieving actions in movies,
ICCV07(1-8).
IEEE DOI 0710
BibRef

Wu, J.Z.[Jian-Zhai], Hu, D.[Dewen],
Learning Effective Event Models to Recognize a Large Number of Human Actions,
MultMed(16), No. 1, January 2014, pp. 147-158.
IEEE DOI 1402
image motion analysis BibRef

Chen, C.H.[Chang-Hong], Yang, S.Q.[Shun-Qing], Gan, Z.L.[Zong-Liang],
Topic-Based Knowledge Transfer Algorithm for Cross-View Action Recognition,
IEICE(E97-D), No. 3, March 2014, pp. 614-617.
WWW Link. 1403
BibRef

Luo, G., Yang, S., Tian, G., Yuan, C.F.[Chun-Feng], Hu, W.M.[Wei-Ming], Maybank, S.J.[Steve J.],
Learning Human Actions by Combining Global Dynamics and Local Appearance,
PAMI(36), No. 12, December 2014, pp. 2466-2482.
IEEE DOI 1411
Behavioral science BibRef

Vrigkas, M.[Michalis], Karavasilis, V.[Vasileios], Nikou, C.[Christophoros], Kakadiaris, I.A.[Ioannis A.],
Matching mixtures of curves for human action recognition,
CVIU(119), No. 1, 2014, pp. 27-40.
Elsevier DOI 1402
Human action recognition See also novel framework for motion segmentation and tracking by clustering incomplete trajectories, A. BibRef

Vrigkas, M.[Michalis], Nikou, C.[Christophoros], Kakadiaris, I.A.[Ioannis A.],
Identifying Human Behaviors Using Synchronized Audio-Visual Cues,
AffCom(8), No. 1, January 2017, pp. 54-66.
IEEE DOI 1703
Computational modeling BibRef

Vrigkas, M.[Michalis], Nikou, C.[Christophoros], Kakadiaris, I.A.[Ioannis A.],
Active privileged learning of human activities from weakly labeled samples,
ICIP16(3036-3040)
IEEE DOI 1610
Entropy BibRef

Zhang, L.[Lei], Zhen, X.T.[Xian-Tong], Shao, L.[Ling],
Learning Object-to-Class Kernels for Scene Classification,
IP(23), No. 8, August 2014, pp. 3241-3253.
IEEE DOI 1408
BibRef
And:
High order co-occurrence of visualwords for action recognition,
ICIP12(757-760).
IEEE DOI 1302
image classification BibRef

Zhang, L.[Lei], Shum, H.P.H.[H. P. H.], Shao, L.[Ling],
Manifold Regularized Experimental Design for Active Learning,
IP(26), No. 2, February 2017, pp. 969-981.
IEEE DOI 1702
design of experiments BibRef

Zhang, L.[Lei], Xie, S.Z.[Shou-Zhi], Zhen, X.T.[Xian-Tong],
Discriminative high-level representations for scene classification,
ICIP13(4345-4348)
IEEE DOI 1402
High-level representation BibRef

Tang, J.[Jun], Shao, L.[Ling], Zhen, X.T.[Xian-Tong],
Human Action Retrieval via efficient feature matching,
AVSS13(306-311)
IEEE DOI 1311
content-based retrieval. Finding videos of the same actions. BibRef

Chen, F.F.[Fei-Fei], Sang, N.[Nong], Kuang, X.Q.[Xiao-Qin], Gan, H.T.[Hai-Tao], Gao, C.X.[Chang-Xin],
Action recognition through discovering distinctive action parts,
JOSA-A(32), No. 2, February 2015, pp. 173-185.
DOI Link 1502
BibRef
Earlier: A1, A2, A5, A3, Only:
Discovering distinctive action parts for action recognition,
ICIP14(1520-1524)
IEEE DOI 1502
Pattern recognition. Computer vision BibRef

Zhang, S.W.[Shi-Wei], Gao, C.X.[Chang-Xin], Chen, F.F.[Fei-Fei], Luo, S.H.[Si-Hui], Sang, N.[Nong],
Group Sparse-Based Mid-Level Representation for Action Recognition,
SMCS(47), No. 4, April 2017, pp. 660-672.
IEEE DOI 1704
Detectors BibRef

Zhou, Z., Shi, F., Wu, W.,
Learning Spatial and Temporal Extents of Human Actions for Action Detection,
MultMed(17), No. 4, April 2015, pp. 512-525.
IEEE DOI 1503
Discrete cosine transforms BibRef

Liu, A., Su, Y., Jia, P., Gao, Z., Hao, T., Yang, Z.,
Multipe/Single-View Human Action Recognition via Part-Induced Multitask Structural Learning,
Cyber(45), No. 6, June 2015, pp. 1194-1208.
IEEE DOI 1506
Correlation BibRef

Hasan, M.[Mahmudul], Roy-Chowdhury, A.K.[Amit K.],
A Continuous Learning Framework for Activity Recognition Using Deep Hybrid Feature Models,
MultMed(17), No. 11, November 2015, pp. 1909-1922.
IEEE DOI 1511
BibRef
And:
Context Aware Active Learning of Activity Recognition Models,
ICCV15(4543-4551)
IEEE DOI 1602
BibRef
Earlier:
Incremental Activity Modeling and Recognition in Streaming Videos,
CVPR14(796-803)
IEEE DOI 1409
BibRef
And:
Continuous Learning of Human Activity Models Using Deep Nets,
ECCV14(III: 705-720).
Springer DOI 1408
Adaptation models. Computational modeling BibRef

Hasan, M.[Mahmudul], Roy-Chowdhury, A.K.[Amit K.],
Incremental learning of human activity models from videos,
CVIU(144), No. 1, 2016, pp. 24-35.
Elsevier DOI 1604
Incremental learning BibRef

Mahmud, T.[Tahmida], Hasan, M.[Mahmudul], Chakraborty, A.[Anirban], Roy-Chowdhury, A.K.[Amit K.],
A poisson process model for activity forecasting,
ICIP16(3339-3343)
IEEE DOI 1610
Forecasting what comes next. BibRef

Feng, Y.[Yang], Wu, X.X.[Xin-Xiao], Jia, Y.,
Multi-group-multi-class domain adaptation for event recognition,
IET-CV(10), No. 1, 2016, pp. 60-66.
DOI Link 1601
neural nets BibRef

Feng, Y.[Yang], Wu, X.X.[Xin-Xiao], Wang, H.[Han], Liu, J.[Jing],
Multi-group Adaptation for Event Recognition from Videos,
ICPR14(3915-3920)
IEEE DOI 1412
Events in consumer videos. Based on loosely labeld web videos. BibRef

Qin, J., Liu, L., Zhang, Z., Wang, Y., Shao, L.,
Compressive Sequential Learning for Action Similarity Labeling,
IP(25), No. 2, February 2016, pp. 756-769.
IEEE DOI 1601
Boosting BibRef

Ijjina, E.P.[Earnest Paul], Chalavadi, K.M.[Krishna Mohan],
Human action recognition using genetic algorithms and convolutional neural networks,
PR(59), No. 1, 2016, pp. 199-212.
Elsevier DOI 1609
Convolutional neural network (CNN) BibRef
Earlier:
Human action recognition based on motion capture information using fuzzy convolution neural networks,
ICAPR15(1-6)
IEEE DOI 1511
BibRef
Earlier:
Human Action Recognition Using Action Bank Features and Convolutional Neural Networks,
DeepLearnV14(328-339).
Springer DOI 1504
convolution BibRef

Ijjina, E.P.[Earnest Paul], Chalavadi, K.M.[Krishna Mohan],
Human action recognition in RGB-D videos using motion sequence information and deep learning,
PR(72), No. 1, 2017, pp. 504-516.
Elsevier DOI 1708
Multi-modal, action, recognition BibRef

Liu, C.H.[Cai-Hua], Liu, J.[Jie], He, Z.C.[Zhi-Cheng], Zhai, Y.[Yujia], Hu, Q.H.[Qing-Hua], Huang, Y.[Yalou],
Convolutional neural random fields for action recognition,
PR(59), No. 1, 2016, pp. 213-224.
Elsevier DOI 1609
Action recognition BibRef

Zhang, J.G.[Jian-Guang], Han, Y.H.[Ya-Hong], Tang, J.H.[Jin-Hui], Hu, Q.H.[Qing-Hua], Jiang, J.M.[Jian-Min],
Semi-Supervised Image-to-Video Adaptation for Video Action Recognition,
Cyber(47), No. 4, April 2017, pp. 960-973.
IEEE DOI 1704
Cameras BibRef

Lei, J., Li, G.H.[Guo-Hui], Zhang, J., Guo, Q., Tu, D.[Dan],
Continuous action segmentation and recognition using hybrid convolutional neural network-hidden Markov model model,
IET-CV(10), No. 6, 2016, pp. 537-544.
DOI Link 1609
Gaussian processes BibRef

Liu, J.J.[Jing-Jing], Chen, C.[Chao], Zhu, Y.[Yan], Liu, W.[Wei], Metaxas, D.N.[Dimitris N.],
Video Classification via Weakly Supervised Sequence Modeling,
CVIU(152), No. 1, 2016, pp. 79-87.
Elsevier DOI 1609
Video classification. for gesture and action classification. BibRef

Pei, L.[Lishen], Ye, M.[Mao], Zhao, X.Z.[Xue-Zhuan], Dou, Y.[Yumin], Bao, J.[Jiao],
Action recognition by learning temporal slowness invariant features,
VC(32), No. 11, November 2016, pp. 1395-1404.
WWW Link. 1611
BibRef

Tzelepis, C.[Christos], Galanopoulos, D.[Damianos], Mezaris, V.[Vasileios], Patras, I.[Ioannis],
Learning to detect video events from zero or very few video examples,
IVC(53), No. 1, 2016, pp. 35-44.
Elsevier DOI 1610
Video event detection BibRef

Zhou, Q.A.[Qi-Ang], Zhao, Q.[Qi],
Flexible Clustered Multi-Task Learning by Learning Representative Tasks,
PAMI(38), No. 2, February 2016, pp. 266-278.
IEEE DOI 1601
Covariance matrices BibRef

Zhou, Q.A.[Qi-Ang], Wang, G.[Gang], Jia, K.[Kui], Zhao, Q.[Qi],
Learning to Share Latent Tasks for Action Recognition,
ICCV13(2264-2271)
IEEE DOI 1403
Action Recognition; Latent Task BibRef

Yi, Y.[Yang], Lin, M.Q.[Mao-Qing],
Human action recognition with graph-based multiple-instance learning,
PR(53), No. 1, 2016, pp. 148-162.
Elsevier DOI 1602
Action recognition BibRef

Guo, Z.X.[Zi-Xin], Yi, Y.[Yang],
Graph-based multiple instance learning for action recognition,
ICIP13(3745-3749)
IEEE DOI 1402
Action Recognition BibRef

Sigari, M.H.[Mohamad-Hoseyn], Soltanian-Zadeh, H.[Hamid], Pourreza, H.R.[Hamid-Reza],
A framework for dynamic restructuring of semantic video analysis systems based on learning attention control,
IVC(53), No. 1, 2016, pp. 20-34.
Elsevier DOI 1610
Attention control BibRef

Yuan, Y.[Yuan], Qi, L.[Lei], Lu, X.Q.[Xiao-Qiang],
Action recognition by joint learning,
IVC(55, Part 2), No. 1, 2016, pp. 77-85.
Elsevier DOI 1612
Computer vision BibRef

Tang, J.[Jun], Jin, H.Q.[Hai-Qun], Tan, S.B.[Shou-Biao], Liang, D.[Dong],
Cross-domain action recognition via collective matrix factorization with graph Laplacian regularization,
IVC(55, Part 2), No. 1, 2016, pp. 119-126.
Elsevier DOI 1612
Action recognition BibRef

Xu, T.T.[Tian-Tian], Zhu, F.[Fan], Wong, E.K.[Edward K.], Fang, Y.[Yi],
Dual many-to-one-encoder-based transfer learning for cross-dataset human action recognition,
IVC(55, Part 2), No. 1, 2016, pp. 127-137.
Elsevier DOI 1612
Cross-dataset BibRef

Richard, A.[Alexander], Gall, J.[Juergen],
A bag-of-words equivalent recurrent neural network for action recognition,
CVIU(156), No. 1, 2017, pp. 79-91.
Elsevier DOI 1702
BibRef
Earlier:
Temporal Action Detection Using a Statistical Language Model,
CVPR16(3131-3140)
IEEE DOI 1612
BibRef
Earlier:
A BoW-equivalent Recurrent Neural Network for Action Recognition,
BMVC15(xx-yy).
DOI Link 1601
Action recognition. untrimmed videos. BibRef

Richard, A.[Alexander], Kuehne, H., Gall, J.[Juergen],
Weakly Supervised Action Learning with RNN Based Fine-to-Coarse Modeling,
CVPR17(1273-1282)
IEEE DOI 1711
Assistive technology, Data models, Hidden Markov models, Supervised learning, Training, Videos BibRef

Kim, M.Y.[Min-Young],
Dual soft assignment clustering algorithm for human action video clustering,
CVIU(155), No. 1, 2017, pp. 106-112.
Elsevier DOI 1702
Dual assignment clustering BibRef

Yang, Y., Deng, C., Tao, D., Zhang, S., Liu, W., Gao, X.,
Latent Max-Margin Multitask Learning With Skelets for 3-D Action Recognition,
Cyber(47), No. 2, February 2017, pp. 439-448.
IEEE DOI 1702
cameras BibRef

Yang, Y., Deng, C., Gao, S., Liu, W., Tao, D., Gao, X.,
Discriminative Multi-instance Multitask Learning for 3D Action Recognition,
MultMed(19), No. 3, March 2017, pp. 519-529.
IEEE DOI 1702
Correlation BibRef

Gibson, J.[James], Katsamanis, A.[Athanasios], Romero, F.[Francisco], Xiao, B.[Bo], Georgiou, P.[Panayiotis], Narayanan, S.[Shrikanth],
Multiple Instance Learning for Behavioral Coding,
AffCom(8), No. 1, January 2017, pp. 81-94.
IEEE DOI 1703
Acoustics BibRef

Xu, K.[Ke], Jiang, X.H.[Xing-Hao], Sun, T.F.[Tan-Feng],
Two-Stream Dictionary Learning Architecture for Action Recognition,
CirSysVideo(27), No. 3, March 2017, pp. 567-576.
IEEE DOI 1703
Cameras BibRef

Chen, C.Y.[Chao-Yeh], Grauman, K.[Kristen],
Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search,
PAMI(39), No. 5, May 2017, pp. 908-921.
IEEE DOI 1704
BibRef
Earlier:
Watching Unlabeled Video Helps Learn New Human Actions from Very Few Labeled Snapshots,
CVPR13(572-579)
IEEE DOI 1309
BibRef
And:
Efficient activity detection with max-subgraph search,
CVPR12(1274-1281).
IEEE DOI 1208
Detectors. BibRef

Bandla, S.I.[Sun-Il], Grauman, K.[Kristen],
Active Learning of an Action Detector from Untrimmed Videos,
ICCV13(1833-1840)
IEEE DOI 1403
action detection BibRef

Ma, Z.G.[Zhi-Gang], Chang, X.J.[Xiao-Jun], Yang, Y.[Yi], Sebe, N.[Nicu], Hauptmann, A.G.[Alexander G.],
The Many Shades of Negativity,
MultMed(19), No. 7, July 2017, pp. 1558-1568.
IEEE DOI 1706
Training, negative examples. Animals, Detectors, Event detection, Feature extraction, Semantics, Support vector machines, Training, Attribute representation, attribute selection, complex event detection, selective, fine-grained, labeling BibRef

Chang, X.J.[Xiao-Jun], Yu, Y.L.[Yao-Liang], Yang, Y.[Yi], Xing, E.P.[Eric P.],
Semantic Pooling for Complex Event Analysis in Untrimmed Videos,
PAMI(39), No. 8, August 2017, pp. 1617-1632.
IEEE DOI 1707
BibRef
Earlier:
They are Not Equally Reliable: Semantic Event Search Using Differentiated Concept Classifiers,
CVPR16(1884-1893)
IEEE DOI 1612
Algorithm design and analysis, Event detection, Feature extraction, Hidden Markov models, Semantics, Support vector machines, Videos, Complex event detection, event recognition, event recounting, nearly-isotonic SVM, semantic saliency. Fewer training samples for events. BibRef

Shi, Y.M.[Ye-Min], Tian, Y.H.[Yong-Hong], Wang, Y.W.[Yao-Wei], Huang, T.J.[Tie-Jun],
Sequential Deep Trajectory Descriptor for Action Recognition With Three-Stream CNN,
MultMed(19), No. 7, July 2017, pp. 1510-1520.
IEEE DOI 1706
Cameras, Feature extraction, Histograms, Neural networks, Optical imaging, Streaming media, Trajectory, Action recognition, long-term motion, sequential deep trajectory descriptor (sDTD), three-stream, framework BibRef

Luvizon, D.C.[Diogo Carbonera], Tabia, H.[Hedi], Picard, D.[David],
Learning features combination for human action recognition from skeleton sequences,
PRL(99), No. 1, 2017, pp. 13-20.
Elsevier DOI 1710
Action recognition BibRef

Mokhtari, V.[Vahid], Lopes, L.S.[Luís Seabra], Pinho, A.J.[Armando J.],
Learning robot tasks with loops from experiences to enhance robot adaptability,
PRL(99), No. 1, 2017, pp. 57-66.
Elsevier DOI 1710
Robot task learning with loops BibRef


Yeung, S.[Serena], Ramanathan, V.[Vignesh], Russakovsky, O.[Olga], Shen, L.Y.[Li-Yue], , G.M.[Greg Mori], Fei-Fei, L.[Li],
Learning to Learn from Noisy Web Videos,
CVPR17(7455-7463)
IEEE DOI 1711
Animals, Data models, Labeling, Noise measurement, Training, Videos, Visualization BibRef

de Souza, C.R.[César Roberto], Gaidon, A.[Adrien], Cabon, Y.[Yohann], López, A.M.[Antonio Manuel],
Procedural Generation of Videos to Train Deep Action Recognition Networks,
CVPR17(2594-2604)
IEEE DOI 1711
Animation, Cameras, Games, Machine learning, Manuals, Training, Videos BibRef

Girdhar, R., Ramanan, D., Gupta, A., Sivic, J., Russell, B.,
ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification,
CVPR17(3165-3174)
IEEE DOI 1711
Aggregates, Computer architecture, Convolution, Feature extraction, Image recognition, Streaming media, Trajectory BibRef

Wang, Y., Long, M., Wang, J., Yu, P.S.,
Spatiotemporal Pyramid Network for Video Action Recognition,
CVPR17(2097-2106)
IEEE DOI 1711
Convolution, Optical imaging, Optical losses, Spatiotemporal phenomena, Training BibRef

Shi, Z., Kim, T.K.,
Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences,
CVPR17(4684-4693)
IEEE DOI 1711
Data models, Feature extraction, Hidden Markov models, Recurrent neural networks, Skeleton, Training BibRef

Kar, A., Rai, N., Sikka, K., Sharma, G.,
AdaScan: Adaptive Scan Pooling in Deep Convolutional Neural Networks for Human Action Recognition in Videos,
CVPR17(5699-5708)
IEEE DOI 1711
Feature extraction, Hidden Markov models, Prediction algorithms, Standards, Training, Videos BibRef

Liu, J., Wang, G., Hu, P., Duan, L.Y., Kot, A.C.,
Global Context-Aware Attention LSTM Networks for 3D Action Recognition,
CVPR17(3671-3680)
IEEE DOI 1711
Data models, Hidden Markov models, Logic gates, Reliability, Skeleton, Solid modeling, BibRef

Kong, Y., Tao, Z., Fu, Y.,
Deep Sequential Context Networks for Action Prediction,
CVPR17(3662-3670)
IEEE DOI 1711
Data mining, Feature extraction, Robustness, Testing, Training, Videos, Visualization BibRef

Yan, X., Hu, S., Ye, Y.,
Multi-task Clustering of Human Actions by Sharing Information,
CVPR17(4049-4057)
IEEE DOI 1711
Clustering methods, Correlation, Linear programming, Mutual information, Videos, Vocabulary BibRef

Gao, J.Y.[Ji-Yang], Nevatia, R.[Ram],
Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data,
ACCV16(II: 19-34).
Springer DOI 1704
BibRef

Dayrit, F.L.[Fabian Lorenzo], Kimura, R.[Ryosuke], Nakashima, Y.[Yuta], Blanco, A.[Ambrosio], Kawasaki, H.[Hiroshi], Ikeuchi, K.[Katsushi], Sato, T.[Tomokazu], Yokoya, N.[Naokazu],
ReMagicMirror: Action Learning Using Human Reenactment with the Mirror Metaphor,
MMMod17(I: 303-315).
Springer DOI 1701
BibRef

Rahman, M.A.[M. Atiqur], Wang, Y.[Yang],
Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation,
ISVC16(I: 234-244).
Springer DOI 1701
BibRef
And:
Learning Neural Networks with Ranking-Based Losses for Action Retrieval,
CRV16(1-7)
IEEE DOI 1612
Award, Best Vision Paper. ROC area optimization; deep learning; image/video retrieval BibRef

Wang, L.M.[Li-Min], Qiao, Y.[Yu], Tang, X.[Xiaoou], Van Gool, L.J.[Luc J.],
Actionness Estimation Using Hybrid Fully Convolutional Networks,
CVPR16(2708-2717)
IEEE DOI 1612
BibRef

Zhang, B.W.[Bo-Wen], Wang, L.M.[Li-Min], Wang, Z.[Zhe], Qiao, Y.[Yu], Wang, H.L.[Han-Li],
Real-Time Action Recognition with Enhanced Motion Vector CNNs,
CVPR16(2718-2726)
IEEE DOI 1612
BibRef

Yeung, S., Russakovsky, O., Mori, G., Fei-Fei, L.[Li],
End-to-End Learning of Action Detection from Frame Glimpses in Videos,
CVPR16(2678-2687)
IEEE DOI 1612
BibRef

Zhu, W.J.[Wang-Jiang], Hu, J.[Jie], Sun, G.[Gang], Cao, X.D.[Xu-Dong], Qiao, Y.[Yu],
A Key Volume Mining Deep Framework for Action Recognition,
CVPR16(1991-1999)
IEEE DOI 1612
BibRef

Singh, B., Marks, T.K., Jones, M., Tuzel, O.[Oncel], Shao, M.,
A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection,
CVPR16(1961-1970)
IEEE DOI 1612
BibRef

Misra, I.[Ishan], Zitnick, C.L.[C. Lawrence], Hebert, M.[Martial],
Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification,
ECCV16(I: 527-544).
Springer DOI 1611
Action recognition BibRef

Li, Y.H.[Yang-Hao], Lan, C.L.[Cui-Ling], Xing, J.L.[Jun-Liang], Zeng, W.J.[Wen-Jun], Yuan, C.F.[Chun-Feng], Liu, J.Y.[Jia-Ying],
Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks,
ECCV16(VII: 203-220).
Springer DOI 1611
BibRef

Peng, X.J.[Xiao-Jiang], Schmid, C.[Cordelia],
Multi-region Two-Stream R-CNN for Action Detection,
ECCV16(IV: 744-759).
Springer DOI 1611
BibRef

Li, Y.K.[Yi-Kang], Hu, S.H.[Sheng-Hung], Li, B.X.[Bao-Xin],
Recognizing unseen actions in a domain-adapted embedding space,
ICIP16(4195-4199)
IEEE DOI 1610
Zero-shot learning. BibRef

Cai, J.J.[Jun-Jie], Yu, J.[Jie], Imai, F.[Francisco], Tian, Q.[Qi],
Towards temporal adaptive representation for video action recognition,
ICIP16(4155-4159)
IEEE DOI 1610
Computational modeling BibRef

Chen, J.L.[Jia-Lin], Lin, Z.Y.[Zhi-Yi], Wan, Y.C.[Yi-Chen], Chen, L.G.[Liang-Gee],
Accelerated local feature extraction in a reuse scheme for efficient action recognition,
ICIP16(296-299)
IEEE DOI 1610
Acceleration BibRef

Park, E., Han, X., Berg, T.L., Berg, A.C.,
Combining multiple sources of knowledge in deep CNNs for action recognition,
WACV16(1-8)
IEEE DOI 1606
Computer vision BibRef

Bagheri, M.A., Gao, Q., Escalera, S.,
Support vector machines with time series distance kernels for action classification,
WACV16(1-7)
IEEE DOI 1606
Kernel BibRef

Bozorgtabar, B.[Behzad], Goecke, R.[Roland],
Multi-level action detection via learning latent structure,
ICIP15(3004-3008)
IEEE DOI 1512
Action detection BibRef

Wang, Z.[Zhe], Wang, L.M.[Li-Min], Du, W.B.[Wen-Bin], Qiao, Y.[Yu],
Exploring Fisher vector and deep networks for action spotting,
ChaLearn15(10-14)
IEEE DOI 1510
Convolutional codes BibRef

Lin, Z.H.[Zhi-Hui], Yuan, C.[Chun],
A Very Deep Sequences Learning Approach for Human Action Recognition,
MMMod16(II: 256-267).
Springer DOI 1601
BibRef

Ullah, I.[Ihsan], Petrosino, A.[Alfredo],
Spatiotemporal Features Learning with 3DPyraNet,
ACIVS16(638-647).
Springer DOI 1611
BibRef
And:
A Strict Pyramidal Deep Neural Network for Action Recognition,
CIAP15(I:236-245).
Springer DOI 1511
Actions. BibRef

Zhuang, N.[Naifan], Yusufu, T.[Tuoerhongjiang], Ye, J.[Jun], Hua, K.A.[Kien A.],
Group Activity Recognition with Differential Recurrent Convolutional Neural Networks,
FG17(526-531)
IEEE DOI 1707
Activity recognition, Algorithm design and analysis, Computer architecture, Logic gates, Neural networks, Trajectory, Video, surveillance BibRef

Veeriah, V.[Vivek], Zhuang, N.[Naifan], Qi, G.J.[Guo-Jun],
Differential Recurrent Neural Networks for Action Recognition,
ICCV15(4041-4049)
IEEE DOI 1602
LSTM: long short-term memory Neural Network. BibRef

Tahmoush, D.[David], Bonial, C.,
Applying attributes to improve human activity recognition,
AIPR15(1-4)
IEEE DOI 1605
feature extraction BibRef

Tahmoush, D.[David],
Applying action attribute class validation to improve human activity recognition,
ChaLearn15(15-21)
IEEE DOI 1510
Accuracy; Databases; Joints; Ontologies; Training; Training data. Dealing with noisy training data for actions. BibRef

Ramanathan, V.[Vignesh], Tang, K.[Kevin], Mori, G.[Greg], Fei-Fei, L.[Li],
Learning Temporal Embeddings for Complex Video Analysis,
ICCV15(4471-4479)
IEEE DOI 1602
Coherence BibRef

Ramanathan, V.[Vignesh], Li, C.C.[Cong-Cong], Deng, J.[Jia], Han, W.[Wei], Li, Z.[Zhen], Gu, K.[Kunlong], Song, Y.[Yang], Bengio, S.[Samy], Rossenberg, C.[Chuck], Fei-Fei, L.[Li],
Learning semantic relationships for better action retrieval in images,
CVPR15(1100-1109)
IEEE DOI 1510
BibRef

Khoshrou, S.[Samaneh], Cardoso, J.S.[Jaime S.], Granger, E.[Eric], Teixeira, L.F.[Luís F.],
Spatio-Temporal Fusion for Learning of Regions of Interests Over Multiple Video Streams,
ISVC15(II: 509-520).
Springer DOI 1601
BibRef
Earlier: A1, A2, A4, Only:
Active Learning from Video Streams in a Multi-camera Scenario,
ICPR14(1248-1253)
IEEE DOI 1412
Accuracy BibRef

Jhuo, I.H.[I-Hong], Lee, D.T.,
Video Event Detection via Multi-modality Deep Learning,
ICPR14(666-671)
IEEE DOI 1412
Event detection. Audio/video. BibRef

Wu, X.Q.[Xu-Qing], Shah, S.K.[Shishir K.],
Regularized Multi-view Multi-metric Learning for Action Recognition,
ICPR14(471-476)
IEEE DOI 1412
Cameras BibRef

Wu, Z.M.[Zi-Ming], Ng, W.W.Y.[Wing W.Y.],
Human action recognition using action bank and RBFNN trained by L-GEM,
ICWAPR14(30-35)
IEEE DOI 1402
Conferences BibRef

Sun, L.[Lin], Jia, K.[Kui], Chan, T.H.[Tsung-Han], Fang, Y.Q.[Yu-Qiang], Wang, G.[Gang], Yan, S.C.[Shui-Cheng],
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition,
CVPR14(2625-2632)
IEEE DOI 1409
action recognition; deep learning; slow feature analysis BibRef

Jones, S.[Simon], Shao, L.[Ling],
Unsupervised Spectral Dual Assignment Clustering of Human Actions in Context,
CVPR14(604-611)
IEEE DOI 1409
Human Action Analysis; Unsupervised Learning; Video Clustering BibRef

Chen, Y.B.[Yuan-Bo], Guo, X.[Xin],
Learning non-negative locality-constrained Linear Coding for human action recognition,
VCIP13(1-6)
IEEE DOI 1402
behavioural sciences computing BibRef

lo Presti, L.[Liliana], Sclaroff, S.[Stan], Rozga, A.,
Joint Alignment and Modeling of Correlated Behavior Streams,
SocialInter13(730-737)
IEEE DOI 1403
correlation methods BibRef

Cai, Q.[Qiao], Yin, Y.F.[Ya-Feng], Man, H.[Hong],
Learning spatio-temporal dependencies for action recognition,
ICIP13(3740-3744)
IEEE DOI 1402
Spatio-temporal dependencies; action recognition; self-organizing map BibRef

Zhou, W.[Wen], Wang, C.H.[Chun-Heng], Xiao, B.H.[Bai-Hua], Zhang, Z.[Zhong], Ma, L.[Long],
Learning weighted features for human action recognition,
ICPR12(1160-1163).
WWW Link. 1302
BibRef

Baccouche, M.[Moez], Mamalet, F.[Franck], Wolf, C.[Christian], Garcia, C.[Christophe], Baskurt, A.[Atilla],
Sparse shift-invariant representation of local 2D patterns and sequence learning for human action recognition,
ICPR12(3823-3826).
WWW Link. 1302
BibRef

Wolf, C.[Christian], Baskurt, A.[Atilla],
Action recognition in videos,
IPTA12(3-4)
IEEE DOI 1503
graph theory BibRef

Possegger, H.[Horst], Mauthner, T.[Thomas], Roth, P.M.[Peter M.], Bischof, H.[Horst],
Occlusion Geodesics for Online Multi-object Tracking,
CVPR14(1306-1313)
IEEE DOI 1409
Multi-Object Tracking;Occlusion Geodesics;Online Tracking BibRef

Mauthner, T.[Thomas], Roth, P.M.[Peter M.], Bischof, H.[Horst],
Learn to Move: Activity Specific Motion Models for Tracking by Detection,
ARTEMIS12(III: 183-192).
Springer DOI 1210
BibRef

Roth, P.M.[Peter M.], Mauthner, T.[Thomas], Khan, I.[Inayatullah], Bischof, H.[Horst],
Efficient human action recognition by cascaded linear classifcation,
ObjectEvent09(546-553).
IEEE DOI 0910
BibRef

Mauthner, T.[Thomas], Roth, P.M.[Peter M.], Bischof, H.[Horst],
Temporal Feature Weighting for Prototype-Based Action Recognition,
ACCV10(II: 566-579).
Springer DOI 1011
BibRef
Earlier:
Instant Action Recognition,
SCIA09(1-10).
Springer DOI 0906
BibRef

Ablavsky, V.[Vitaly], Sclaroff, S.[Stan],
Learning parameterized histogram kernels on the simplex manifold for image and action classification,
ICCV11(1473-1480).
IEEE DOI 1201
See also Layered Graphical Models for Tracking Partially Occluded Objects. BibRef

Liu, X.H.[Xiang-Hang], Zhang, J.[Jian],
Active learning for human action recognition with Gaussian Processes,
ICIP11(3253-3256).
IEEE DOI 1201
BibRef

Kovashka, A.[Adriana], Grauman, K.[Kristen],
Learning a hierarchy of discriminative space-time neighborhood features for human action recognition,
CVPR10(2046-2053).
IEEE DOI 1006
BibRef

Yao, B.[Benjamin], Zhu, S.C.[Song-Chun],
Learning deformable action templates from cluttered videos,
ICCV09(1507-1514).
IEEE DOI 0909
Sequence of image templates with shape and motion primitives (Gabor wavelets, and optical flow). BibRef

Xu, J.[Jie], Ye, G.[Getian], Wang, Y.[Yang], Wang, W.[Wei], Yang, J.[Jun],
Online Learning for PLSA-Based Visual Recognition,
ACCV10(II: 95-108).
Springer DOI 1011
BibRef

Xu, J.[Jie], Ye, G.[Getian], Wang, Y.[Yang], Herman, G.[Gunawan], Zhang, B.[Bang], Yang, J.[Jun],
Incremental EM for Probabilistic Latent Semantic Analysis on Human Action Recognition,
AVSBS09(55-60).
IEEE DOI 0909
BibRef

Connolly, C.I.[Christopher I.],
Learning to Recognize Complex Actions Using Conditional Random Fields,
ISVC07(II: 340-348).
Springer DOI 0711
BibRef

Jung, S.H.[Sang-Hack], Guo, Y.L.[Yan-Lin], Sawhney, H.S.[Harpreet S.], Kumar, R.T.[Rakesh T.],
Action exemplar based real-time action detection,
MLMotion09(498-505).
IEEE DOI 0910
BibRef
Earlier:
Multiple Cue Integrated Action Detection,
CVHCI07(108-117).
Springer DOI 0710
BibRef

Yang, C.J.[Chang-Jiang], Guo, Y.L.[Yan-Lin], Sawhney, H.S.[Harpreet S.], Kumar, R.T.[Rakesh T.],
Learning Actions Using Robust String Kernels,
HUMO07(313-327).
Springer DOI 0710
BibRef

Lee, C.,
Learning Reduced-Dimension Models of Human Actions,
CMU-RI-TR-00-17, May 2000. BibRef 0005 Ph.D.Thesis.
PDF File. 0102
BibRef

Bobick, A.F.[Aaron F.], Pentland, A.P.[Alex P.], Poggio, T.[Tommy],
VSAM at the MIT Media Laboratory and CBCL: Learning and Understanding Action in Video Imagery PI Report 1998,
DARPA98(85-91). BibRef 9800
And:
VSAM at the MIT Media laboratory and CBCL: Learning and Understanding Action in Video Imagery,
DARPA97(25-30). BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Egocentric Human Action Recognition, First Person, Wearable Monitoring .


Last update:Nov 18, 2017 at 20:56:18