17.1.3.7.21 Viewpoint invariant, View Invariant, Human Action Detection, Human Action Recognition

Chapter Contents (Back)
Action Detection. Human Actions. Human Motion.

Rao, C.[Cen], Yilmaz, A.[Alper], Shah, M.[Mubarak],
View-Invariant Representation and Recognition of Actions,
IJCV(50), No. 2, November 2002, pp. 203-226.
DOI Link Or:
PDF File. 0210

See also View-invariant alignment and matching of video sequences. BibRef

Yilmaz, A.[Alper], Shah, M.[Mubarak],
Matching actions in presence of camera motion,
CVIU(103), No. 2-3, November-December 2006, pp. 221-231.
Elsevier DOI 0611
BibRef
Earlier:
Recognizing Human Actions in Videos Acquired by Uncalibrated Moving Cameras,
ICCV05(I: 150-157).
IEEE DOI 0510
BibRef
Earlier:
Actions Sketch: A Novel Action Representation,
CVPR05(I: 984-989).
IEEE DOI 0507
Action recognition; Epipolar geometry; Video; Action retrieval; Moving camera BibRef

Yilmaz, A.[Alper], Shah, M.[Mubarak],
A differential geometric approach to representing the human actions,
CVIU(109), No. 3, March 2008, pp. 335-351.
Elsevier DOI 0802
Human Actions; Differential geometry; Epipolar geometry; Action representation; Action recognition BibRef

Rao, C.[Cen], Shah, M.[Mubarak],
View-Invariance in Action Recognition,
CVPR01(II:316-322).
IEEE DOI 0110
BibRef
And:
View-Invariant Representation and Learning of Human Action,
EventVideo01(55-63).
IEEE DOI 0106
BibRef

Parameswaran, V.[Vasu], Chellappa, R.[Rama],
Human action-recognition using mutual invariants,
CVIU(98), No. 2, May 2005, pp. 294-324.
Elsevier DOI 0501
BibRef

Parameswaran, V.[Vasu], Chellappa, R.[Rama],
View Invariance for Human Action Recognition,
IJCV(66), No. 1, January 2006, pp. 83-101.
Springer DOI 0601
BibRef
Earlier:
View invariants for human action recognition,
CVPR03(II: 613-619).
IEEE DOI 0307
BibRef
Earlier:
Quasi-invariants for human action representation and recognition,
ICPR02(I: 307-310).
IEEE DOI 0211
BibRef

Li, X.[Xi], Fukui, K.[Kazuhiro],
View Invariant Human Action Recognition Based on Factorization and HMMs,
IEICE(E91-D), No. 7, July 2008, pp. 1848-1854.
DOI Link 0807
BibRef

Souvenir, R.[Richard], Parrigan, K.[Kyle],
Viewpoint Manifolds for Action Recognition,
JIVP(2009), No. 2009, pp. xx-yy.
DOI Link 0911
BibRef

Parrigan, K.[Kyle], Souvenir, R.[Richard],
Aggregating Low-Level Features for Human Action Recognition,
ISVC10(I: 143-152).
Springer DOI 1011
BibRef

Souvenir, R.[Richard], Babbs, J.[Justin],
Learning the viewpoint manifold for action recognition,
CVPR08(1-7).
IEEE DOI 0806
BibRef

Suma, E.A.[Evan A.], Sinclair, C.W.[Christopher Walton], Babbs, J.[Justin], Souvenir, R.[Richard],
A Sketch-Based Approach for Detecting Common Human Actions,
ISVC08(I: 418-427).
Springer DOI 0812
BibRef

Huang, K.Q., Tao, D.C., Yuan, Y., Li, X.L., Tan, T.,
View-Independent Behavior Analysis,
SMC-B(39), No. 4, August 2009, pp. 1028-1035.
IEEE DOI 0906
Motion analysis of the human body is an important topic of research in computer vision devoted to detecting, tracking, and understanding people's physical behavior. BibRef

Shen, Y.P.[Yu-Ping], Foroosh, H.[Hassan],
View-Invariant Action Recognition from Point Triplets,
PAMI(31), No. 10, October 2009, pp. 1898-1905.
IEEE DOI 0909
BibRef
Earlier:
View-invariant action recognition using fundamental ratios,
CVPR08(1-6).
IEEE DOI 0806
Decompose body motion into rigid motion of planes defined by 3 points. Can easily measure similarity from this representation. BibRef

Boyraz, H.[Hakan], Masood, S.Z.[Syed Zain], Liu, B.Y.[Bao-Yuan], Tappen, M.[Marshall], Foroosh, H.[Hassan],
Action Recognition by Weakly-Supervised Discriminative Region Localization,
BMVC14(xx-yy).
HTML Version. 1410
BibRef

Sun, C.[Chuan], Junejo, I.N.[Imran N.], Foroosh, H.[Hassan],
Action recognition using rank-1 approximation of Joint Self-Similarity Volume,
ICCV11(1007-1012).
IEEE DOI 1201
BibRef

Ashraf, N.[Nazim], Foroosh, H.[Hassan],
Motion retrieval using consistency of epipolar geometry,
ICIP15(4219-4223)
IEEE DOI 1512
Animation BibRef

Ashraf, N.[Nazim], Sun, C.[Chuan], Foroosh, H.[Hassan],
Motion retrival using low-rank decomposition of Fundamental Ratios,
ICIP12(1905-1908).
IEEE DOI 1302
convert action sequences into compact representations of the action. Motion capture data. BibRef

Ashraf, N.[Nazim], Shen, Y.P.[Yu-Ping], Cao, X.C.[Xiao-Chun], Foroosh, H.[Hassan],
View invariant action recognition using weighted fundamental ratios,
CVIU(117), No. 6, June 2013, pp. 587-602.
Elsevier DOI 1304
View invariance; Pose transition; Action recognition; Action alignment; Fundamental ratios BibRef

Ashraf, N.[Nazim], Sun, C.[Chuan], Foroosh, H.[Hassan],
View invariant action recognition using projective depth,
CVIU(123), No. 1, 2014, pp. 41-52.
Elsevier DOI 1405
View invariance BibRef

Ashraf, N.[Nazim], Shen, Y.P.[Yu-Ping], Foroosh, H.[Hassan],
View-Invariant Action Recognition Using Rank Constraint,
ICPR10(3611-3614).
IEEE DOI 1008
BibRef
Earlier: A2, A1, A3:
Action recognition based on homography constraints,
ICPR08(1-4).
IEEE DOI 0812
BibRef

Pedersoli, M.[Marco], Gonzàlez, J.[Jordi], Bagdanov, A.D.[Andrew D.], Roca, F.X.[F. Xavier],
Efficient discriminative multiresolution cascade for real-time human detection applications,
PRL(32), No. 13, 1 October 2011, pp. 1581-1587.
Elsevier DOI 1109
Human detection; Object detection; Support Vector Machine BibRef

Pedersoli, M.[Marco], Gonzàlez, J.[Jordi], Hu, X.[Xu], Roca, F.X.[F. Xavier],
Toward Real-Time Pedestrian Detection Based on a Deformable Template Model,
ITS(15), No. 1, February 2014, pp. 355-364.
IEEE DOI 1403
driver information systems BibRef

Chakraborty, B.[Bhaskar], Rudovic, O.[Ognjen], Gonzalez, J.[Jordi],
View-invariant human-body detection with extension to human action recognition using component-wise HMM of body parts,
FG08(1-6).
IEEE DOI 0809
BibRef

Pedersoli, M.[Marco], Gonzàlez, J.[Jordi], Villanueva, J.J.[Juan José],
High-Speed Human Detection Using a Multiresolution Cascade of Histograms of Oriented Gradients,
IbPRIA09(48-55).
Springer DOI 0906
BibRef

Chakraborty, B.[Bhaskar], Pedersoli, M.[Marco], Gonzàlez, J.[Jordi],
View-Invariant Human Action Detection Using Component-Wise HMM of Body Parts,
AMDO08(xx-yy).
Springer DOI 0807
BibRef

Gong, W.J.[Wen-Juan], Bagdanov, A.D.[Andrew D.], Roca, F.X.[F. Xavier], Gonzàlez, J.[Jordi],
Automatic Key Pose Selection for 3D Human Action Recognition,
AMDO10(290-299).
Springer DOI 1007
BibRef

Chakraborty, B.[Bhaskar], Bagdanov, A.D.[Andrew D.], Gonzàlez, J.[Jordi],
Towards Real-Time Human Action Recognition,
IbPRIA09(425-432).
Springer DOI 0906
BibRef

Huang, K., Zhang, Y., Tan, T.,
A Discriminative Model of Motion and Cross Ratio for View-Invariant Action Recognition,
IP(21), No. 4, April 2012, pp. 2187-2197.
IEEE DOI 1204
BibRef

Liu, Y.[Yi], Qin, L.[Lei], Cheng, Z.W.[Zhong-Wei], Zhang, Y.H.[Yan-Hao], Zhang, W.G.[Wei-Gang], Huang, Q.M.[Qing-Ming],
Weakly supervised cross-view action recognition via sequential motion accumulation,
ICIP14(2383-2387)
IEEE DOI 1502
Accuracy BibRef

Zhu, F.[Fan], Shao, L.[Ling], Lin, M.X.[Ming-Xiu],
Multi-view action recognition using local similarity random forests and sensor fusion,
PRL(34), No. 1, 1 January 2013, pp. 20-24.
Elsevier DOI 1211
Local similarity; Random forests; Sensor fusion; Voting strategy; IXMAS; Action recognition BibRef

Zhu, F.[Fan], Shao, L.[Ling],
Weakly-Supervised Cross-Domain Dictionary Learning for Visual Recognition,
IJCV(109), No. 1-2, August 2014, pp. 42-59.
WWW Link. 1407
BibRef
Earlier:
Enhancing Action Recognition by Cross-Domain Dictionary Learning,
BMVC13(xx-yy).
DOI Link 1402
BibRef

Zhu, F.[Fan], Shao, L.[Ling], Fang, Y.,
Boosted Cross-Domain Dictionary Learning for Visual Categorization,
IEEE_Int_Sys(31), No. 3, May 2016, pp. 6-18.
IEEE DOI 1606
Classification BibRef

Zhang, J.T.[Jing-Tian], Shum, H.P.H.[Hubert P.H.], Han, J.G.[Jun-Gong], Shao, L.[Ling],
Action Recognition From Arbitrary Views Using Transferable Dictionary Learning,
IP(27), No. 10, October 2018, pp. 4709-4723.
IEEE DOI 1808
feature extraction, image classification, image coding, image representation, learning (artificial intelligence), transfer dictionary learning BibRef

Zhu, F.[Fan], Shao, L.[Ling],
Correspondence-Free Dictionary Learning for Cross-View Action Recognition,
ICPR14(4525-4530)
IEEE DOI 1412
Cameras BibRef

Zhu, F.[Fan], Jiang, Z.L.[Zhuo-Lin], Shao, L.[Ling],
Submodular Object Recognition,
CVPR14(2457-2464)
IEEE DOI 1409
CPMC;Object Recognition;Regression;Submodularity BibRef

Anwaar_ul-Haq, Gondal, I.[Iqbal], Murshed, M.[Manzur],
On Temporal Order Invariance for View-Invariant Action Recognition,
CirSysVideo(23), No. 2, February 2013, pp. 203-211.
IEEE DOI 1301
BibRef
Earlier:
Action Recognition Using Spatio-Temporal Distance Classifier Correlation Filter,
DICTA11(474-479).
IEEE DOI 1205
BibRef

ul-Haq, A.[Anwaar], Yin, X.X.[Xiao-Xia], Zhang, Y.C.[Yun-Chan], Gondal, I.[Iqbal],
Action-02MCF: A Robust Space-Time Correlation Filter for Action Recognition in Clutter and Adverse Lighting Conditions,
ACIVS16(465-476).
Springer DOI 1611
BibRef

Anwaar-ul-Haq, Gondal, I.[Iqbal], Murshed, M.[Manzur],
On dynamic scene geometry for view-invariant action matching,
CVPR11(3305-3312).
IEEE DOI 1106
BibRef
And: CVPR11(3369-3376).
IEEE DOI 1106
BibRef

Anwaar-ul-Haq, Gondal, I.[Iqbal], Murshed, M.[Manzur],
Contextual Action Recognition in Multi-sensor Nighttime Video Sequences,
DICTA11(256-261).
IEEE DOI 1205
BibRef

Kim, S.J.[Sun Jung], Kim, S.W.[Soo Wan], Sandhan, T.[Tushar], Choi, J.Y.[Jin Young],
View invariant action recognition using generalized 4D features,
PRL(49), No. 1, 2014, pp. 40-47.
Elsevier DOI 1410
Action recognition BibRef

Yan, Y.[Yan], Ricci, E.[Elisa], Subramanian, R.[Ramanathan], Liu, G.[Gaowen], Sebe, N.[Nicu],
Multitask Linear Discriminant Analysis for View Invariant Action Recognition,
IP(23), No. 12, December 2014, pp. 5599-5611.
IEEE DOI 1402
BibRef
Earlier: A1, A2, A4, A3, A5:
Clustered Multi-task Linear Discriminant Analysis for View Invariant Color-Depth Action Recognition,
ICPR14(3493-3498)
IEEE DOI 1412

See also Egocentric Daily Activity Recognition via Multitask Clustering. graph theory. Cameras BibRef

Yan, Y.[Yan], Liu, G.[Gaowen], Ricci, E.[Elisa], Sebe, N.[Nicu],
Multi-task linear discriminant analysis for multi-view action recognition,
ICIP13(2842-2846)
IEEE DOI 1402
Action Recognition BibRef

Wu, X.X.[Xin-Xiao], Wang, H.[Han], Liu, C.W.[Cui-Wei], Jia, Y.D.[Yun-De],
Cross-View Action Recognition Over Heterogeneous Feature Spaces,
IP(24), No. 11, November 2015, pp. 4096-4108.
IEEE DOI 1509
BibRef
Earlier: ICCV13(609-616)
IEEE DOI 1403
correlation theory. What you see vs. what you recognize in different view. BibRef

Liu, C.W.[Cui-Wei], Wu, X.X.[Xin-Xiao], Jia, Y.D.[Yun-De],
Transfer Latent SVM for Joint Recognition and Localization of Actions in Videos,
Cyber(46), No. 11, November 2016, pp. 2596-2608.
IEEE DOI 1609
BibRef
Earlier:
Weakly Supervised Action Recognition and Localization Using Web Images,
ACCV14(V: 642-657).
Springer DOI 1504
BibRef

Spurlock, S.[Scott], Souvenir, R.[Richard],
Dynamic view selection for multi-camera action recognition,
MVA(27), No. 1, January 2016, pp. 53-63.
WWW Link. 1601
BibRef
Earlier:
Pedestrian Verification for Multi-Camera Detection,
ACCV14(I: 322-334).
Springer DOI 1504
BibRef
And:
Multi-view action recognition one camera at a time,
WACV14(604-609)
IEEE DOI 1406
Accuracy; Azimuth; Cameras; Feature extraction; Silicon; Testing; Training BibRef

Spurlock, S.[Scott], Wu, H.[Hui], Souvenir, R.[Richard],
Multi-view Recognition Using Weighted View Selection,
ACCV14(IV: 538-552).
Springer DOI 1504
BibRef

Zheng, J.J.[Jing-Jing], Jiang, Z.L.[Zhuo-Lin], Chellappa, R.[Rama],
Cross-View Action Recognition via Transferable Dictionary Learning,
IP(25), No. 6, June 2016, pp. 2542-2556.
IEEE DOI 1605
BibRef
Earlier: A1, A2, Only:
Learning View-Invariant Sparse Representations for Cross-View Action Recognition,
ICCV13(3176-3183)
IEEE DOI 1403
image recognition. action recognition; dictionary learning BibRef

Zheng, J.J.[Jing-Jing], Jiang, Z.L.[Zhuo-Lin], Chellappa, R.[Rama],
Submodular Attribute Selection for Visual Recognition,
PAMI(39), No. 11, November 2017, pp. 2242-2255.
IEEE DOI 1710
selecting a subset of discriminative attributes from a large attribute set. Videos, Visualization, Attribute selection, entropy rate, maximum coverage function, submodular, optimization BibRef

Zheng, J.J.[Jing-Jing], Jiang, Z.L.[Zhuo-Lin], Phillips, J.[Jonathon], Chellappa, R.[Rama],
Cross-View Action Recognition via a Transferable Dictionary Pair,
BMVC12(125).
DOI Link 1301
BibRef

Wang, J.[Jing], Zheng, H.C.[Hui-Cheng], Gao, J.Y.[Jin-Yu], Cen, J.P.[Jie-Peng],
Cross-View Action Recognition Based on a Statistical Translation Framework,
CirSysVideo(26), No. 8, August 2016, pp. 1461-1475.
IEEE DOI 1609
feature extraction BibRef

Nie, W.Z.[Wei-Zhi], Liu, A.A.[An-An], Li, W.H.[Wen-Hui], Su, Y.T.[Yu-Ting],
Cross-view action recognition by cross-domain learning,
IVC(55, Part 2), No. 1, 2016, pp. 109-118.
Elsevier DOI 1612
Cross-domain BibRef

Liu, A.A.[An-An], Su, Y.T.[Yu-Ting], Nie, W.Z.[Wei-Zhi], Kankanhalli, M.[Mohan],
Hierarchical Clustering Multi-Task Learning for Joint Human Action Grouping and Recognition,
PAMI(39), No. 1, January 2017, pp. 102-114.
IEEE DOI 1612
Correlation
See also Multi-Domain and Multi-Task Learning for Human Action Recognition. BibRef

Kong, Y.[Yu], Ding, Z.M.[Zheng-Ming], Li, J.[Jun], Fu, Y.[Yun],
Deeply Learned View-Invariant Features for Cross-View Action Recognition,
IP(26), No. 6, June 2017, pp. 3028-3037.
IEEE DOI 1705
Cameras, Feature extraction, Magnetic sensors, Magnetometers, Robustness, Sensor phenomena and characterization, Action recognition, autoencoder, multi-view learning, view-invariant, features BibRef

Ji, Y.L.[Yan-Li], Yang, Y., Shen, F., Shen, H.T., Zheng, W.S.,
Arbitrary-View Human Action Recognition: A Varying-View RGB-D Action Dataset,
CirSysVideo(31), No. 1, January 2021, pp. 289-300.
IEEE DOI 2101
Dataset, Action Recognition. Skeleton, Sensors, Videos, Dictionaries, Robots, HRI BibRef

Ji, Y.L.[Yan-Li], Yang, Y.[Yang], Shen, H.T.[Heng Tao], Harada, T.[Tatsuya],
View-invariant action recognition via Unsupervised AttentioN Transfer (UANT),
PR(113), 2021, pp. 107807.
Elsevier DOI 2103
View-invariant recognition, Cross-view evaluation, Attention learning, Transfer learning BibRef

Gao, L.L.[Ling-Ling], Ji, Y.L.[Yan-Li], Gedamu, K.[Kumie], Zhu, X.F.[Xiao-Feng], Xu, X.[Xing], Shen, H.T.[Heng Tao],
View-Invariant Human Action Recognition Via View Transformation Network (VTN),
MultMed(24), 2022, pp. 4493-4503.
IEEE DOI 2212
Skeleton, Feature extraction, Computational modeling, Mathematical models, Transforms, Transformers, view transformation network (VTN) BibRef

Dai, R.[Rui], Das, S.[Srijan], Minciullo, L.[Luca], Garattoni, L.[Lorenzo], Francesca, G.[Gianpiero], Bremond, F.[François],
PDAN: Pyramid Dilated Attention Network for Action Detection,
WACV21(2969-2978)
IEEE DOI 2106
Handheld computers, Convolution, Focusing, Robustness, Task analysis BibRef

Liang, Z.X.[Zi-Xi], Yin, M.[Ming], Gao, J.L.[Jun-Li], He, Y.C.[Yi-Cheng], Huang, W.T.[Wei-Tian],
View knowledge transfer network for multi-view action recognition,
IVC(118), 2022, pp. 104357.
Elsevier DOI 2202
Action recognition, Deep learning, Multi-view learning, Generative adversarial network, Late fusion BibRef

Chen, J.Y.[Jian-Yu], Wang, Z.Y.[Zhong-Yuan], Zeng, K.L.[Kang-Li], He, Z.[Zheng], Xiong, Z.X.[Zi-Xiang],
Rethinking Lightweight: Multiple Angle Strategy for Efficient Video Action Recognition,
SPLetters(29), 2022, pp. 498-502.
IEEE DOI 2202
Spatiotemporal phenomena, Convolution, Feature extraction, Computational modeling, Solid modeling, video action recognition BibRef

Dave, I.[Ishan], Scheffer, Z.[Zacchaeus], Kumar, A.[Akash], Shiraz, S.[Sarah], Rawat, Y.S.[Yogesh Singh], Shah, M.[Mubarak],
GabriellaV2: Towards better generalization in surveillance videos for Action Detection,
Activity22(122-132)
IEEE DOI 2202
Training, Correlation, Conferences, Detectors, Streaming media, Video surveillance, Prediction algorithms BibRef

Zhang, C.K.[Cheng-Kun], Zheng, H.C.[Hui-Cheng], Lai, J.H.[Jian-Huang],
Cross-view Action Recognition via Dual-Codebook and Hierarchical Transfer Framework,
ACCV14(V: 579-592).
Springer DOI 1504
BibRef