16.7.4.5.1 Inference, Learning Human Actions, Human Activities, Human Behavior

Stauffer, C.[Chris], Grimson, W.E.L.[W. Eric L.],
Learning Patterns of Activity Using Real-Time Tracking,
PAMI(22), No. 8, August 2000, pp. 747-757.
IEEE Abstract. IEEE Top Reference.
WWW Version. 0010Using the 24 hour data from tracking motion, learn the different patterns, especially to see things that don't fit. Motion segmentation uses adaptive background subtraction with an updated model. Objects are not recognized, but identity is maintained throught the track. BibRef

Stauffer, C.[Chris],
Automated Audio-visual Activity Analysis,
CSAIL-2005-057, September 2005.
WWW Version. BibRef 0509

Brand, M.[Matthew], Kettnaker, V.M.[Vera M.],
Discovery and Segmentation of Activities in Video,
PAMI(22), No. 8, August 2000, pp. 844-851.
IEEE Abstract. IEEE Top Reference.
WWW Version. 0010HMM to organize activity into meaningful states. Infer body orientation and pose from low resolution silhouettes. BibRef

Kettnaker, V.M.[Vera M.], Brand, M.[Matthew],
Minimum-entropy models of scene activity,
CVPR99(I: 281-286).
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 9900

Brand, M.[Matthew],
Discovering and Visualizing Narrative Themes,
Visual97(xx). BibRef 9700

Brand, M.[Matthew],
Understanding Manipulation in Video,
AFGR96(94-99).
WWW Version. 9610
Postscript Version. BibRef
And: Vismod--404, 1996. BibRef

Galata, A.[Aphrodite], Johnson, N.[Neil], Hogg, D.C.[David C.],
Learning Variable-Length Markov Models of Behavior,
CVIU(81), No. 3, March 2001, pp. 398-413.
WWW Version. 0001 BibRef
Earlier:
Learning Structured Behavior Models using Variable Length Markov Models,
MPeople99(xx-yy). BibRef
And:
Learning Behaviour Models of Human Activities,
BMVC99(Modelling Human Behaviour). BibRef
Earlier: A2, A1, A3:
The Acquisition and Use of Interaction Behaviour Models,
CVPR98(866-871).
IEEE Abstract. IEEE Top Reference. BibRef

Hu, W., Xie, D., Tan, T.N., Maybank, S.J.,
Learning Activity Patterns Using Fuzzy Self-Organizing Neural Network,
SMC-B(34), No. 3, June 2004, pp. 1618-1626.
IEEE Abstract. IEEE Top Reference. 0407 BibRef

Hu, W.M.[Wei-Ming], Xie, D.[Dan], Fu, Z.Y.[Zhou-Yu], Zeng, W.[Wenrong], Maybank, S.J.[Steve J.],
Semantic-Based Surveillance Video Retrieval,
IP(16), No. 4, April 2007, pp. 1168-1181.
WWW Version. 0704 BibRef

Oliver, N.[Nuria], Garg, A.[Ashutosh], Horvitz, E.[Eric],
Layered representations for learning and inferring office activity from multiple sensory channels,
CVIU(96), No. 2, November 2004, pp. 163-180.
WWW Version. 0410 BibRef

Jiang, S.[ShengYi], Song, X.[Xiaoyu], Wang, H.[Hui], Han, J.J.[Jian-Jun], Li, Q.H.[Qing-Hua],
A clustering-based method for unsupervised intrusion detections,
PRL(27), No. 7, May 2006, pp. 802-810.
WWW Version. Clustering; Threshold; Outlier factor; Intrusion detection 0604 BibRef

Davis, J.W.[James W.], Tyagi, A.[Ambrish],
Minimal-latency human action recognition using reliable-inference,
IVC(24), No. 5, 1 May 2006, pp. 455-472.
WWW Version. 0606 BibRef
Earlier:
A reliable-inference framework for recognition of human actions,
AVSBS03(169-176).
IEEE Abstract. IEEE Top Reference. 0310Action recognition; Reliable-inference; MAP; Video analysis Determine shortest video sequence, and extend if confusing or unreliable. BibRef

Gueguen, L.[Lionel], Datcu, M.[Mihai],
Image Time-Series Data Mining Based on the Information-Bottleneck Principle,
GeoRS(45), No. 4, April 2007, pp. 827-838.
WWW Version. 0704 BibRef

Shechtman, E.[Eli], Irani, M.[Michal],
Space-Time Behavior-Based Correlation - OR - How to Tell If Two Underlying Motion Fields Are Similar Without Computing Them?,
PAMI(29), No. 11, November 2007, pp. 2045-2056.
WWW Version. 0711 BibRef
Earlier:
Space-Time Behavior Based Correlation,
CVPR05(I: 405-412).
WWW Version. 0507Do the space-time patterns arise from the same motion. Detect complex patterns, dance, running water, etc. BibRef

Gorelick, L.[Lena], Blank, M.[Moshe], Shechtman, E.[Eli], Irani, M.[Michal], Basri, R.[Ronen],
Actions as Space-Time Shapes,
PAMI(29), No. 12, December 2007, pp. 2247-2253.
WWW Version. 0711 Dataset, Actions.
HTML Version. BibRef
Earlier: A2, A1, A3, A4, A5: ICCV05(II: 1395-1402).
WWW Version. 0510Human action as 3-D shapes induced by silhouettes in the spacetime volume. BibRef

Gudmundsson, J.[Joachim], van Kreveld, M.[Marc], Speckmann, B.[Bettina],
Efficient Detection of Patterns in 2D Trajectories of Moving Points,
GeoInfo(11), No. 2, June 2007, pp. 195-215.
WWW Version. 0709 BibRef

Mokhber, A.[Arash], Achard, C.[Catherine], Milgram, M.[Maurice],
Recognition of human behavior by space-time silhouette characterization,
PRL(29), No. 1, 1 January 2008, pp. 81-89.
WWW Version. 0711Behavior recognition; Action recognition; Motion analysis BibRef

Achard, C.[Catherine], Qu, X.T.[Xing-Tai], Mokhber, A.[Arash], Milgram, M.[Maurice],
A novel approach for recognition of human actions with semi-global features,
MVA(19), No. 1, January 2008, pp. 27-34.
WWW Version. 0801 BibRef
Earlier:
Action Recognition with Semi-global Characteristics and Hidden Markov Models,
ACIVS07(274-284).
WWW Version. 0708 BibRef
Earlier: A3, A1, A4, A2:
Combined Classifiers for Action Recognition,
IWICPAS06(27-34).
WWW Version. 0608 BibRef
Earlier: A3, A1, A2, A4:
Action Recognition with Global Features,
CVHCI05(110).
WWW Version. 0601 BibRef

Oh, S.M.[Sang Min], Rehg, J.M.[James M.], Balch, T.[Tucker], Dellaert, F.[Frank],
Learning and Inferring Motion Patterns using Parametric Segmental Switching Linear Dynamic Systems,
IJCV(77), No. 1-3, May 2008, pp. 103-124.
WWW Version. 0803 BibRef
Earlier:
Learning and Inference in Parametric Switching Linear Dynamical Systems,
ICCV05(II: 1161-1168).
WWW Version. 0510 BibRef
And:
Parameterized Duration Mmodeling for Switching Linear Dynamic Systems,
CVPR06(II: 1694-1700).
WWW Version. 0606Bee dances. for learning parameterized motions. BibRef

Xie, L., Sundaram, H., Campbell, M.,
Event Mining in Multimedia Streams,
PIEEE(96), No. 4, April 2008, pp. 623-647.
WWW Version. 0804 BibRef

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

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

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

Li, H.P.[He-Ping], Hu, Z.Y.[Zhan-Yi], Wu, Y.H.[Yi-Hong], Wu, F.C.[Fu-Chao],
MAPACo-Training: A Novel Online Learning Algorithm of Behavior Models,
ACCV07(I: 472-481).
WWW Version. 0711 BibRef

Jung, S.H.[Sang-Hack], Guo, Y.L.[Yan-Lin], Sawhney, H.S.[Harpreet S.], Kumar, R.T.[Rakesh T.],
Multiple Cue Integrated Action Detection,
CVHCI07(108-117).
WWW Version. 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).
WWW Version. 0710 BibRef

Nascimento, J.C.[Jacinto C.], Figueiredo, M.A.T.[Mario A. T.], Marques, J.S.[Jorge S.],
Semi-Supervised Learning of Switched Dynamical Models for Classification of Human Activities in Surveillance Applications,
ICIP07(III: 197-200).
WWW Version. 0709 BibRef

Wong, S.F.[Shu-Fai], Cipolla, R.[Roberto],
Extracting Spatiotemporal Interest Points using Global Information,
ICCV07(1-8).
WWW Version. 0710 BibRef

Wong, S.F.[Shu-Fai], Kim, T.K.[Tae-Kyun], Cipolla, R.[Roberto],
Learning Motion Categories using both Semantic and Structural Information,
CVPR07(1-6).
WWW Version. 0706Human actions, expressions, gestures. BibRef

Gui, L.[Laura], Thiran, J.P.[Jean-Philippe], Paragios, N.[Nikos],
A Variational Framework for the Simultaneous Segmentation and Object Behavior Classification of Image Sequences,
SSVM07(652-664).
WWW Version. 0705 BibRef
And:
Joint Object Segmentation and Behavior Classification in Image Sequences,
CVPR07(1-8).
WWW Version. 0706 BibRef

Meessen, J.[Jerome], Desurmont, X.[Xavier], Delaigle, J.F.[Jean-Francois], De Vleeschouwer, C.[Christophe], Macq, B.[Benoit],
Progressive Learning for Interactive Surveillance Scenes Retrieval,
VS07(1-8).
WWW Version. 0706 BibRef

Veeraraghavan, H.[Harini], Papanikolopoulos, N.[Nikolaos], Schrater, P.[Paul],
Learning Dynamic Event Descriptions in Image Sequences,
CVPR07(1-6).
WWW Version. 0706 BibRef

Zhang, Z.[Zhang], Huang, K.Q.[Kai-Qi], Tan, T.N.[Tie-Niu], Wang, L.S.[Liang-Sheng],
Trajectory Series Analysis based Event Rule Induction for Visual Surveillance,
CVPR07(1-8).
WWW Version. 0706 BibRef

Wang, X.G.[Xiao-Gang], Ma, X.X.[Xiao-Xu], Grimson, W.E.L.[W. Eric L.],
Unsupervised Activity Perception by Hierarchical Bayesian Models,
CVPR07(1-8).
WWW Version. 0706 BibRef

Natarajan, P., Nevatia, R.,
Coupled Hidden Semi Markov Models for Activity Recognition,
Motion07(10-10).
WWW Version. 0702 BibRef

Lee, J.Y.[Jae Young], Hoff, W.[William],
Activity Identification Utilizing Data Mining Techniques,
Motion07(12-12).
WWW Version. 0702 BibRef

Naftel, A., Anwar, F.B.[Fahad Bin],
Visual Recognition of Manual Tasks Using Object Motion Trajectories,
AVSBS06(69-69).
WWW Version. 0611 BibRef

Khalid, S.[Shehzad], Naftel, A.[Andrew],
Classifying spatiotemporal object trajectories using unsupervised learning of basis function coefficients,
VSSN05(45-52).
WWW Version. 0511 BibRef

Wang, H.B.[Hong-Bin], Miller, P., Culverhouse, P.F.,
Discovering the Local Co-occurring Patterns in Visual Categorization,
AVSBS06(6-6).
WWW Version. 0611 BibRef

Cho, K.[Kyungeun], Cho, H.[Hyungje], Um, K.[Kyhyun],
Inferring Stochastic Regular Grammar with Nearness Information for Human Action Recognition,
ICIAR06(II: 193-204).
WWW Version. 0610 BibRef

Brdiczka, O.[Oliver], Yuen, P.C.[Pong C.], Zaidenberg, S.[Sofia], Reignier, P.[Patrick], Crowley, J.L.[James L.],
Automatic Acquisition of Context Models and its Application to Video Surveillance,
ICPR06(I: 1175-1178).
WWW Version. 0609 BibRef

Bauer, D.[Dietmar], Brandle, N.[Norbert], Seer, S.[Stefan], Pflugfelder, R.[Roman],
Finding Highly Frequented Paths in Video Sequences,
ICPR06(I: 387-391).
WWW Version. 0609 BibRef

Guha, P.[Prithwijit], Mukerjee, A.[Amitabha], Venkatesh, K.S.,
Spatio-temporal Discovery: Appearance + Behavior = Agent,
ICCVGIP06(516-527).
WWW Version. 0612 BibRef

Guha, P.[Prithwijit], Mukerjee, A.[Amitabha], Venkatesh, K.S., Mitra, P.[Pabitra],
Activity Discovery from Surveillance Videos,
ICPR06(I: 433-436).
WWW Version. 0609 BibRef

Ogata, T.[Takehito], Christmas, W.J.[William J.], Kittler, J.V.[Josef V.], Ishikawa, S.[Seiji],
Improving human activity detection by combining multi-dimensional motion descriptors with boosting,
ICPR06(I: 295-298).
WWW Version. 0609 BibRef

Lublinerman, R.[Roberto], Ozay, N.[Necmiye], Zarpalas, D.[Dimitrios], Camps, O.I.[Octavia I.],
Activity Recognition from Silhouettes using Linear Systems and Model (In)validation Techniques,
ICPR06(I: 347-350).
WWW Version. 0609 BibRef

Toshev, A.[Alexander], Bremond, F.[Francois], Thonnat, M.[Monique],
An APRIORI-based Method for Frequent Composite Event Discovery in Videos,
CVS06(10).
WWW Version. 0602 BibRef

Moënne-Loccoz, N.[Nicolas], Brémond, F.[François], Thonnat, M.[Monique],
Recurrent Bayesian Network for the Recognition of Human Behaviors from Video,
CVS03(68 ff).
HTML Version. 0306 BibRef

Vu, V.T.[Van-Thinh], Brémond, F.[François], Thonnat, M.[Monique],
Automatic Video Interpretation: A Recognition Algorithm for Temporal Scenarios Based on Pre-compiled Scenario Models,
CVS03(523 ff).
HTML Version. 0306 BibRef
And:
Automatic Video Interpretation: A Novel Algorithm for Temporal Scenario Recognition,
IJCAI03(xx-yy). Joint Conference on Artificial Intelligence, Acapulco, Mexico, 9-15 August 2003 BibRef
Earlier:
Human Behaviour Visualisation and Simulation for Automatic Video Understanding,
WSCG02(485).
PDF Version.
HTML Version. 0209Specify the characters involved in a scenario, the sub-scenarios and the constraints combining the sub-scenarios. BibRef

Zhang, Z.[Zhang], Huang, K.Q.[Kai-Qi], Tan, T.N.[Tie-Niu],
Comparison of Similarity Measures for Trajectory Clustering in Outdoor Surveillance Scenes,
ICPR06(III: 1135-1138).
WWW Version. 0609 BibRef

Zhang, Z.[Zhang], Huang, K.Q.[Kai-Qi], Tan, T.N.[Tie-Niu],
Complex Activity Representation and Recognition by Extended Stochastic Grammar,
ACCV06(I:150-159).
WWW Version. 0601 BibRef

Xin, L.[Lun], Tan, T.N.[Tie-Niu],
Semi-supervised Learning on Semantic Manifold for Event Analysis in Dynamic Scenes,
VS07(1-8).
WWW Version. 0706 BibRef

Xin, L.[Lun], Tan, T.N.[Tie-Niu],
From Motion Patterns to Visual Concepts for Event Analysis in Dynamic Scenes,
ACCV06(I:826-835).
WWW Version. 0601 BibRef
Earlier:
Ontology-based hierarchical conceptual model for semantic representation of events in dynamic scenes,
PETS05(57-64).
WWW Version. 0602 BibRef

Shimoide, A.[Alan], Yoon, I.[Ilmi], Fuse, M.[Megumi], Beale, H.C.[Holly C.], Singh, R.[Rahul],
Automated Behavioral Phenotype Detection and Analysis Using Color-Based Motion Tracking,
CRV05(370-377).
WWW Version. 0505 BibRef

Lv, F.[Fengjun], Nevatia, R.[Ramakant],
Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching,
CVPR07(1-8).
WWW Version. 0706 BibRef
Earlier:
Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost,
ECCV06(IV: 359-372).
WWW Version. 0608 BibRef

Lv, F.[Fengjun], Nevatia, R.[Ramakant], Lee, M.W.[Mun Wai],
3D Human Action Recognition Using Spatio-temporal Motion Templates,
CVHCI05(120).
WWW Version. 0601 BibRef

Laskov, P.[Pavel], Düssel, P.[Patrick], Schäfer, C.[Christin], Rieck, K.[Konrad],
Learning Intrusion Detection: Supervised or Unsupervised?,
CIAP05(50-57).
WWW Version. 0509 BibRef

Pla, F.[Filiberto], Ribeiro, P.[Pedro], Santos-Victor, J.[José], Bernardino, A.[Alexandre],
Extracting Motion Features for Visual Human Activity Representation,
IbPRIA05(I:537).
WWW Version. 0509 BibRef

Pierobon, M., Marcon, M., Sarti, A., Tubaro, S.,
Clustering of human actions using invariant body shape descriptor and dynamic time warping,
AVSBS05(22-27).
WWW Version. 0602 BibRef

Jung, S.H.[Sang-Hack], Bajcsy, R.[Ruzena],
Learning Physical Activities in Immersive Virtual Environments,
CVS06(5).
WWW Version. 0602 BibRef

Nguyen, N.T.[Nam T.], Phung, D.Q.[Dinh Q.], Venkatesh, S.[Svetha], Bui, H.[Hung],
Learning and Detecting Activities from Movement Trajectories Using the Hierarchical Hidden Markov Models,
CVPR05(II: 955-960).
WWW Version. 0507 BibRef

Nguyen, N.T., Venkatesh, S.,
Discovery of Activity Structures using the Hierarchical Hidden Markov Model,
BMVC05(xx-yy).
HTML Version. 0509 BibRef

Nguyen, N.T., Bui, H.H., Venkatesh, S., West, G.A.W.,
Recognising and monitoring high-level behaviours in complex spatial environments,
CVPR03(II: 620-625).
IEEE Abstract. IEEE Top Reference. 0307 BibRef

Nguyen, N.T., Venkatesh, S., West, G.A.W., Bui, H.H.,
Hierarchical monitoring of people's behaviors in complex environments using multiple cameras,
ICPR02(I: 13-16).
WWW Version. 0211 BibRef

Duong, T.V.[Thi V.], Phung, D.Q.[Dinh Q.], Bui, H.H.[Hung H.], Venkatesh, S.[Svetha],
Human Behavior Recognition with Generic Exponential Family Duration Modeling in the Hidden Semi-Markov Model,
ICPR06(III: 202-207).
WWW Version. 0609 BibRef
Earlier: A1, A3, A2, A4:
Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model,
CVPR05(I: 838-845).
WWW Version. 0507 BibRef

Ikizler, N.[Nazli], Forsyth, D.A.[David A.],
Searching Video for Complex Activities with Finite State Models,
CVPR07(1-8).
WWW Version. 0706 BibRef

Yan, W.[Wei], Forsyth, D.A.,
Learning the Behavior of Users in a Public Space through Video Tracking,
WACV05(I: 370-377).
WWW Version. 0502 BibRef

Ren, J.P., Orwell, J., Jones, G.A.,
Learning Surveillance Tracking Models for the Self-Calibrated Ground Plane,
BMVC02(Poster Session). 0208 BibRef

Wechsler, H., Duric, Z., Li, F.Y.[Fa-Yin],
Hierarchical interpretation of human activities using competitive learning,
ICPR02(II: 338-341).
WWW Version. 0211 BibRef

Menendez, J., Velastin, S.A.,
A Method for Obtaining Neural Network Training Sets in Video Sequences,
VS00(xx-yy). 0102 BibRef

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

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Human Activities, Drowning, Underwater .