16.7.3 Event Descriptions, Understanding Motion and Events

Chapter Contents (Back)
Event Understanding. Event Detection. General surveillance issues. See also Human Motion, General Analysis. See also Gesture Recognition Techniques.

Verificon,
2003.
Mann, R.[Richard], Jepson, A.D.[Allan D.], Siskind, J.M.,
The Computational Perception of Scene Dynamics,
CVIU(65), No. 2, February 1997, pp. 113-128. 9704

WWW Version. BibRef
Earlier: (Same title, no The) ECCV96(II:528-539).
Springer DOI Link BibRef

Siskind, J.M.[Jeffrey Mark],
Reconstructing force-dynamic models from video sequences,
AI(151), No. 1-2, December 2003, pp. 91-154.
WWW Version. 0401
BibRef

Mann, R.[Richard], Jepson, A.D.[Allan D.],
Towards the Computational Perception of Action,
CVPR98(794-799).
IEEE Abstract. IEEE Top Reference. BibRef 9800

Siskind, J.M., Morris, Q.,
A Maximum-Likelihood Approach to Visual Event Classification,
ECCV96(II:347-360).
Springer DOI Link Using real data, group into spatial events. BibRef 9600

Siskind, J.M.,
Visual Event Classification via Force Dynamics,
AAAI-00(149-155). BibRef 0001

Yacoob, Y.[Yaser], and Black, M.J.[Michael J.],
Parameterized Modeling and Recognition of Activities,
CVIU(73), No. 2, February 1999, pp. 232-247.
WWW Version.
HTML Version. BibRef 9902
Earlier: ICCV98(120-127).
IEEE DOI Link See also Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion. BibRef

Buxton, H., Walker, N.,
Query Based Visual Analysis: Spatio-Temporal Reasoning in Computer Vision,
IVC(6), No. 4, November 1988, pp. 247-254.
WWW Version. BibRef 8811

Duong, V., Buxton, H., Howarth, R.J., Toal, P., Gong, S., King, S., Thomere, J., Hyde, J.,
Spatio-Temporal Reasoning,
TRD203, Esprit Project 2152: Views, 1990. BibRef 9000

Johnson, N.[Neil], Hogg, D.C.[David C.],
Learning the Distribution of Object Trajectories for Event Recognition,
IVC(14), No. 8, August 1996, pp. 609-615.
WWW Version. 9609
BibRef
Earlier: BMVC95(xx-yy).
PDF Version. 9509
BibRef

Fernyhough, J.H., Cohn, A.G.[Anthony G.], Hogg, D.C.[David C.],
Constructing qualitative event models automatically from video input,
IVC(18), No. 2, January 2000, pp. 81-103.
WWW Version. 0001
BibRef
Earlier:
Building Qualitative Event Models Automatically from Visual Input,
ICCV98(350-355).
IEEE DOI Link BibRef
Earlier:
Generation of Semantic Regions from Image Sequences,
ECCV96(II:475-484).
Springer DOI Link Generate regions where an object has gone through. Uses tracking rather than differencing. BibRef

Buxton, H., Mukerjee, A.,
Conceptualizing Images,
IVC(18), No. 2, January 2000, pp. 79.
WWW Version. 0001
BibRef

Howarth, R.J.[Richard J.],
Interpreting a Dynamic and Uncertain World: Task-Based Control,
AI(100), No. 1-2, April 1998, pp. 5-86.
WWW Version. Activity at a traffic circle. Identify behaviors overtake, follow, give way. BibRef 9804

Howarth, R.J.,
Interpreting a Dynamic and Uncertain World: High-Level Vision,
AIR(9), No. 1, February 1995, pp. 37-63. BibRef 9502

Howarth, R.J., Buxton, H.,
Conceptual descriptions from monitoring and watching image sequences,
IVC(18), No. 2, January 2000, pp. 105-135.
WWW Version. 0001
BibRef
Earlier:
Visual Surveillance Monitoring and Watching,
ECCV96(II:321-334). BibRef
And:
Springer DOI Link
Attentional Control for Visual Surveillance,
VS98(Monitoring and Surveillance of Traffic Scenes). Monitor traffic pattern, determine the activities. BibRef

Buxton, H.[Hilary], Howarth, R.J.[Richard J.],
Watching Behaviour: The Role of Context and Learning,
ICIP96(II: 797-800).
IEEE DOI Link BibRef 9600

Howarth, R.J.[Richard J.],
Spatial Representation, Reasoning and Control for a Surveillance System,
Ph.D.Thesis, University of Londonn, July 1994. BibRef 9407

Buxton, H.[Hilary], Gong, S.G.[Shao-Gang],
Visual Surveillance in a Dynamic and Uncertain World,
AI(78), No. 1-2, October 1995, pp. 431-459.
WWW Version. Surveillance. BibRef 9510
Earlier:
Advanced Visual Surveillance Using Bayesian Networks,
Context95(xx) BibRef

Sun, R., Sessions, C.,
Self-Segmentation of Sequences: Automatic Formation of Hierarchies of Sequential Behaviors,
SMC-B(30), No. 3, June 2000, pp. 403-418.
IEEE Top Reference. 0006
BibRef

North, B.[Ben], Blake, A.[Andrew], Isard, M.[Michael], Rittscher, J.[Jens],
Learning and Classification of Complex Dynamics,
PAMI(22), No. 9, September 2000, pp. 1016-1034.
IEEE Abstract. IEEE Top Reference.
WWW Version. 0010
EM-K Expectation-Maximization based on Kalman Filtering. And EM-C Expectation-Maximization with Condensation. ( See also Statistical Models of Visual Shape and Motion. ) See also C-Conditional Density Propagation for Visual Tracking. BibRef

Medioni, G.[Gérard], Cohen, I.[Isaac], Brémond, F.[François], Hongeng, S.[Somboon], Nevatia, R.[Ramakant],
Event Detection and Analysis from Video Streams,
PAMI(23), No. 8, August 2001, pp. 873-889.
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 0108 USC Computer Vision 0109
BibRef
Earlier: A1, A5, A2 only: DARPA98(63-72).
PDF Version. Integration of motion detection and tracking with baehvior inference to handle noisy data and inaccurate detections. Selection from scenarios. BibRef

Hongeng, S.[Somboon], Nevatia, R.[Ram], Bremond, F.[Francois],
Video-based event recognition: activity representation and probabilistic recognition methods,
CVIU(96), No. 2, November 2004, pp. 129-162.
WWW Version. 0410
BibRef

Hongeng, S.[Somboon], Nevatia, R.[Ram],
Large-scale event detection using semi-hidden markov models,
ICCV03(1455-1462).
IEEE DOI Link 0311
BibRef
Earlier:
Multi-Agent Event Recognition,
ICCV01(II: 84-91).
IEEE DOI Link 0106
BibRef USC Computer VisionHierarchical decomposition into separate threads related by temporal constraints. BibRef

Hongeng, S.[Somboon], Brémond, F.[Francois], Nevatia, R.[Ramakant],
Bayesian Framework for Video Surveillance Application,

Representation and Optimal Recognition of Human Activities,
CVPR00(I: 818-825).
IEEE Abstract. IEEE Top Reference.
WWW Version. BibRef 0001 USC Computer Vision 0005
BibRef
And: ICPR00(Vol I: 164-170).
IEEE DOI Link BibRef USC Computer Vision
HTML Version. 0009
BibRef

Hongeng, S.,
Unsupervised Learning of Multi-Object Events,
BMVC04(xx-yy).
HTML Version. 0508
BibRef

Chella, A., Frixione, M., Gaglio, S.,
Understanding dynamic scenes,
AI(123), No. 1-2, October 2000, pp. 89-132. 0101

WWW Version. Integrating AI approach of describing actions and computer vision approach of describing 3d motions. BibRef

Zhao, R.[Rong], Grosky, W.I.,
Negotiating the semantic gap: from feature maps to semantic landscapes,
PR(35), No. 3, March 2002, pp. 593-600.
WWW Version. 0201
BibRef

Fan, J.P.[Jian-Ping], Elmagarmid, A.K.[Ahmed K.],
An automatic algorithm for semantic object generation and temporal tracking,
SP:IC(17), No. 2, February 2002, pp. 145-164.
WWW Version. 0201
BibRef

Johnson, N.[Neil], Hogg, D.C.[David C.],
Representation and synthesis of behaviour using Gaussian mixtures,
IVC(20), No. 12, October 2002, pp. 889-894.
WWW Version. 0210
BibRef

Keren, D.[Daniel],
Recognizing image 'style' and activities in video using local features and naive Bayes,
PRL(24), No. 16, December 2003, pp. 2913-2922.
WWW Version. 0310
BibRef

Osadchy, M.[Margarita], Keren, D.[Daniel],
A Rejection-Based Method for Event Detection in Video,
CirSysVideo(14), No. 4, April 2004, pp. 534-541.
IEEE Abstract. IEEE Top Reference. 0407
BibRef

Osadchy, M.[Margarita], Keren, D.[Daniel], Gal, Y.[Yaniv],
Anti-Sequences: Event Detection by Frame Stacking,
CVPR01(II:46-51).
IEEE Abstract. IEEE Top Reference. 0110
BibRef

Fablet, R., Bouthemy, P.,
Motion recognition using nonparametric image motion models estimated from temporal and multiscale co-occurrence statistics,
PAMI(25), No. 12, December 2003, pp. 1619-1624.
IEEE Abstract. IEEE Top Reference. 0401
BibRef
Earlier:
Non-Parametric Motion Recognition Using Temporal Multiscale Gibbs Models,
CVPR01(I:501-508).
IEEE Abstract. IEEE Top Reference. 0110
Statistical model of distributions of motion features. Recognize different motion types. BibRef

Ng, J.[Jeffrey], Gong, S.G.[Shao-Gang],
Learning Pixel-Wise Signal Energy for Understanding Semantics,
IVC(21), No. 12-13, December 2003, pp. 1183-1189.
WWW Version. 0401
BibRef
Earlier: BMVC01(Session 8: Modelling Behaviour).
HTML Version. Queen Mary, University of London 0110
BibRef

Laptev, I.[Ivan], Lindeberg, T.[Tony],
Velocity adaptation of spatio-temporal receptive fields for direct recognition of activities: an experimental study,
IVC(22), No. 2, 1 February 2004, pp. 105-116.
WWW Version. 0402
BibRef
Earlier:
Local Descriptors for Spatio-temporal Recognition,
SCVMA04(91-103).
Springer DOI Link 0405
BibRef
And:
Velocity adaptation of space-time interest points,
ICPR04(I: 52-56).
IEEE DOI Link 0409
BibRef
Earlier:
Space-time interest points,
ICCV03(432-439).
IEEE DOI Link 0311
BibRef

Lindeberg, T., Akbarzadeh, A., Laptev, I.,
Galilean-diagonalized spatio-temporal interest operators,
ICPR04(I: 57-62).
IEEE DOI Link 0409
BibRef

Lu, C.M.[Chun-Mei], Ferrier, N.J.[Nicola J.],
Repetitive motion analysis: segmentation and event classification,
PAMI(26), No. 2, February 2004, pp. 258-263.
IEEE Abstract. IEEE Top Reference. 0402
Analysis of repetitive motion to evaluate postural stress. BibRef

Lu, C.M.[Chun-Mei], Liu, H.Z.[Hai-Zhu], Ferrier, N.J.[Nicola J.],
Multidimensional Motion Segmentation and Identification,
CVPR00(II: 629-636).
IEEE Abstract. IEEE Top Reference.
WWW Version. 0005
Trajectory segmentation BibRef

Snidaro, L., Micheloni, C., Chiavedale, C.,
Video Security for Ambient Intelligence,
SMC-A(35), No. 1, January 2005, pp. 133-144.
IEEE Abstract. IEEE Top Reference. 0501
Parking lots. BibRef

Snidaro, L.[Lauro], Belluz, M.[Massimo], Foresti, G.L.[Gian Luca],
Representing and recognizing complex events in surveillance applications,
AVSBS07(493-498).
IEEE DOI Link 0709
BibRef

Goldenberg, R.[Roman], Kimmel, R.[Ron], Rivlin, E.[Ehud], Rudzsky, M.[Michael],
Behavior classification by eigendecomposition of periodic motions,
PR(38), No. 7, July 2005, pp. 1033-1043.
WWW Version. 0505
BibRef
Earlier:
'Dynamism of a Dog on a Leash' or Behavior Classification by Eigen-Decomposition of Periodic Motions,
ECCV02(I: 461 ff.).
HTML Version. 0205
BibRef

Amer, A.[Aishy], Dubois, E.[Eric], Mitiche, A.[Amar],
Rule-based real-time detection of context-independent events in video shots,
RealTimeImg(11), No. 3, June 2005, pp. 244-256.
WWW Version. 0508
BibRef

Makris, D., Ellis, T.,
Learning Semantic Scene Models From Observing Activity in Visual Surveillance,
SMC-B(35), No. 3, June 2005, pp. 397-408.
IEEE DOI Link 0508
BibRef
Earlier:
Automatic learning of an activity-based semantic scene model,
AVSBS03(183-188).
IEEE Abstract. IEEE Top Reference. 0310
BibRef
Earlier:
Spatial and Probabilistic Modelling of Pedestrian Behaviour,
BMVC02(Poster Session). 0208
BibRef

Pan, H.[Hao], van Beek, P.J.L.[Petrus J.L.],
Method for automatic extraction of semantically significant events from video,
US_Patent6,931,595, Aug 16, 2005
WWW Version. BibRef 0508

Lim, J.H.[Joo-Hwee], Jin, J.S.[Jesse S.],
Discovering Recurrent Image Semantics From Class Discrimination,
JASP(2006), No. Article ID 76093, 2006, pp. 1-11.
WWW Version. 0603
BibRef

Smith, P.[Paul], Shah, M.[Mubarak], da Vitoria Lobo, N.[Niels],
Integrating multiple levels of zoom to enable activity analysis,
CVIU(103), No. 1, July 2006, pp. 33-51.
WWW Version. 0606
BibRef
Earlier:
Integrating and employing multiple levels of zoom for activity recognition,
CVPR04(II: 928-935).
IEEE Abstract. IEEE Top Reference. 0408
Multiple cameras; Multiple zoom BibRef

Smith, P.[Paul], da Vitoria Lobo, N.[Niels], Shah, M.[Mubarak],
TemporalBoost for Event Recognition,
ICCV05(I: 733-740).
IEEE DOI Link 0510
BibRef

Zelnik-Manor, L.[Lihi], Irani, M.[Michal],
Statistical Analysis of Dynamic Actions,
PAMI(28), No. 9, September 2006, pp. 1530-1535.
IEEE DOI Link 0608
BibRef
Earlier:
Degeneracies, dependencies and their implications in multi-body and multi-sequence factorizations,
Weinland, D.[Daniel], Ronfard, R.[Remi], Boyer, E.[Edmond],
Free viewpoint action recognition using motion history volumes,
CVIU(103), No. 2-3, November-December 2006, pp. 249-257.
WWW Version. 0611
Dataset, Action Recognition.
WWW Version. BibRef
Earlier:
Automatic Discovery of Action Taxonomies from Multiple Views,
CVPR06(II: 1639-1645).
IEEE DOI Link 0606
Action recognition; View invariance; Volumetric reconstruction BibRef

Weinland, D.[Daniel], Boyer, E.[Edmond],
Action recognition using exemplar-based embedding,
CVPR08(1-7).
IEEE DOI Link 0806
BibRef

Weinland, D.[Daniel], Boyer, E.[Edmond], Ronfard, R.[Remi],
Action Recognition from Arbitrary Views using 3D Exemplars,
ICCV07(1-7).
IEEE DOI Link 0710
BibRef

Jiang, H.[Hao], Drew, M.S.[Mark S.], Li, Z.N.[Ze-Nian],
Matching by Linear Programming and Successive Convexification,
PAMI(29), No. 6, June 2007, pp. 959-975.
IEEE DOI Link 0704
BibRef
Earlier:
Successive Convex Matching for Action Detection,
CVPR06(II: 1646-1653).
IEEE DOI Link 0606
BibRef
And:
Convex Quadratic Programming for Object Localization,
ICPR06(III: 24-27).
WWW Version. 0609
BibRef
Earlier:
Linear Programming Matching and Appearance-Adaptive Object Tracking,
EMMCVPR05(203-219).
Springer DOI Link 0601
BibRef

Wang, Y.[Yang], Jiang, H.[Hao], Drew, M.S.[Mark S.], Li, Z.N.[Ze-Nian], Mori, G.[Greg],
Unsupervised Discovery of Action Classes,
CVPR06(II: 1654-1661).
IEEE DOI Link 0606
BibRef

Bashir, F.I., Khokhar, A.A., Schonfeld, D.,
Object Trajectory-Based Activity Classification and Recognition Using Hidden Markov Models,
IP(16), No. 7, July 2007, pp. 1912-1919.
IEEE DOI Link 0707
BibRef

Ma, X., Bashir, F.I., Khokhar, A.A., Schonfeld, D.,
Event Analysis Based on Multiple Interactive Motion Trajectories,
CirSysVideo(19), No. 3, March 2009, pp. 397-406.
IEEE DOI Link 0903
BibRef

Bashir, F.I., Qu, W.[Wei], Khokhar, A.A., Schonfeld, D.,
HMM-Based Motion Recognition System Using Segmented PCA,
ICIP05(III: 1288-1291).
IEEE DOI Link 0512
BibRef

Chen, X.[Xu], Schonfeld, D.[Dan], Khokhar, A.A.[Ashfaq A.],
Robust multi-dimensional Null Space representation for image retrieval and classification,
ICIP08(177-180).
IEEE DOI Link 0810
BibRef
And:
Robust null space representation and sampling for view-invariant motion trajectory analysis,
CVPR08(1-6).
IEEE DOI Link 0806
BibRef

Ma, X.[Xiang], Schonfeld, D.[Dan], Khokhar, A.A.[Ashfaq A.],
Video Event Classification and Image Segmentation Based on Noncausal Multidimensional Hidden Markov Models,
IP(18), No. 6, June 2009, pp. 1304-1313.
IEEE DOI Link 0905
BibRef
Earlier:
A General Two-Dimensional Hidden Markov Model and its Application in Image Classification,
ICIP07(VI: 41-44).
IEEE DOI Link 0709
BibRef

Veeraraghavan, A.[Ashok], Chellappa, R.[Rama], Srinivasan, M.[Mandyam],
Shape-and-Behavior Encoded Tracking of Bee Dances,
PAMI(30), No. 3, March 2008, pp. 463-476.
IEEE DOI Link 0801
Analyze behaviors. BibRef

Turaga, P.K.[Pavan K.], Veeraraghavan, A.[Ashok], Chellappa, R.[Rama],
Statistical analysis on Stiefel and Grassmann manifolds with applications in computer vision,
CVPR08(1-8).
IEEE DOI Link 0806
BibRef

Turaga, P.K.[Pavan K.], Chellappa, R.[Rama],
Learning action dictionaries from video,
ICIP08(1704-1707).
IEEE DOI Link 0810
BibRef

Turaga, P.K.[Pavan K.], Veeraraghavan, A.[Ashok], Chellappa, R.[Rama],
Unsupervised view and rate invariant clustering of video sequences,
CVIU(113), No. 3, March 2009, pp. 353-371.
Elsevier DOI Link
WWW Version. 0902
BibRef
Earlier:
From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems,
CVPR07(1-8).
IEEE DOI Link 0706
Video clustering; Summarization; Surveillance; Cascade of linear dynamical systems; View invariance; Affine invariance; Rate invariance BibRef

Veeraraghavan, A.[Ashok], Roy-Chowdhury, A.K.[Amit K.],
The Function Space of an Activity,
CVPR06(I: 959-968).
IEEE DOI Link 0606
BibRef

Sanmohan, Krüger, V.[Volker],
Primitive Based Action Representation and Recognition,
SCIA09(31-40).
Springer DOI Link 0906
BibRef

Kruger, V.,
Recognition of Action as a Bayesian Parameter Estimation Problem over Time,
HumMotBook08(3). 0802
BibRef

Lin, B.[Bin], Su, J.W.[Jian-Wen],
One Way Distance: For Shape Based Similarity Search of Moving Object Trajectories,
GeoInfo(12), No. 2, June 2008, pp. xx-yy.
Springer DOI Link 0804
BibRef

Wu, S.D.[Shan-Dong], Li, Y.F.,
Flexible signature descriptions for adaptive motion trajectory representation, perception and recognition,
PR(42), No. 1, January 2009, pp. 194-214.
WWW Version. 0809
Signature; Trajectory descriptor; Trajectory representation; Motion perception; Trajectory recognition; Robot vision BibRef

Wu, S.D.[Shan-Dong], Li, Y.F.,
Motion trajectory reproduction from generalized signature description,
PR(43), No. 1, January 2010, pp. 204-221,.
Elsevier DOI Link
WWW Version. 0909
Motion trajectory; Signature descriptor; Mutual description; Trajectory reproduction; Computer vision BibRef

Jacobs, N.[Nathan], Pless, R.[Robert],
Time Scales in Video Surveillance,
CirSysVideo(18), No. 8, August 2008, pp. 1106-1113.
IEEE DOI Link 0809
BibRef
Earlier:
Real-time constant memory visual summaries for surveillance,
VSSN06(155-160).
WWW Version. 0611
BibRef

Jacobs, N.[Nathan], Dixon, M.[Michael], Pless, R.[Robert],
Location-specific Transition Distributions for Tracking,
Motion08(1-6).
IEEE DOI Link 0801
BibRef

Wright, J.[John], Pless, R.[Robert],
Analysis of Persistent Motion Patterns Using the 3D Structure Tensor,
Motion05(II: 14-19).
WWW Version.
PDF Version. 0502
Capture the background model of motion and events for Surveillance. BibRef

Sohn, Y.W.[Young Wook], Kang, M.G.[Moon Gi],
Block-based recursive motion filtering for preserving true motion vectors in time-varying texture objects,
IJIST(18), No. 4, 2008, pp. 265-275.
WWW Version. 0810
BibRef
Earlier:
Block-Based Motion Vector Smoothing for Periodic Pattern Region,
ICIAR07(491-500).
Springer DOI Link 0708
multiple minima from periodic patterns. BibRef

Lin, L.[Liang], Gong, H.F.[Hai-Feng], Li, L.[Li], Wang, L.[Liang],
Semantic event representation and recognition using syntactic attribute graph grammar,
PRL(30), No. 2, 15 January 2009, pp. 180-186,.
Elsevier DOI Link
WWW Version. 0804
Visual surveillance; Event representation; Event recognition; Attribute graph grammar BibRef

Stauder, J.[Jürgen], Chupeau, B.[Bertrand], Oisel, L.[Lionel], Chevallier, L.[Louis],
Method for identification of tokens in video sequences,
US_Patent7,340,096, Mar 4, 2008
WWW Version. particular events or objects. BibRef 0803

Shyu, M.L.[Mei-Ling], Xie, Z.X.[Zong-Xing], Chen, M.[Min], Chen, S.C.[Shu-Ching],
Video Semantic Event/Concept Detection Using a Subspace-Based Multimedia Data Mining Framework,
MultMed(10), No. 2, February 2008, pp. 252-259.
IEEE DOI Link 0905
BibRef

Tseng, V.S., Su, J.H.[Ja-Hwung], Huang, J.H.[Jhih-Hong], Chen, C.J.[Chih-Jen],
Integrated Mining of Visual Features, Speech Features, and Frequent Patterns for Semantic Video Annotation,
MultMed(10), No. 2, February 2008, pp. 260-267.
IEEE DOI Link 0905
BibRef

Ziani, A.[Ahmed], Motamed, C.[Cina], Noyer, J.C.,
Temporal reasoning for scenario recognition in video-surveillance using Bayesian networks,
IET-CV(2), No. 2, June 2008, pp. 99-107.
WWW Version. 0905
BibRef
Earlier: A1, A2, Only:
Temporal Bayesian Networks for Scenario Recognition,
SCIA07(689-698).
Springer DOI Link 0706
BibRef

Bhargava, M.[Medha], Chen, C.C.[Chia-Chih], Ryoo, M.S., Aggarwal, J.K.,
Detection of object abandonment using temporal logic,
MVA(20), No. 5, July 2009, pp. xx-yy.
Springer DOI Link 0906
BibRef
Earlier:
Detection of abandoned objects in crowded environments,
AVSBS07(271-276).
IEEE DOI Link 0709
BibRef

Chang, J.W.[Jae-Woo], Um, J.H.[Jung-Ho],
A New Signature-Based Indexing Scheme for Efficient Trajectory Retrieval in Spatial Networks,
IEICE(E92-D), No. 6, June 2009, pp. 1240-1249.
WWW Version. 0907
BibRef

Li, N.[Ning], Xu, D.[De],
Action Recognition Using Visual-Neuron Feature,
IEICE(E92-D), No. 2, February 2009, pp. 361-364.
WWW Version. 0907
HVS (neural net) based approach. BibRef

Li, N.[Ning], Xu, D.[De],
2D Log-Gabor Wavelet Based Action Recognition,
IEICE(E92-D), No. 11, November 2009, pp. 2275-2278.
WWW Version. 0911
BibRef

Hsu, W.L., Hsiao, C.C., Chang, Y.L., Chen, T.L.,
Vision-based monitoring method using gray relational analysis,
IET-CV(3), No. 3, September 2009, pp. 103-111.
WWW Version. 0909
Room surveillance using cellular model. BibRef

Papadopoulos, G.T.[Georgios T.], Briassouli, A., Mezaris, V.[Vasileios], Kompatsiaris, I.[Ioannis], Strintzis, M.G.[Michael G.],
Statistical Motion Information Extraction and Representation for Semantic Video Analysis,
CirSysVideo(19), No. 10, October 2009, pp. 1513-1528.
IEEE DOI Link 0911
BibRef
Earlier: A1, A3, A4, A5:
Estimation and representation of accumulated motion characteristics for semantic event detection,
ICIP08(41-44).
IEEE DOI Link 0810
BibRef
And: A1, A3, A4, A5:
Accumulated motion energy fields estimation and representation for semantic event detection,
CIVR08(221-230). 0807
BibRef


Rimey, R., Keefe, D.,
Exploitation of massive numbers of simple events,
AIPR08(1-6).
IEEE DOI Link 0810
BibRef
And:
Temporal structure methods for image-based change analysis,
AIPR08(1-7).
IEEE DOI Link 0810
BibRef

Dudek, G.[Gregory], Lobos, J.P.[John-Paul],
Towards Navigation Summaries: Automated Production of a Synopsis of a Robot Trajectories,
CRV09(93-100).
IEEE DOI Link 0905
BibRef

Shao, L.[Ling], Ji, L.[Ling],
Motion Histogram Analysis Based Key Frame Extraction for Human Action/Activity Representation,
CRV09(88-92).
IEEE DOI Link 0905
BibRef

Farenzena, M.[Michela], Bazzani, L.[Loris], Murino, V.[Vittorio], Cristani, M.[Marco],
Towards a Subject-Centered Analysis for Automated Video Surveillance,
CIAP09(481-489).
Springer DOI Link 0909
Analyze from perspective of the actor, not camera. BibRef

Ko, T.[Teresa], Soatto, S.[Stefano], Estrin, D.[Deborah],
Categorization in natural time-varying image sequences,
VCL-ViSU09(53-60).
IEEE DOI Link 0906
Mult-view for categorization. BibRef

Briassouli, A.[Alexia], Matsiki, D.[Dimitra], Kompatsiaris, I.[Ioannis],
Wavelet domain processing for trajectory extraction,
ICIP08(1560-1563).
IEEE DOI Link 0810
BibRef

Otoom, A.F.[Ahmed Fawzi], Gunes, H.[Hatice], Piccardi, M.[Massimo],
Feature extraction techniques for abandoned object classification in video surveillance,
ICIP08(1368-1371).
IEEE DOI Link 0810
See also Maximum-likelihood dimensionality reduction in gaussian mixture models with an application to object classification. BibRef

Tian, Y.L.[Ying-Li], Feris, R.S.[Rogerio S.], Hampapur, A.[Arun],
Real-Time Detection of Abandoned and Removed Objects in Complex Environments,
VS08(xx-yy). 0810
BibRef

Li, J.[Jian], Gong, S.G.[Shao-Gang], Xiang, T.[Tao],
Scene Segmentation for Behaviour Correlation,
ECCV08(IV: 383-395).
Springer DOI Link 0810
BibRef

Jiang, H.[Hao], Martin, D.R.[David R.],
Finding Actions Using Shape Flows,
ECCV08(II: 278-292).
Springer DOI Link 0810
BibRef

Pogalin, E., Smeulders, A.W.M., Thean, A.H.C.,
Visual quasi-periodicity,
CVPR08(1-8).
IEEE DOI Link 0806
Detect and describe 10 types of periodicity. BibRef

Ding, T.[Tao], Sznaier, M.[Mario], Camps, O.I.[Octavia I.],
Fast track matching and event detection,
CVPR08(1-8).
IEEE DOI Link 0806
BibRef

Cao, L.L.[Liang-Liang], Luo, J.B.[Jie-Bo], Kautz, H.[Henry], Huang, T.S.[Thomas S.],
Annotating collections of photos using hierarchical event and scene models,
CVPR08(1-8).
IEEE DOI Link 0806
BibRef

Huebner, K.[Kai], Björkman, M.[Mĺrten], Rasolzadeh, B.[Babak], Schmidt, M.[Martina], Kragic, D.[Danica],
Integration of Visual and Shape Attributes for Object Action Complexes,
CVS08(xx-yy).
Springer DOI Link 0805
Objects and actions are intertwined. BibRef

Miezianko, R.[Roland], Pokrajac, D.[Dragoljub],
Localization of detected objects in multi-camera network,
ICIP08(2376-2379).
IEEE DOI Link 0810
BibRef

Miezianko, R.[Roland], Pokrajac, D.[Dragoljub],
Detecting and Recognizing Abandoned Objects in Crowded Environments,
CVS08(xx-yy).
Springer DOI Link 0805
BibRef

Senior, A.W., Brown, L., Hampapur, A., Shu, C.F., Zhai, Y., Feris, R.S., Tian, Y.L., Borger, S., Carlson, C.,
Video analytics for retail,
AVSBS07(423-428).
IEEE DOI Link 0709
BibRef

Leykin, A.[Alex], Tuceryan, M.[Mihran],
Detecting shopper groups in video sequences,
AVSBS07(417-422).
IEEE DOI Link 0709
BibRef

Zhang, Z.[Zhong], Scanlon, A.[Andrew], Yin, W.H.[Wei-Hong], Yu, L.[Li], Venetianer, P.L.[Peter L.],
Video Surveillance using a Multi-Camera Tracking and Fusion System,
M2SFA208(xx-yy). 0810
BibRef

Venetianer, P.L., Zhang, Z., Scanlon, A., Hu, Y., Lipton, A.J.,
Video verification of point of sale transactions,
AVSBS07(411-416).
IEEE DOI Link 0709
BibRef

Li, L.J.[Li-Jia], Li, F.F.[Fei-Fei],
What, where and who? Classifying events by scene and object recognition,
ICCV07(1-8).
IEEE DOI Link 0710
BibRef

Jhuang, H., Serre, T., Wolf, L., Poggio, T.,
A Biologically Inspired System for Action Recognition,
ICCV07(1-8).
IEEE DOI Link 0710
BibRef

Uchida, S.[Seiichi], Mori, A.[Akihiro], Kurazume, R.[Ryo], Taniguchi, R.I.[Rin-Ichiro], Hasegawa, T.[Tsutomu],
Logical DP Matching for Detecting Similar Subsequence,
ACCV07(I: 628-637).
Springer DOI Link 0711
Dynamic Programming. Similar gesturs. BibRef

Wei, Q.D.[Qing-Di], Hu, W.M.[Wei-Ming], Zhang, X.Q.[Xiao-Qin], Luo, G.[Guan],
Dominant Sets-Based Action Recognition using Image Sequence Matching,
ICIP07(VI: 133-136).
IEEE DOI Link 0709
BibRef

Yuk, J.S.C.[Jacky S.C.], Wong, K.Y.K.[Kwan-Yee K.], Chung, R.H.Y.[Ronald H.Y.], Chow, K.P., Chin, F.Y.L.[Francis Y.L.], Tsang, K.S.H.[Kenneth S.H.],
Object-Based Surveillance Video Retrieval System with Real-Time Indexing Methodology,
ICIAR07(626-637).
Springer DOI Link 0708
BibRef

Arbib, M.A.[Michael A.], Lee, J.Y.[Jin-Yong],
Vision and Action in the Language-Ready Brain: From Mirror Neurons to SemRep,
BVAI07(104-123).
Springer DOI Link 0710
BibRef

Gupta, A.[Abhinav], Davis, L.S.[Larry S.],
Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers,
ECCV08(I: 16-29).
Springer DOI Link 0810
BibRef
Earlier:
Objects in Action: An Approach for Combining Action Understanding and Object Perception,
CVPR07(1-8).
IEEE DOI Link 0706
BibRef

Kaiser, B.[Benedikt], Heidemann, G.[Gunther],
Qualitative analysis of spatio-temporal event detectors,
ICPR08(1-4).
IEEE DOI Link 0812
BibRef
And:
Context-Free Detection of Events,
SCIA07(223-232).
Springer DOI Link 0706
BibRef

Grest, D.[Daniel], Krüger, V.[Volker], Koch, R.[Reinhard],
Single View Motion Tracking by Depth and Silhouette Information,
SCIA07(719-729).
Springer DOI Link 0706
BibRef

Krüger, V.[Volker], Grest, D.[Daniel],
Using Hidden Markov Models for Recognizing Action Primitives in Complex Actions,
SCIA07(203-212).
Springer DOI Link 0706
BibRef

Krüger, V.[Volker],
Recognizing Action Primitives in Complex Actions Using Hidden Markov Models,
ISVC06(I: 538-547).
Springer DOI Link 0611
BibRef

Park, T.S.[Tae-Su], Lee, J.H.[Ju-Hong], Park, S.H.[Sang-Ho], Choi, B.[Bumghi], Kim, D.H.[Deok-Hwan],
Search Method of Time Sensitive Frequent Itemsets in Data Streams,
CIARP06(511-518).
Springer DOI Link 0611
Data mining. BibRef

Alahari, K.[Karteek], Jawahar, C.V.,
Dynamic Events as Mixtures of Spatial and Temporal Features,
ICCVGIP06(540-551).
Springer DOI Link 0612
BibRef

Alahari, K.[Karteek], Jawahar, C.V.,
Discriminative Actions for Recognising Events,
ICCVGIP06(552-563).
Springer DOI Link 0612
BibRef

Muncaster, J.[Justin], Ma, Y.Q.[Yun-Qian],
Activity Recognition using Dynamic Bayesian Networks with Automatic State Selection,
Motion07(30-30).
IEEE DOI Link 0702
BibRef

Ma, Y.Q.[Yun-Qian], Damelin, S.B., Masoud, O.T., Papanikolopoulos, N.P.,
Activity Recognition Via Classification Constrained Diffusion Maps,
ISVC06(I: 1-8).
Springer DOI Link 0611
BibRef

Ma, Y.Q.[Yun-Qian], Bazakos, M.[Mike], Miller, B.[Ben], Buddharaju, P.[Pradeep],
Activity Awareness: from Predefined Events to New Pattern Discovery,
CVS06(11).
IEEE DOI Link 0602
BibRef

Ma, Y.Q.[Yun-Qian], Buddharaju, P.[Pradeep], Bazakos, M.[Mike],
Pattern Discovery for Video Surveillance,
ISVC05(347-354).
Springer DOI Link 0512
BibRef

Ferrando, S., Gera, G., Massa, M., Regazzoni, C.,
A New Method for Real Time Abandoned Object Detection and Owner Tracking,
ICIP06(3329-3332). 0610

IEEE DOI Link BibRef

Dockstader, S.L.[Shiloh L.],
Motion Trajectory Classification for Visual Surveillance and Tracking,
AVSBS06(34-34).
IEEE DOI Link 0611
BibRef

Wang, T.[Tao], Li, J.G.[Jian-Guo], Diao, Q.[Qian], Hu, W.[Wei], Zhang, Y.M.[Yi-Min], Dulong, C.[Carole],
Semantic Event Detection using Conditional Random Fields,
SLAM06(109).
IEEE DOI Link 0609
BibRef

Altinok, A.[Alphan], El-Saban, M.[Motaz], Peck, A.J.[Austin J.], Wilson, L.[Leslie], Feinstein, S.C.[Stuart C.], Manjunath, B.S., Rose, K.[Kenneth],
Activity Analysis in Microtubule Videos by Mixture of Hidden Markov Models,
CVPR06(II: 1662-1669).
IEEE DOI Link 0606
BibRef

Jhala, S.[Sanjit], Lodha, S.K.[Suresh K.],
On-line Learning of Motion Patterns using an Expert Learning Framework,
LCV04(100).
IEEE DOI Link 0406
BibRef

Zhang, J.[Jain], Yang, Y.M.[Yi-Ming], Carbonell, J.[Jaime],
New Event Detection with Nearest Neighbor, Support Vector Machines, and Kernel Regression,
CMU-CS-TR-04-118.
HTML Version. 0501
BibRef

Mustafa, A., Sethi, I.,
Detecting retail events using moving edges,
AVSBS05(626-631).
IEEE DOI Link 0602
BibRef

Krahnstoever, N.O., Rittscher, J., Tu, P.H., Chean, K., Tomlinson, T.,
Activity Recognition using Visual Tracking and RFID,
WACV05(I: 494-500).
WWW Version. 0502
BibRef

Yu, L.[Li], Boult, T.E.[Terrance E.],
Understanding Images of Graphical User Interfaces: A New Approach to Activity Recognition for Visual Surveillance,
EventVideo04(113).
HTML Version. 0502
How to specify interesting activities. BibRef

Ghanem, N.M.[Nagia M.], Davis, L.S.[Larry S.],
Human Appearance Change Detection,
CIAP07(536-541).
IEEE DOI Link 0709
Changes in human appearance. I.e. with or without backpack, suitcase. BibRef

Ghanem, N.M.[Nagia M.], DeMenthon, D.F.[Daniel F.], Doermann, D.[David], Davis, L.S.[Larry S.],
Representation and Recognition of Events in Surveillance Video Using Petri Nets,
EventVideo04(112).
HTML Version. 0502
BibRef

Prange, J.D.,
Detecting, recognizing and understanding video events in surveillance video,
AVSBS03(4-4).
IEEE Abstract. IEEE Top Reference. 0310
BibRef

Kottow, D.[Daniel], Köppen, M.[Mario], Ruiz-del-Solar, J.[Javier],
Temporal Dynamical Interactions between Multiple Layers of Local Image Features for Event Detection in Video Sequences,
SCIA03(223-231).
WWW Version. 0310
BibRef

Ogris, G.[Georg], Paletta, L.[Lucas],
Predicting Detection Events from Bayesian Scene Recognition,
SCIA03(1058-1065).
WWW Version. 0310
BibRef

Peyrard, N., Bouthemy, P.,
Detection of meaningful events in videos based on a supervised classification approach,
ICIP03(III: 621-624).
IEEE Abstract. IEEE Top Reference. 0312
BibRef

Buzan, D., Sclaroff, S., Kollios, G.,
Extraction and clustering of motion trajectories in video,
ICPR04(II: 521-524).
IEEE DOI Link 0409
BibRef

Alon, J., Sclaroff, S., Kollios, G., Pavlovic, V.,
Discovering clusters in motion time-series data,
CVPR03(I: 375-381).
IEEE Abstract. IEEE Top Reference. 0307
Discover groupings of similar object motions. Allows each sequence to belong to more than a single HMM with some probability, and the hard decision about the sequence class membership can be deferred until a later time when such a decision is required. BibRef

Wu, Y.[Yi], Lin, C.K.[Ching-King], Chang, E.Y., Smith, J.R.,
Multimodal information fusion for video concept detection,
ICIP04(IV: 2391-2394).
IEEE DOI Link 0505
BibRef

Minnen, D., Essa, I.A., Starner, T.E.,
Expectation Grammars: Leveraging High-Level Expectations for Activity Recognition,
CVPR03(II: 626-632).
IEEE Abstract. IEEE Top Reference. 0307
BibRef

Syeda-Mahmood, T.F.,
Segmenting actions in velocity curve space,
ICPR02(IV: 170-175).
IEEE DOI Link 0211
BibRef

Natale, L.[Lorenzo], Rao, S.[Sajit], Sandini, G.[Giulio],
Learning to Act on Objects,
BMCV02(567 ff.).
HTML Version. 0303
BibRef

Ilg, W.[Winfried], Giese, M.[Martin],
Modeling of Movement Sequences Based on Hierarchical Spatial-Temporal Correspondence of Movement Primitives,
BMCV02(528 ff.).
HTML Version. 0303
BibRef

Diaz de Leon, R., Sucar, L.E.,
Continuous activity recognition with missing data,
ICPR02(I: 439-442).
IEEE DOI Link 0211
BibRef

Satoh, Y., Tanahashi, H., Wang, C.H.[Cai-Hua], Kaneko, S., Niwa, Y., Yamamoto, K.,
Robust event detection by radial reach filter (RRF),
ICPR02(II: 623-626).
IEEE DOI Link 0211
BibRef

Kawashima, H.[Hiroaki], Matsuyama, T.[Takashi],
Interval-Based Linear Hybrid Dynamical System for Modeling Cross-Media Timing Structures in Multimedia Signals,
CIAP07(789-794).
IEEE DOI Link 0709
BibRef
Earlier:
Integrated event recognition from multiple sources,
ICPR02(II: 785-789).
IEEE DOI Link 0211
BibRef

Xu, G.[Gu], Ma, Y.F.[Yu-Fei], Zhang, H.J.[Hong-Jiang], Yang, S.Q.A.[Shi-Qi-Ang],
Motion based event recognition using HMM,
ICPR02(II: 831-834).
IEEE DOI Link 0211
BibRef

Sun, X.D.[Xin-Ding], Manjunath, B.S., Divakaran, A.,
Representation of motion activity in hierarchical levels for video indexing and filtering,
ICIP02(I: 149-152).
IEEE Abstract. IEEE Top Reference. 0210
BibRef

Naphade, M.R., Huang, T.S.,
Discovering recurrent events in video using unsupervised methods,
ICIP02(II: 13-16).
IEEE Abstract. IEEE Top Reference. 0210
BibRef

Caelli, T.M.[Terry M.], McCabe, A.[Andrew], Binsted, G.[Gordon],
On Learning the Shape of Complex Actions,
VF01(24 ff.).
HTML Version. 0209
BibRef

Bischof, W.F.[Walter F.], Caelli, T.M.[Terry M.],
On the Learning of Complex Movement Sequences,
VF01(463 ff.).
HTML Version. 0209
BibRef

Piater, J.H., Richetto, S., Crowley, J.L.,
Event-based Activity Analysis in Live Video using a Generic Object Tracker,
PETS02(1-8). 0207
BibRef

Miller, E.[Erik], Tieu, K.[Kinh], Stauffer, C.[Chris],
Learning Object-Independent Modes of Variation with Feature Flow Fields,
MIT AIM-2001-021, September 2001.
WWW Version. 0205
BibRef

Vedula, S.,
Image Based Spatio-Temporal Modeling and View Interpolation of Dynamic Events,
CMU-RI-TR-01-37, September, 2001. BibRef 0109 Ph.D.Thesis.
PDF Version. 0205
BibRef

Vedula, S., Baker, S., Kanade, T.,
Spatio-Temporal View Interpolation,
CMU-RI-TR-01-35, September, 2001.
PDF Version.
Postscript Version. 0205
BibRef

Mittal, A.[Ankush], Cheong, L.F.[Loong Fah], and Sing, L.T.[Leung Tung],
Dynamic Bayesian Framework for Extracting Temporal Structure in Video,
CVPR01(II:110-115).
IEEE Abstract. IEEE Top Reference. 0110
Descriptors based on perceptual-level motion features such as time-to-collision, shot transition and temporal motion. BibRef

Remagnino, P., Jones, G.A.,
Classifying Surveillance Events from Attributes and Behaviour,
BMVC01(Session 8: Modelling Behaviour).
HTML Version. Kingston University 0110
BibRef

Rares, A., Reinders, M., Biemond, J.,
Complex Event Classification in Degraded Image Sequences,
ICIP01(I: 253-256).
IEEE Abstract. IEEE Top Reference. 0108
BibRef

Slaney, M., Ponceleon, D., Kaufman, J.,
Understanding the Semantics of Media,
VideoMining03(Chapter 8). BibRef 0300

Slaney, M.[Malcolm], Ponceleon, D.[Dulce], Kaufman, J.[James],
Temporal Events in All Dimensions and Scales,
EventVideo01(83-91).
IEEE DOI Link 0106
BibRef

Hoey, J.[Jesse],
Hierarchical unsupervised learning of facial expression categories,
EventVideo01(99-106).
IEEE DOI Link 0106
BibRef

Owens, J., Hunter, A.,
Application of the Self-Organizing Map to Trajectory Classification,
VS00(77-83). 0102
BibRef

Rui, Y.[Yong], Anandan, P.,
Segmenting Visual Actions based on Spatio-Temporal Motion Patterns,
CVPR00(I: 111-118).
IEEE Abstract. IEEE Top Reference.
WWW Version. 0005
BibRef

Mugurel, M.L., Venkatesh, S., West, G.A.W.,
On the Incremental Learning and Recognition of the Pattern of Movement of Multiple Labelled Objects in Dynamic Scenes,
ICPR00(Vol II: 652-655).
IEEE DOI Link
HTML Version. 0009
BibRef

Paletta, L.[Lucas], Prantl, M.[Manfred], Pinz, A.[Axel],
Learning Temporal Context in Active Object Recognition Using Bayesian Analysis,
ICPR00(Vol I: 695-699).
IEEE DOI Link
HTML Version. 0009
BibRef

Lomker, F.[Frank], Wrede, S.[Sebastian], Hanheide, M.[Marc], Fritsch, J.[Jannik],
Building Modular Vision Systems with a Graphical Plugin Environment,
CVS06(2).
IEEE DOI Link 0602
See also Integration and Coordination in a Cognitive Vision System. BibRef

Li, Z.[Zhe], Fritsch, J.[Jannik], Wachsmuth, S.[Sven], Sagerer, G.[Gerhard],
An Object-Oriented Approach Using a Top-Down and Bottom-Up Process for Manipulative Action Recognition,
DAGM06(212-221).
Springer DOI Link 0610
BibRef

Fritsch, J., Lomker, F., Wienecke, M., Sagerer, G.,
Detecting Assembly Actions by Scene Observation,
ICIP00(Vol I: 212-215).
IEEE Abstract. IEEE Top Reference. 0008
BibRef

Shotton, D.M., Rodríguez, A., Guil, N., Trelles, O.,
Object Tracking and Event Recognition in Biological Microscopy Videos,
ICPR00(Vol IV: 226-229).
IEEE DOI Link
HTML Version. 0009
BibRef

Davis, J.W.[James W.], Bobick, A.F.[Aaron F.], Richards, W.A.[Whitman A.],
Categorical Representation and Recognition of Oscillatory Motion Patterns,
CVPR00(I: 628-635).
IEEE Abstract. IEEE Top Reference.
WWW Version. 0005
BibRef

Babaguchi, N.[Noboru], Jain, R.C.[Ramesh C.],
Event Detection from Continuous Media,
ICPR98(Vol II: 1209-1212).
IEEE DOI Link 9808
BibRef

Uchibe, E.[Eiji], Asada, M.[Minoru], and Hosoda, K.[Koh],
State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action,
ICCV98(870-875).
IEEE DOI Link BibRef 9800

Fabiani, P.,
Dynamics of Beliefs and Strategy of Perception,
ECAI96(XX-YY). BibRef 9600

Rao, R.P.N.[Rajesh P.N.],
A Kalman Filter that Learns Robust Models of Dynamic Phenomena,
DARPA97(123-128). BibRef 9700

Olson, T.J.[Thomas J.], Brill, F.Z.[Frank Z.],
Moving Object Detection and Event Recognition Algorithms for Smart Camera,
DARPA97(159-176). BibRef 9700

Herzog, G.,
From Visual Input to Verbal Output in the Visual Translator,
TR124, Universitat Des Saarlandes, 1995. BibRef 9500

Shavit, E., Jepson, A.D.,
Motion Understanding from Qualitative Visual Dynamics,
WQV93(82-88). BibRef 9300

Okada, N.,
SUPP: Understanding Moving Picture Patterns Based on Linguistic Knowledge,
IJCAI79(690-692). BibRef 7900

Badler, N.I.,
Three-Dimensional Motion from Two-Dimensional Picture Sequences,
ICPR74(157-161). BibRef 7400

Badler, N.I.,
Temporal Scene Analysis: Conceptual Descriptions of Object Movements,
TorontoTR-80, February 1975, BibRef 7502 Ph.D.Thesis (CS). Event Understanding. Understand and describe events based on motion analysis. BibRef

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Event Models, Action Models, Motion Detection for Events, Backgrounds .


Last update:Nov 16, 2009 at 19:35:14