Abstract:
We describe a characterization of "visual action " that encodes local photometry via a choice of interest operators and global dynamics via a realization of a stochastic dynamical model. In order to allow detecting such actions in clutter, it is necessary for the corresponding models to have a compositional property, in that a simple action (e.g. foreground action) can be detected within a more complex one (e.g. foreground and background actions). We show that this is the case for the model we propose, which can therefore be used as a basis for building models of dynamic scenes from images without explicit supervision, by composing a complex action from a collection of elementary ones.
Citations
|
334
|
The robust estimation of multiple motions: Parametric and piecewise-smooth flow fields
– BLACK, ANANDA
- 1996
|
|
330
|
The visual analysis of human movement: A survey
– Gavrila
- 1999
|
|
283
|
Real-time american sign language recognition using desk and wearable computer based video
– Starner, Weaver, et al.
- 1998
|
|
221
|
Learning and Recognizing Human Dynamics in Video Sequences
– Bregler
- 1997
|
|
149
|
Unsupervised learning of models for recognition
– WEBER, WELLING, et al.
|
|
120
|
Adaptive probabilistic networks with hidden variables
– Binder, Koller, et al.
- 1997
|
|
111
|
Parameterized modeling and recognition of activities
– Yacoob, Black
- 1999
|
|
107
|
Recognition of visual activities and interactions by stochastic parsing
– Ivanov, Bobick
|
|
90
|
Facial expression recognition using a dynamic model and motion energy
– Essa, Pentland
- 1995
|
|
85
|
Parametric hidden markov models for gesture recognition
– Wilson, Bobick
- 1999
|
|
61
|
III, “Exploiting Human Actions and Object Context for Recognition Tasks
– Moore, Essa, et al.
- 1999
|
|
54
|
A probabilistic distance measure for hidden Markov models
– Juang, Rabiner
- 1985
|
|
39
|
Human Action Detection Using PNF Propagation of Temporal Constraints. CVPR
– Pinhanez, Bobick
- 1998
|
|
25
|
Parameter expansion for data augmentation
– Liu, Wu
- 1999
|
|
24
|
Representation and recognition of complex human motion
– Hoey, Little
- 2000
|
|
23
|
Explaining optical flow events with parameterized spatio-temporal models
– Black
- 1999
|
|
20
|
A Bayesian approach to human activity recognition
– Madabhushi, Aggarwal
- 1999
|
|
15
|
of organization in perceptual forms
– Laws
- 1939
|
|
14
|
Hidden Markov models: estimation and control
– Elliot, Aggoun, et al.
- 1995
|
|
10
|
Coupled hmm for complex action recognition
– Brand, Oliver, et al.
- 1997
|
|
10
|
et al. Classifying facial actions
– Donato
- 1999
|
|
9
|
Measuring shapes by size functions
– Frosini
- 1991
|
|
5
|
Visual recognition of multi agent action using binary temporal relations
– Intille, Bobick
- 1999
|
|
5
|
Frequency Tracking and Hidden Markov Models
– Karan
- 1995
|
|
5
|
The moments of matched and mismatched hidden markov models
– Streit
- 1990
|
|
5
|
Realtime online adaptive gesture recognition
– Wilson, Bobick
- 1999
|
|
