Practical Generation of Video Textures using the Auto-Regressive Process

Campbell, Neill; Dalton, Colin J; Gibson, David; Thomas, Barry

doi:10.5244/c.16.41

Cited by 12 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, dynamic information has been intensively investigated in order to predict human behaviors or improve face recognition systems [1,5,7,12,19]. A number of studies assume that the facial moving patterns of individuals are predictive [5,7] so that regression based models can be built to capture the motion pattern.…”

Section: Relevant Workmentioning

confidence: 99%

“…A number of studies assume that the facial moving patterns of individuals are predictive [5,7] so that regression based models can be built to capture the motion pattern. Conversely, others assume that the motion is un-predictive even though some familiar behavioral patterns can be learned to represent the variations an individual makes.…”

Section: Relevant Workmentioning

confidence: 99%

“…The auto-regressive model [7,11,12] is a typical dynamic system for learning the moving patterns of individuals. The state vectors α t in the current frame can be approximated using a linear combination of several previous steps,…”

Section: Relevant Workmentioning

confidence: 99%

See 2 more Smart Citations

From Rank-N to Rank-1 Face Recognition Based on Motion Similarity

Fang

Costen

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

In this paper, we present a sequential framework using facial motion information as a subsidiary to improve face recognition performance. As is generally known, reasonable static face recognition has been achieved based on subspace reduction techniques. In order to further improve performance, some extra cues, such as temporal variation, are investigated by building dynamic models. We propose a permuted similarity motion feature and integrate it into a sequential recognition system. This system can select the best candidate from the Rank-N candidates picked up in the recognition step based on static appearance parameters by using motion information. The recognition rate of the motion similarity is compared with the motion feature obtained from auto-regressive models to prove its efficiency. In addition, the sequential system achieves better performance when the motion information is integrated with the static appearance information in a flexible manner.

show abstract

Section: Relevant Workmentioning

confidence: 99%

Section: Relevant Workmentioning

confidence: 99%

See 1 more Smart Citation

From Rank-N to Rank-1 Face Recognition Based on Motion Similarity

Fang

Costen

2009

Procedings of the British Machine Vision Conference 2009

View full text Add to dashboard Cite

show abstract

“…For textured motions or dynamic textures, people used numerous Markov models which are constrained to reproduce some statistics extracted from the input video. For example, dynamic textures [6,35] were modeled by a spatio-temporal autoregressive (STAR) model, in which the intensity of each pixel was represented by a linear summation of intensities of its spatial and temporal neighbors. Bouthemy et al [5] proposed mixed-state auto-models for motion textures by generalizing the auto-models in [3].…”

Section: Motivationmentioning

confidence: 99%

Video Primal Sketch: A Unified Middle-Level Representation for Video

2015

View full text Add to dashboard Cite

This paper presents a middle-level video representation named video primal sketch (VPS), which integrates two regimes of models: (i) sparse coding model using static or moving primitives to explicitly represent moving corners, lines, feature points, etc., (ii) FRAME /MRF model reproducing feature statistics extracted from input video to implicitly represent textured motion, such as water and fire. The feature statistics include histograms of spatio-temporal filters and velocity distributions. This paper makes three contributions to the literature: (i) Learning a dictionary of video primitives using parametric generative models; (ii) Proposing the spatio-temporal FRAME and motion-appearance FRAME models for modeling and synthesizing textured motion; and (iii) Developing a parsimonious hybrid model for generic video representation. Given an input video, VPS selects the proper models automatically for different motion patterns and is compatible with high-level action representations. In the experiments, we synthesize a number of textured motion; reconstruct real videos using the VPS; report a series of human perception experiments to verify the quality of reconstructed videos; demonstrate how the VPS changes over the

show abstract

“…In dynamic textures [13], also called temporal textures [14] or video textures [2], the existing generative models have been generally limited to using a linear dynamical system (LDS). Due to the large dimensionality of images, learning of dynamic textures is usually accomplished in two stages: principal component analysis (PCA) and autoregressive (AR) process, that is, finding observation matrix with noise model by PCA and estimating system matrix with noise model of an AR model.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Textures Synthesis as Nonlinear Manifold Learning and Traversing

Liu

Lin

Ahuja

et al. 2006

Procedings of the British Machine Vision Conference 2006

View full text Add to dashboard Cite

We formulate the problem of dynamic texture synthesis as a nonlinear manifold learning and traversing problem. We characterize dynamic textures as the temporal changes in spectral parameters of image sequences. For continuous changes of such parameters, it is commonly assumed that all these parameters lie on or close to a low-dimensional manifold embedded in the original configuration space. For complex dynamic data, the manifolds are usually nonlinear and we propose to use a mixture of linear subspaces to model a nonlinear manifold. These locally linear subspaces are further aligned within a global coordinate system. With the nonlinear manifold being globally parameterized, we overcome motion discontinuity problems encountered in switching linear models and dynamics. We present a nonparametric method to describe the complex dynamics of data sequences on the manifold. We also apply such approach to dynamic spatial parameters such as motion capture data. The experimental results suggest that our approach is able to synthesize smooth, complex dynamic textures and human motions, and has potential applications to other dynamic data synthesis problems.

show abstract

Practical Generation of Video Textures using the Auto-Regressive Process

Cited by 12 publications

References 10 publications

From Rank-N to Rank-1 Face Recognition Based on Motion Similarity

From Rank-N to Rank-1 Face Recognition Based on Motion Similarity

Video Primal Sketch: A Unified Middle-Level Representation for Video

Dynamic Textures Synthesis as Nonlinear Manifold Learning and Traversing

Contact Info

Product

Resources

About