On the existence of complete invariant feature spaces in pattern recognition

Schulz-Mirbach, Hanns

doi:10.1109/icpr.1992.201749

Cited by 17 publications

(18 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has to be pointed out that this is an upper bound, and it was shown in many applications that the number of practically needed basis functions is considerably smaller [e.g., 41,43,45]. We can assume that the maximal translation that occurs as effect of VTL changes in the subband-index space is limited to a certain range W [46].…”

Section: Invariant-integration Featuresmentioning

confidence: 99%

Contextual invariant-integration features for improved speaker-independent speech recognition

Müller

Mertins

2011

Speech Communication

View full text Add to dashboard Cite

Section: Invariant-integration Featuresmentioning

confidence: 99%

Contextual invariant-integration features for improved speaker-independent speech recognition

Müller

Mertins

2011

Speech Communication

View full text Add to dashboard Cite

“…Furthermore, even if the issue of invariance can be addressed at the classifier level when using sparse classifiers, many of the desirable invariance properties that characterize a good human action recognition/event detection method should be obtained by means of the feature extraction process. We have shown how to use the invariant integration as described by Schulz-Mirbach (1992) to extract such features from the contour of the acting person.…”

Section: Discussion Conclusion and Summarymentioning

confidence: 99%

Sparse Representations and Invariant Sequence-Feature Extraction for Event Detection

Condurache¹,

Mertins

2012

Proceedings of the International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:We address the problem of detecting unusual actions performed by a human in a video. Broadly speaking, we achieve our goal by matching the observed action to a set of a-priori known actions. If the observed action can not be matched to any of the known actions (representing the normal case), we conclude that an event has taken place. In this contribution we will show how sparse representations of actions can be used for event detection. Our input data are video sequences showing different actions. Special care is taken to extract features from these sequences. The features are chosen such that the sparse-representations paradigm can be applied and they exhibit a set of invariance properties needed for detecting unusual human actions. We test our methods on sequences showing different people performing various actions such as walking or running.

show abstract

“…The choice of Γ in Eq. (46) ensures that the proportionality constant betweend and m 2 is independent of the volume. Hence, a straightforward dimensional analysis of Eq.…”

Section: Extracting T C and The Critical Exponentsmentioning

confidence: 99%

Machine Learning as a universal tool for quantitative investigations of phase transitions

2019

View full text Add to dashboard Cite

The problem of identifying the phase of a given system for a certain value of the temperature can be reformulated as a classification problem in Machine Learning. Taking as a prototype the Ising model and using the Support Vector Machine as a tool to classify Monte Carlo generated configurations, we show that the critical region of the system can be clearly identified and the symmetry that drives the transition can be reconstructed from the performance of the learning process. The role of the discrete symmetry of the system in obtaining this result is discussed. A finite size analysis of the learned Support Vector Machine decision function allows us to determine the critical temperature and critical exponents with a precision that is comparable to that of the most efficient numerical approaches relying on a known Hamiltonian description of the system. For the determination of the critical temperature and of the critical exponent connected with the divergence of the correlation length, other than the availability of a range of temperatures having information on both phases, the method we propose does not rest on any physical input on the system, and in particular is agnostic to its Hamiltonian, its symmetry properties and its order parameter. Hence, our investigation provides a first significant step in the direction of devising robust tools for quantitative analyses of phase transitions in cases in which an order parameter is not known.

show abstract

On the existence of complete invariant feature spaces in pattern recognition

Cited by 17 publications

References 2 publications

Contextual invariant-integration features for improved speaker-independent speech recognition

Contextual invariant-integration features for improved speaker-independent speech recognition

Sparse Representations and Invariant Sequence-Feature Extraction for Event Detection

Machine Learning as a universal tool for quantitative investigations of phase transitions

Contact Info

Product

Resources

About