Continuous Relaxation and Local Maxima Selection: Conditions for Equivalence

Zucker, Steven W.; Leclerc, Yvan G.; Mohammed, John L.

doi:10.1109/tpami.1981.4767069

Cited by 40 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See Rosenfeld et al (1976), Zucker et al (1978Zucker et al ( , 1981, Hummel and Zucker (1983), Boyce et al (1985). We note also that in employing a free parameter there is a similarity with the author's ICM method.…”

Section: Discussion Of the Paper By Professor Besagmentioning

confidence: 99%

Statistical analysis of dirty pictures*

Besag

1993

Journal of Applied Statistics

1,381

2,134

View full text Add to dashboard Cite

Section: Discussion Of the Paper By Professor Besagmentioning

confidence: 99%

Statistical analysis of dirty pictures*

Besag

1993

Journal of Applied Statistics

1,381

2,134

View full text Add to dashboard Cite

“…While this paper aims at comparing two existing and popular kernels for local descriptors, it would be interesting to design new match kernels, based on matching heuristics that are commonly used for stereo image matching, such as [25,24,32]. The results shown in this paper should also be validated further, repeating the benckmark evaluation for several feature types, including space-time interest point detectors and descriptors [13].…”

Section: Discussionmentioning

confidence: 97%

A Performance Evaluation of Exact and Approximate Match Kernels for Object Recognition

Caputo¹,

Luo²

2010

ELCVIA

View full text Add to dashboard Cite

Local features have repeatedly shown their effectiveness for object recognition during the last years, and they have consequently become the preferred descriptor for this type of problems. The solution of the correspondence problem is traditionally approached with exact or approximate techniques. In this paper we are interested in methods that solve the correspondence problem via the definition of a kernel function that makes it possible to use local features as input to a support vector machine. We single out the match kernel, an exact approach, and the pyramid match kernel, that uses instead an approximate strategy. We present a thorough experimental evaluation of the two methods on three different databases. Results show that the exact method performs consistently better than the approximate one, especially for the object identification task, when training on a decreasing number of images. Based on these findings and on the computational cost of each approach, we suggest some criteria for choosing between the two kernels given the application at hand.

show abstract

“…This optimization problem is an NP hard problem [9]. However, several greedy algorithms like matching pursuit [8], Orthogonal Matching Pursuit (OMP) [8], etc.…”

Section: Sparse Representation Frameworkmentioning

confidence: 99%

Speaker Recognition Using Sparse Representation via Superimposed Features

Gaur

Madhavi

Patil

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we demonstrate the effectiveness of superimposed features for the purpose of template matching-based speaker recognition using sparse representations. The principle behind our hypothesis is, if the test template approximately lies in the linear span of the training templates of the genuine class, then so does any linear combination of test templates. In this paper, we introduce the notion of superimposed features for the first time. Using our initial trials on the TIMIT database, we have shown that superimposed features can result in reducing the complexity cost by 80 % with a very minor decrease in identification rate by 0.67 % and a minor increase in EER by 0.85 %.

show abstract

Continuous Relaxation and Local Maxima Selection: Conditions for Equivalence

Cited by 40 publications

References 11 publications

Statistical analysis of dirty pictures*

Statistical analysis of dirty pictures*

A Performance Evaluation of Exact and Approximate Match Kernels for Object Recognition

Speaker Recognition Using Sparse Representation via Superimposed Features

Contact Info

Product

Resources

About