Multi-channel correlation filters for human action recognition

Kiani, Hamed; Sim, Terence; Lucey, Simon

doi:10.1109/icip.2014.7025297

Cited by 14 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Partial-aliasing correlation filters were introduced to optimise the performance by producing sharper correlation peaks [30]. Efficacy of CPR has also been exploited for human action recognition in some recent studies [31][32][33][34][35][36], where these filters have shown quite promising results.…”

Section: Latest Trends In Cpr Filtersmentioning

confidence: 99%

Composite filtering strategy for improving distortion invariance in object recognition

Awan

Rehman

Bakhshi

2018

IET Image Processing

View full text Add to dashboard Cite

Section: Latest Trends In Cpr Filtersmentioning

confidence: 99%

Composite filtering strategy for improving distortion invariance in object recognition

Awan

Rehman

Bakhshi

2018

IET Image Processing

View full text Add to dashboard Cite

“…Due to their efficiency and reasonable detection time, channel features quickly became a reference. Over the years, many extensions were proposed, in terms of either speed [13] or performance [11,5,52,24,28,54]. In all these works, the response of one filter region is summarized with one value, by averaging or subtracting means.…”

Section: Introductionmentioning

confidence: 99%

“…On the other hand, individual filter responses would be more discriminative if characterized by more values. Moreover, since channel features were first introduced, heuristics [52,5,24,28] have been brought up to narrow down the filter search space. Therefore, in this paper, we propose to study the trade-off between these two factors and to show through the introduction of a new channel descriptor that several-valued filters can now reliably be extracted.…”

Section: Introductionmentioning

confidence: 99%

LBP Channels for Pedestrian Detection

Trichet

Brémond

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This paper introduces a new channel descriptor for pedestrian detection. This type of descriptor usually selects a set of one-valued filters within the enormous set of all possible filters for improved efficiency. The main claim underpinning this paper is that the recent works on channel-based features restrict the filter space search, therefore bringing along the obsolescence of one-valued filter representation. To prove our claim, we introduce a 12-valued filter representation based on local binary patterns. Indeed, various improvements now allow for this texture feature to provide a very discriminative, yet compact descriptor. Filter selection boasting new combination restrictions as well as a reverse selection process are also presented to choose the best filters. experiments on the INRIA and Caltech-USA datasets validate the approach.

show abstract

“…Moreover, the process of identifying an authentic correlation shape can be used to refine the correlation outputs after the initial matching for improved discrimination. There are a large number of CFs that have been developed [1,2,3,4,5] for image matching problems and have been previously shown to perform well in biometric recognition scenarios like face [6], iris [7], periocular [8], fingerprint [9], and palm print [10]. However, the matching challenge is noticeably more difficult when only a single image is available for the gallery template, e.g., as in real-world applications (such as when matching crime-scene face images to face images in surveillance videos) and in several NIST biometric competitions [11,12,13] designed to mimic such real world scenarios.…”

Section: Introductionmentioning

confidence: 99%

Stacked correlation filters for biometric verification

Smereka

Boddeti

Kumar

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Correlation filters (CFs) are a well-known pattern classification approach used in biometrics. A CF is a spatial-frequency array that is specifically synthesized from a set of training patterns to produce a sharp correlation output peak at the location of the best match for an authentic image comparison and no such peak for an impostor image comparison. The underlying premise when using CFs is that this correlation output peak behavior on training data ideally extends to testing data. Yet in 1 : 1 verification scenarios, where there is limited training data available to represent pattern distortions, the correlation output from an authentic comparison can be difficult to discern from the correlation output from an impostor. In this paper we introduce Stacked Correlation Filters (SCFs), a simple and powerful approach to address this problem by training an additional set of classifiers which learn to differentiate correlation outputs from authentic and impostor match pairs. This is done by training a series of stacked modular CFs with each layer refining the output of the previous layer. Our basic premise is that since correlation outputs have an expected shape, an additional CF can be trained to recognize such shape and refine the final output. As previous works with CFs have only focused on individual filter design or application, which assumes the CF to provide a sharp peak, this is a new CF paradigm that can benefit many existing CF designs and applications.

show abstract

Multi-channel correlation filters for human action recognition

Cited by 14 publications

References 20 publications

Composite filtering strategy for improving distortion invariance in object recognition

Composite filtering strategy for improving distortion invariance in object recognition

LBP Channels for Pedestrian Detection

Stacked correlation filters for biometric verification

Contact Info

Product

Resources

About