Results 41 to 50 of about 523,433 (260)
Saliency Detection Using Sparse and Nonlinear Feature Representation
The Scientific World Journal, 2014 An important aspect of visual saliency detection is how features that form an input image are represented. A popular theory supports sparse feature representation, an image being represented with a basis dictionary having sparse weighting coefficient ...
Shahzad Anwar +3 more
doaj +1 more source
Visual Tracking Based on Extreme Learning Machine and Sparse Representation
Sensors, 2015 The existing sparse representation-based visual trackers mostly suffer from both being time consuming and having poor robustness problems. To address these issues, a novel tracking method is presented via combining sparse representation and an emerging ...
Baoxian Wang +4 more
doaj +1 more source
Learning Joint Intensity-Depth Sparse Representations [PDF]
IEEE Transactions on Image Processing, 2014 This paper presents a method for learning overcomplete dictionaries composed of two modalities that describe a 3D scene: image intensity and scene depth. We propose a novel Joint Basis Pursuit (JBP) algorithm that finds related sparse features in two modalities using conic programming and integrate it into a two-step dictionary learning algorithm.
Tošić, Ivana, Drewes, Sarah
openaire +4 more sources
Mapping the evolution of mitochondrial complex I through structural variation
FEBS Letters, EarlyView.Respiratory complex I (CI) is crucial for bioenergetic metabolism in many prokaryotes and eukaryotes. It is composed of a conserved set of core subunits and additional accessory subunits that vary depending on the organism. Here, we categorize CI subunits from available structures to map the evolution of CI across eukaryotes. Respiratory complex I (CI)
Dong‐Woo Shin +2 more
wiley +1 more source
Subtype‐specific enhancer RNAs define transcriptional regulators and prognosis in breast cancers
Molecular Oncology, EarlyView.This study employed machine learning methodologies to perform the subtype‐specific classification of RNA‐seq data sets, which are mapped on enhancers from TCGA‐derived breast cancer patients. Their integration with gene expression (referred to as ProxCReAM eRNAs) and chromatin accessibility profiles has the potential to identify lineage‐specific and ...
Aamena Y. Patel +6 more
wiley +1 more source
Integrated Sparse Coding With Graph Learning for Robust Data Representation
IEEE Access, 2020 Sparse coding is a popular technique for achieving compact data representation and has been used in many applications. However, the instability issue often causes degeneration in practice and thus attracts a lot of studies.
Yupei Zhang, Shuhui Liu
doaj +1 more source
Hyperspectral Image Denoising via Nonlocal Spectral Sparse Subspace Representation
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023 Hyperspectral image (HSI) denoising based on nonlocal subspace representation has attracted a lot of attention recently. However, most of the existing works mainly focus on refining the representation coefficient images (RCIs) using certain nonlocal ...
Hailin Wang +5 more
doaj +1 more source
Group Sparse CNNs for Question Classification with Answer Sets
, 2017 Question classification is an important task with wide applications. However, traditional techniques treat questions as general sentences, ignoring the corresponding answer data.
Huang, Liang +3 more
core +1 more source
Molecular Oncology, EarlyView.Tumors contain diverse cellular states whose behavior is shaped by context‐dependent gene coordination. By comparing gene–gene relationships across biological contexts, we identify adaptive transcriptional modules that reorganize into distinct vulnerability axes.
Brian Nelson +9 more
wiley +1 more source
Multiscale Union Regions Adaptive Sparse Representation for Hyperspectral Image Classification
Remote Sensing, 2017 Sparse Representation has been widely applied to classification of hyperspectral images (HSIs). Besides spectral information, the spatial context in HSIs also plays an important role in the classification.
Fei Tong +3 more
doaj +1 more source