A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision
Higher dimensional data such as video and 3D are the leading edge of multimedia retrieval
and computer vision research. In this survey, we give a comprehensive overview and key …
and computer vision research. In this survey, we give a comprehensive overview and key …
A review of recent methods for the determination of ranges of feasible solutions resulting from soft modelling analyses of multivariate data
A Golshan, H Abdollahi, S Beyramysoltan… - Analytica Chimica …, 2016 - Elsevier
Soft modelling or multivariate curve resolution (MCR) are well-known methodologies for the
analysis of multivariate data in many different application fields. Results obtained by soft …
analysis of multivariate data in many different application fields. Results obtained by soft …
Centerclip: Token clustering for efficient text-video retrieval
Recently, large-scale pre-training methods like CLIP have made great progress in multi-
modal research such as text-video retrieval. In CLIP, transformers are vital for modeling …
modal research such as text-video retrieval. In CLIP, transformers are vital for modeling …
Sign and basis invariant networks for spectral graph representation learning
We introduce SignNet and BasisNet--new neural architectures that are invariant to two key
symmetries displayed by eigenvectors:(i) sign flips, since if $ v $ is an eigenvector then so is …
symmetries displayed by eigenvectors:(i) sign flips, since if $ v $ is an eigenvector then so is …
SHOT: Unique signatures of histograms for surface and texture description
This paper presents a local 3D descriptor for surface matching dubbed SHOT. Our proposal
stems from a taxonomy of existing methods which highlights two major approaches, referred …
stems from a taxonomy of existing methods which highlights two major approaches, referred …
Rotational projection statistics for 3D local surface description and object recognition
Recognizing 3D objects in the presence of noise, varying mesh resolution, occlusion and
clutter is a very challenging task. This paper presents a novel method named Rotational …
clutter is a very challenging task. This paper presents a novel method named Rotational …
Unique signatures of histograms for local surface description
This paper deals with local 3D descriptors for surface matching. First, we categorize existing
methods into two classes: Signatures and Histograms. Then, by discussion and experiments …
methods into two classes: Signatures and Histograms. Then, by discussion and experiments …
[HTML][HTML] Faster permutation inference in brain imaging
Permutation tests are increasingly being used as a reliable method for inference in
neuroimaging analysis. However, they are computationally intensive. For small, non …
neuroimaging analysis. However, they are computationally intensive. For small, non …
The why and how of nonnegative matrix factorization
N Gillis - … , optimization, kernels, and support vector machines, 2014 - books.google.com
Nonnegative matrix factorization (NMF) has become a widely used tool for the analysis of
high-dimensional data as it automatically extracts sparse and meaningful features from a set …
high-dimensional data as it automatically extracts sparse and meaningful features from a set …
Unique shape context for 3D data description
The use of robust feature descriptors is now key for many 3D tasks such as 3D object
recognition and surface alignment. Many descriptors have been proposed in literature which …
recognition and surface alignment. Many descriptors have been proposed in literature which …