A survey of geometric optimization for deep learning: from Euclidean space to Riemannian manifold
Deep Learning (DL) has achieved remarkable success in tackling complex Artificial
Intelligence tasks. The standard training of neural networks employs backpropagation to …
Intelligence tasks. The standard training of neural networks employs backpropagation to …
Scene recognition by manifold regularized deep learning architecture
Scene recognition is an important problem in the field of computer vision, because it helps to
narrow the gap between the computer and the human beings on scene understanding …
narrow the gap between the computer and the human beings on scene understanding …
Probabilistic elastic matching for pose variant face verification
Pose variation remains to be a major challenge for realworld face recognition. We approach
this problem through a probabilistic elastic matching method. We take a part based …
this problem through a probabilistic elastic matching method. We take a part based …
Semi-supervised multitask learning for scene recognition
Scene recognition has been widely studied to understand visual information from the level of
objects and their relationships. Toward scene recognition, many methods have been …
objects and their relationships. Toward scene recognition, many methods have been …
Object bank: An object-level image representation for high-level visual recognition
It is a remarkable fact that images are related to objects constituting them. In this paper, we
propose to represent images by using objects appearing in them. We introduce the novel …
propose to represent images by using objects appearing in them. We introduce the novel …
Automatic one-hand gesture (mudra) identification in bharatanatyam using eigenmudra projections and convolutional neural networks
G Vadakkot, K Ramesh… - Journal of Electronic …, 2023 - spiedigitallibrary.org
Mudras in traditional Indian dance forms convey meaningful information when performed by
an artist. The subtle changes between the different mudras in a dance form render automatic …
an artist. The subtle changes between the different mudras in a dance form render automatic …
Learning object-to-class kernels for scene classification
High-level image representations have drawn increasing attention in visual recognition, eg,
scene classification, since the invention of the object bank. The object bank represents an …
scene classification, since the invention of the object bank. The object bank represents an …
BFO meets HOG: feature extraction based on histograms of oriented pdf gradients for image classification
T Kobayashi - Proceedings of the IEEE Conference on Computer …, 2013 - cv-foundation.org
Image classification methods have been significantly developed in the last decade. Most
methods stem from bagof-features (BoF) approach and it is recently extended to a vector …
methods stem from bagof-features (BoF) approach and it is recently extended to a vector …
Adaptive image denoising by mixture adaptation
We propose an adaptive learning procedure to learn patch-based image priors for image
denoising. The new algorithm, called the expectation-maximization (EM) adaptation, takes a …
denoising. The new algorithm, called the expectation-maximization (EM) adaptation, takes a …
Pedestrian detection for transformer substation based on gaussian mixture model and YOLO
Q Peng, W Luo, G Hong, M Feng, Y Xia… - … on intelligent human …, 2016 - ieeexplore.ieee.org
Safety is a core requirement of the transformer substation where is dangerous due to high
voltage. It requires to detect pedestrians efficiently based on the surveillance video near the …
voltage. It requires to detect pedestrians efficiently based on the surveillance video near the …