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 …
A comprehensive taxonomy of dynamic texture representation
Representing dynamic textures (DTs) plays an important role in many real implementations
in the computer vision community. Due to the turbulent and non-directional motions of DTs …
in the computer vision community. Due to the turbulent and non-directional motions of DTs …
Robust fusion for RGB-D tracking using CNN features
Recently, RGB-D sensors have become popular. Many computer vision problems can be
better dealt with depth data. It is a challenging problem to integrate depth data into a visual …
better dealt with depth data. It is a challenging problem to integrate depth data into a visual …
A robust visual tracking method via local feature extraction and saliency detection
Y Wang, X Wei, L Ding, X Tang, H Zhang - The Visual Computer, 2020 - Springer
Visual object tracking is a fundamental problem in computer vision. It heavily relies on
feature description for the appearance of object. In this paper, we present a robust algorithm …
feature description for the appearance of object. In this paper, we present a robust algorithm …
CNN tracking based on data augmentation
Correlation filter based tracking methods have aroused increasing attention due to the
appealing performance on tracking benchmark datasets. For each frame, a filter is trained to …
appealing performance on tracking benchmark datasets. For each frame, a filter is trained to …
Hierarchical concept score postprocessing and concept-wise normalization in CNN-based video event recognition
M Soltanian, S Ghaemmaghami - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
This paper is focused on video event recognition based on frame level convolutional neural
network (CNN) descriptors. Using transfer learning, the image trained descriptors are …
network (CNN) descriptors. Using transfer learning, the image trained descriptors are …
New Robust PCA for Outliers and Heavy Sparse Noises' Detection via Affine Transformation, the L∗,w and L2,1 Norms, and Spatial Weight Matrix in High …
P Liang, HT Likassa, C Zhang… - International Journal of …, 2021 - Wiley Online Library
In this paper, we propose a novel robust algorithm for image recovery via affine
transformations, the weighted nuclear, L∗, w, and the L2, 1 norms. The new method …
transformations, the weighted nuclear, L∗, w, and the L2, 1 norms. The new method …
Dynamic texture classification using directional binarized random features
X Zhao, F Xu, Y Ma, Z Liu, M Deng, US Khan… - IEEE …, 2023 - ieeexplore.ieee.org
Dynamic texture description has been studied extensively due to its wide applications in the
field of computer vision. Local binary pattern (LBP) and its various variants account for a …
field of computer vision. Local binary pattern (LBP) and its various variants account for a …
Dynamic Texture Classification Using AutoEncoder-Based Local Features and Fisher Vector Encoding
Z Li, X Zhao, T Zhang, X Jing, W Shi, Q Chen - IEEE Access, 2024 - ieeexplore.ieee.org
Dynamic texture classification has been widely studied because of its applications in various
computer vision tasks. The key to classifying dynamic textures lies in describing them, ie …
computer vision tasks. The key to classifying dynamic textures lies in describing them, ie …
Battery-operated electric vehicles and plug-in hybrid electric vehicles
The crucial problem of precise state of charge (SOC) estimate for electric car batteries is at
the center of this chapter. This problem is made more difficult by the lengthy training times …
the center of this chapter. This problem is made more difficult by the lengthy training times …