Remote sensing object detection (RSOD), one of the most fundamental and
...
Drones have been widely used in many areas of our daily lives. It reliev...
Hyperspectral image change detection (HSI-CD) has emerged as a crucial
r...
The knowledge distillation uses a high-performance teacher network to gu...
The network pruning algorithm based on evolutionary multi-objective (EMO...
To address the challenges of long-tailed classification, researchers hav...
General change detection (GCD) and semantic change detection (SCD) are c...
The construction of machine learning models involves many bi-level
multi...
Model bias triggered by long-tailed data has been widely studied. Howeve...
Weakly supervised object detection (WSOD) is a challenging task, in whic...
Influence maximization is a key issue for mining the deep information of...
Facial expression recognition (FER) is still one challenging research du...
Dynamic attention mechanism and global modeling ability make Transformer...
Recently, a massive number of deep learning based approaches have been
s...
Ship detection in aerial images remains an active yet challenging task d...
Existing anchor-base oriented object detection methods have achieved ama...
Sparse representation-based classification (SRC) has attracted much atte...
This report summarizes the results of Learning to Understand Aerial Imag...
Semantic segmentation has been continuously investigated in the last ten...
Outlier detection is one of the most important processes taken to create...
In this paper, we focus on the challenging multicategory instance
segmen...
By utilizing label distribution learning, a probability distribution is
...
Locating diseases in chest X-ray images with few careful annotations sav...
The training of deep neural networks (DNNs) always requires intensive
re...
We propose a balanced coarsening scheme for multilevel hypergraph
partit...
Feature alignment between domains is one of the mainstream methods for
U...
As an effective technique to achieve the implementation of deep neural
n...
Model quantization can reduce the model size and computational latency, ...
Since model quantization helps to reduce the model size and computation
...
Deep neural networks (DNNs) are playing key roles in various artificial
...
Identifying and locating diseases in chest X-rays are very challenging, ...
Small objects are difficult to detect because of their low resolution an...
Recently, many Convolution Neural Networks (CNN) have been successfully
...
We can consider Counterfactuals as belonging in the domain of Discourse
...
In synthetic aperture radar (SAR) image change detection, it is quite
ch...
Polarimetric SAR data has the characteristics of all-weather, all-time a...
In this paper, we propose a feature-aware correlation filter (FACF) for
...
In this paper, we propose a hierarchical feature-aware tracking framewor...
In this paper, we propose a new first-order gradient-based algorithm to ...
Object detection is one of the most important and challenging branches o...
The log-ratio (LR) operator has been widely employed to generate the
dif...
Change detection is a quite challenging task due to the imbalance betwee...
POLSAR image has an advantage over optical image because it can be acqui...
Exploiting rich spatial and spectral features contributes to improve the...
Polarimetric synthetic aperture radar (PolSAR) images are widely used in...
The training of deep neural networks (DNNs) requires intensive resources...
Existing polarimetric synthetic aperture radar (PolSAR) image classifica...
Global average pooling (GAP) allows to localize discriminative informati...
This paper proposes an accelerated proximal stochastic variance reduced
...
Due to the limited amount and imbalanced classes of labeled training dat...