Novel Categories Discovery (NCD) tackles the open-world problem of
class...
Novel Categories Discovery (NCD) facilitates learning from a partially
a...
To effectively interrogate UAV-based images for detecting objects of
int...
We present a Momentum Re-identification (MoReID) framework that can leve...
A pretrain-finetune strategy is widely used to reduce the overfitting th...
In this paper, we propose a novel and highly practical score-level fusio...
Recently, self-supervised learning has attracted attention due to its
re...
We present a novel event recognition approach called Spatially-preserved...
We address two questions for training a convolutional neural network (CN...
Currently, accurate detection of natural phenomena, such as red tide, th...
Recognizing an event in an image can be enhanced by detecting relevant
o...
In this paper, we address the dataset scarcity issue with the hyperspect...
We introduce Multi-Expert Region-based CNN (ME R-CNN) which is equipped ...
Many previous methods have showed the importance of considering semantic...
In this paper, we introduce a novel fusion method that can enhance objec...
Learning an event classifier is challenging when the scenes are semantic...
In this paper, we describe a novel deep convolutional neural network (CN...
A novel template matching algorithm that can incorporate the concept of
...
Object localization is an important task in computer vision but requires...
Object localization is an important computer vision problem with a varie...
A novel approach for the fusion of heterogeneous object detection method...