Supervised trackers trained on labeled data dominate the single object
t...
Scene understanding using multi-modal data is necessary in many applicat...
Ensuring the realism of computer-generated synthetic images is crucial t...
Synthetic-to-real data translation using generative adversarial learning...
Frequency-domain learning draws attention due to its superior tradeoff
b...
In this work, we target the problem of uncertain points refinement for
i...
Scene-graph generation involves creating a structural representation of ...
This work introduces alternating latent topologies (ALTO) for high-fidel...
Motivated by the increasing application of low-resolution LiDAR recently...
Supervised and unsupervised deep trackers that rely on deep learning
tec...
We propose a large-scale dataset of real-world rainy and clean image pai...
On the basis of DefakeHop, an enhanced lightweight Deepfake detector cal...
An unsupervised, lightweight and high-performance single object tracker,...
A robust fake satellite image detection method, called Geo-DefakeHop, is...
Object detectors trained on large-scale RGB datasets are being extensive...
An unsupervised online object tracking method that exploits both foregro...
The human-object interaction (HOI) detection task refers to localizing
h...
Our goal is to develop stable, accurate, and robust semantic scene
under...
Current perception systems often carry multimodal imagers and sensors su...
A light-weight high-performance Deepfake detection method, called Defake...
A non-parametric low-resolution face recognition model for
resource-cons...
The construction of a multilayer perceptron (MLP) as a piecewise low-ord...
A closed-form solution exists in two-class linear discriminant analysis
...
A light-weight low-resolution face gender classification method, called
...
Without using extra 3-D data like points cloud or depth images for provi...
The successive subspace learning (SSL) principle was developed and used ...
In this paper, we propose our Correlation For Completion Network (CFCNet...
In this work, we study the power of Saak features as an effort towards
i...
Image classification is vulnerable to adversarial attacks. This work
inv...
Many state-of-the-art computer vision algorithms use large scale
convolu...
Recent advances in convolutional neural networks have shown promising re...
Recurrent neural network (RNN), as a powerful contextual dependency mode...