Although recent deep learning based gaze estimation approaches have achi...
Gaze estimation methods estimate gaze from facial appearance with a sing...
In recent years, metaverse and digital humans have become important rese...
Due to the prevalence of scale variance in nature images, we propose to ...
Low-light hazy scenes commonly appear at dusk and early morning. The vis...
Visual Place Recognition (VPR) is the task of retrieving database images...
Deep neural networks have demonstrated superior performance on
appearanc...
Intrinsic image decomposition is an important and long-standing computer...
The crux of text-to-image synthesis stems from the difficulty of preserv...
Augmented Reality (AR) see-through vision is an interesting research top...
Appearance-based gaze estimation aims to predict the 3D eye gaze directi...
In the area of 3D shape analysis, the geometric properties of a shape ha...
Unsupervised image-to-image translation aims to learn the mapping betwee...
Deep neural networks have significantly improved appearance-based gaze
e...
Remote photoplethysmography (rPPG) monitors heart rate without requiring...
Though deep learning has shown successful performance in classifying the...
Recent work has proven the effectiveness of transformers in many compute...
Gaze estimation reveals where a person is looking. It is an important cl...
Recently, the methods based on Convolutional Neural Networks (CNNs) have...
Gaze estimation methods learn eye gaze from facial features. However, am...
Appearance-based gaze estimation has achieved significant improvement by...
Anomaly detection from a single image is challenging since anomaly data ...
Since specular reflection often exists in the real captured images and c...
Recently, many multi-stream gaze estimation methods have been proposed. ...
To achieve reliable mining results for massive vessel trajectories, one ...
Recent studies have shown that DNNs can be compromised by backdoor attac...
This paper proposes a new light-weight convolutional neural network (5k
...
The current industry practice for 24-hour outdoor imaging is to use a si...
With the uptake of algorithmic personalization in the news domain, news
...
Human gaze is essential for various appealing applications. Aiming at mo...
Typical methods for text-to-image synthesis seek to design effective
gen...
Thanks to the latest progress in image sensor manufacturing technology, ...
Intrinsic image decomposition, which is an essential task in computer vi...
Real-time semantic segmentation plays a significant role in industry
app...
Low-light image enhancement is a challenging task since various factors,...
Reflection is common in images capturing scenes behind a glass window, w...
Deep neural networks (DNNs) have become popular for medical image analys...
Unsupervised single image layer separation aims at extracting two layers...
In recent years, more and more videos are captured from the first-person...
Though deep learning has shown successful performance in classifying the...
Convolutional Neural Networks have demonstrated superior performance on
...
Voxel is an important format to represent geometric data, which has been...
The implementation details of factorizing the 3x4 projection matrices of...
We present algebraic projective geometry definitions of 3D rotations so ...