Recognizing objects from sparse and noisy events becomes extremely diffi...
Sensor fusion approaches for intelligent self-driving agents remain key ...
Understanding the interaction between multiple agents is crucial for
rea...
Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-le...
Test-time adaptation methods have been gaining attention recently as a
p...
We present a unified and compact representation for object rendering, 3D...
Monocular depth estimation has been extensively explored based on deep
l...
The limited dynamic range of commercial compact camera sensors results i...
Semantic segmentation algorithms require access to well-annotated datase...
Video deblurring is a highly ill-posed problem due to the loss of motion...
The 360imaging has recently gained great attention; however, its
angular...
Providing omnidirectional depth along with RGB information is important ...
Image stitching aims at stitching the images taken from different viewpo...
Existing studies in weakly supervised semantic segmentation (WSSS) have
...
Learning to estimate object pose often requires ground-truth (GT) labels...
Event cameras sense per-pixel intensity changes and produce asynchronous...
High dynamic range (HDR) imaging is a technique that allows an extensive...
Event cameras are novel sensors that perceive the per-pixel intensity ch...
Event cameras are novel sensors that perceive the per-pixel intensity ch...
Region modification-based data augmentation techniques have shown to imp...
Deep neural models in recent years have been successful in almost every
...
Event cameras sense intensity changes and have many advantages over
conv...
Deep neural networks (DNNs) have achieved impressive performance on hand...
An event camera detects per-pixel intensity difference and produces
asyn...
Digital prototyping and evaluation using 3D modeling and digital human m...
Digital prototyping and evaluation using 3D modeling and digital human m...
The rolling shutter camera has received great attention due to its low c...
Event cameras have a lot of advantages over traditional cameras, such as...
Omni-directional cameras have many advantages over conventional cameras ...
Many applications in computer vision can be formulated as a multiple gra...
Relative pose estimation is a fundamental problem in computer vision and...
In this paper, we propose a novel distance-based camera network topology...
Person re-identification is the task of recognizing or identifying a per...
Person re-identification is the problem of recognizing people across
dif...
To watch 360 videos on normal 2D displays, we need to project the
select...