This technical report details our submission system to the CHiME-7 DASR
...
Transducer is one of the mainstream frameworks for streaming speech
reco...
High-quality panoramic images with a Field of View (FoV) of 360-degree a...
In this paper, we present a new question-answering (QA) based key-value ...
In view of the extended formulations (EFs) developments (e.g. "Fiorini, ...
We present a new table structure recognition (TSR) approach, called
TSRF...
Fast and accurate auto-focus in adverse conditions remains an arduous ta...
The performance of video frame interpolation is inherently correlated wi...
Sex difference in allele frequency is an emerging topic that is critical...
Semantic scene understanding with Minimalist Optical Systems (MOS) in mo...
Automatic human matting is highly desired for many real applications. We...
We present a new table structure recognition (TSR) approach, called
TSRF...
Since convolutional neural networks perform well in learning generalizab...
Blind face restoration usually encounters with diverse scale face inputs...
This paper presents our submission to the Multi-Task Learning (MTL) Chal...
Panoramic Annular Lens (PAL), composed of few lenses, has great potentia...
Human Pose Estimation (HPE) based on RGB images has experienced a rapid
...
Various defense models have been proposed to resist adversarial attack
a...
Deep neural networks are widely used in various fields because of their
...
Spatial perception problems are the fundamental building blocks of robot...
Power and sample size computation plays an important role in the design ...
Multi-collinearity is a wide-spread phenomenon in modern statistical
app...
We introduce a new table detection and structure recognition approach na...
Traditional frame-based cameras inevitably suffer from motion blur due t...
3D point cloud registration ranks among the most fundamental problems in...
Correspondence-based point cloud registration is a cornerstone in roboti...
Correspondence-based point cloud registration is a cornerstone in geomet...
We propose a separation guided speaker diarization (SGSD) approach by fu...
Vision Transformer (ViT) attains state-of-the-art performance in visual
...
Recent grid-based document representations like BERTgrid allow the
simul...
Aerial pixel-wise scene perception of the surrounding environment is an
...
Rotation search and point cloud registration are two fundamental problem...
Correspondence-based rotation search and point cloud registration are tw...
This system description describes our submission system to the Third DIH...
In this paper, we present IRON (Invariant-based global Robust estimation...
Hypothesis testing results often rely on simple, yet important assumptio...
Using polygenic risk score for trait association analyses and disease
pr...
One-class novelty detection is to identify anomalous instances that do n...
In evolutionary computation, different reproduction operators have vario...
We introduce a new arbitrary-shaped text detection approach named ReLaTe...
Semantic segmentation has made striking progress due to the success of d...
This paper presents the problems and solutions addressed at the JSALT
wo...
Currently, semantic segmentation shows remarkable efficiency and reliabi...
Learning causal effects from observational data greatly benefits a varie...
The conventional speaker recognition frameworks (e.g., the i-vector and
...
There has been a series of developments in the recent literature (by
ess...
The Normal Means problem plays a fundamental role in many areas of moder...
In this paper, we present a new Mask R-CNN based text detection approach...
X-chromosome is often excluded from whole-genome association studies due...
In this article, we show that solving the system of linear equations by
...