Multi-task learning (MTL) has shown great potential in medical image
ana...
Accurate traffic forecasting at intersections governed by intelligent tr...
Methods: In this study, a benchmark Abdominal Adipose Tissue CT Image
Da...
Transformer-based methods have exhibited remarkable potential in single ...
Lyrics generation is a well-known application in natural language genera...
In today's competitive and fast-evolving business environment, it is a
c...
Visual question answering (VQA) is a challenging task that requires the
...
Current Vision and Language Models (VLMs) demonstrate strong performance...
In this paper, we present a simple but performant semi-supervised semant...
The field of protein folding research has been greatly advanced by deep
...
Affected by the massive amount of parameters, ViT usually suffers from
s...
We present Antler, which exploits the affinity between all pairs of task...
Time series anomaly detection strives to uncover potential abnormal beha...
Ensemble learning serves as a straightforward way to improve the perform...
Current efficient LiDAR-based detection frameworks are lacking in exploi...
Aesthetic assessment of images can be categorized into two main forms:
n...
In recent years, image generation has made great strides in improving th...
The essence of video semantic segmentation (VSS) is how to leverage temp...
Data augmentation is an effective approach to tackle over-fitting. Many
...
Although sequence-to-sequence models often achieve good performance in
s...
Simile interpretation (SI) and simile generation (SG) are challenging ta...
Recently, Transformer has become a prevailing deep architecture for solv...
Existing salient object detection (SOD) methods mainly rely on CNN-based...
We unveil a long-standing problem in the prevailing co-saliency detectio...
We tackle the low-efficiency flaw of vision transformer caused by the hi...
We propose a monocular depth estimator SC-Depth, which requires only
unl...
Recent progress on salient object detection (SOD) mainly benefits from
m...
Generalized zero-shot learning (GZSL) aims to recognize both seen and un...
Much of the recent efforts on salient object detection (SOD) has been de...
Recent years have seen increasing use of supervised learning methods for...
Is recurrent network really necessary for learning a good visual
represe...
Triplet loss has been widely employed in a wide range of computer vision...
Superpixel is widely used in image processing. And among the methods for...
In this paper, a non-local adaptive mean filter (NAMF) is proposed, whic...
Matching two images while estimating their relative geometry is a key st...
Nonlinear regression has been extensively employed in many computer visi...
Segmentation stands at the forefront of many high-level vision tasks. In...
The exploitation of large-scale population data has the potential to imp...
Recent progress on salient object detection mainly aims at exploiting ho...
Personality and emotion are both central to affective computing. Existin...
Cardiac magnetic resonance (CMR) images play a growing role in the diagn...
Feature matching is one of the most fundamental and active research area...
Detecting fake users (also called Sybils) in online social networks is a...
Deep learning stands at the forefront in many computer vision tasks. How...
In this paper, we comprehensively describe the methodology of our submis...
Semantic edge detection (SED), which aims at jointly extracting edges as...
Sybil detection in social networks is a basic security research problem....
Image matching approaches have been widely used in computer vision
appli...
Cross-correlator plays a significant role in many visual perception task...