This paper targets a novel trade-off problem in generalizable prompt lea...
Privacy protection has become a top priority as the proliferation of AI
...
Impressive performance on point cloud semantic segmentation has been ach...
Due to the successful development of deep image generation technology, v...
This paper proposes a novel paradigm for facial privacy protection that
...
Advanced manipulation techniques have provided criminals with opportunit...
Synthetic aperture radar (SAR) is prevalent in the remote sensing field ...
Unsupervised learning visible-infrared person re-identification (USL-VI-...
Unsupervised visible-infrared person re-identification (USL-VI-ReID) aim...
How humans understand and recognize the actions of others is a complex
n...
DEtection TRansformer (DETR) and its variants (DETRs) achieved impressiv...
Although numerous clustering algorithms have been developed, many existi...
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to t...
Due to the lack of temporal annotation, current Weakly-supervised Tempor...
Weakly Supervised Temporal Action Localization (WTAL) aims to classify a...
Hyperspectral unmixing is a critical yet challenging task in hyperspectr...
Human cognition has a “large-scale first” cognitive mechanism, therefore...
State-of-the-art 3D object detectors are usually trained on large-scale
...
Multi-view clustering (MVC) based on non-negative matrix factorization (...
In recent years, the problem of fuzzy clustering has been widely concern...
Most of the existing clustering methods are based on a single granularit...
Few-shot font generation (FFG) aims to preserve the underlying global
st...
Face forgery detection plays an important role in personal privacy and s...
Attention-based arbitrary style transfer studies have shown promising
pe...
This technical report briefly describes our JDExplore d-team's Vega v2
s...
Unsupervised person re-identification (ReID) aims at learning discrimina...
Network traffic classification is the basis of many network security
app...
Very high-resolution (VHR) remote sensing (RS) image classification is t...
With the continuous development of deep learning in the field of image
g...
GBSVM (Granular-ball Support Vector Machine) is an important attempt to ...
With the development of online artificial intelligence systems, many dee...
The deep convolutional neural networks (CNNs)-based single image dehazin...
Deep neural networks (DNNs) are found to be vulnerable to adversarial no...
Visual Emotion Analysis (VEA), which aims to predict people's emotions
t...
Face attribute evaluation plays an important role in video surveillance ...
In recent years, with the rapid development of face editing and generati...
In label-noise learning, estimating the transition matrix has attracted ...
Single image dehazing as a fundamental low-level vision task, is essenti...
Only parts of unlabeled data are selected to train models for most
semi-...
The large discrepancy between the source non-makeup image and the refere...
Granular-ball computing is an efficient, robust, and scalable learning m...
Pawlak rough set and neighborhood rough set are the two most common roug...
This paper present a strong data mining method based on rough set, which...
Recently, deep-learning-based super-resolution methods have achieved
exc...
Visual Emotion Analysis (VEA) aims at finding out how people feel emotio...
Attributed graph clustering, which learns node representation from node
...
The infrared small-dim target detection is one of the key techniques in ...
Unsupervised person re-identification (Re-Id) has attracted increasing
a...
Single image dehazing is a prerequisite which affects the performance of...
Visual emotion analysis (VEA) has attracted great attention recently, du...