This paper targets a novel trade-off problem in generalizable prompt lea...
Privacy protection has become a top priority as the proliferation of AI
...
Facial sketch synthesis (FSS) aims to generate a vivid sketch portrait f...
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...
As more deep learning models are being applied in real-world application...
Unsupervised learning visible-infrared person re-identification (USL-VI-...
Unsupervised visible-infrared person re-identification (USL-VI-ReID) aim...
Quantized Neural Networks (QNNs) receive increasing attention in
resourc...
Zero-shot sketch-based image retrieval (ZS-SBIR) is challenging due to t...
Neural radiance fields (NeRF) based methods have shown amazing performan...
Due to the lack of temporal annotation, current Weakly-supervised Tempor...
Weakly Supervised Temporal Action Localization (WTAL) aims to classify a...
We present a novel framework for exemplar based image translation. Recen...
Face image translation has made notable progress in recent years. Howeve...
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...
Unsupervised person re-identification (ReID) aims at learning discrimina...
We present VideoReTalking, a new system to edit the faces of a real-worl...
With the wide and deep adoption of deep learning models in real applicat...
With the continuous development of deep learning in the field of image
g...
Adversarial training (AT) is proved to reliably improve network's robust...
With the development of online artificial intelligence systems, many dee...
Deep neural networks (DNNs) are found to be vulnerable to adversarial no...
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...
Unsupervised person re-identification (Re-Id) has attracted increasing
a...
Single image dehazing is a prerequisite which affects the performance of...
Deep neural networks have been demonstrated to be vulnerable to adversar...
Current approaches for video grounding propose kinds of complex architec...
By considering the spatial correspondence, dense self-supervised
represe...
Estimating the kernel mean in a reproducing kernel Hilbert space is a
cr...
Deep neural networks (DNNs) are vulnerable to adversarial noise. A range...
Deep neural networks (DNNs) are vulnerable to adversarial noise. Their
a...
Deep neural networks (DNNs) are vulnerable to adversarial noise.
Preproc...
Artistic style transfer aims at migrating the style from an example imag...
The label noise transition matrix T, reflecting the probabilities that t...
To reduce the amount of transmitted data, feature map based fusion is
re...
Temporal action localization presents a trade-off between test performan...
Learning with the instance-dependent label noise is challenging,
because...
Label noise is ubiquitous in the era of big data. Deep learning algorith...
Heterogeneous face recognition (HFR) refers to matching face images acqu...
Existing face super-resolution (SR) methods mainly assume the input imag...
A similarity label indicates whether two instances belong to the same cl...