The introduction of ChatGPT and the subsequent improvement of Large Lang...
In the realm of Large Language Models, the balance between instruction d...
This paper offers a new perspective to ease the challenge of domain
gene...
Chinese Automatic Speech Recognition (ASR) error correction presents
sig...
Conversational Question Answering (CQA) is a challenging task that aims ...
This paper addresses the problem of ranking pre-trained models for objec...
Parameter Efficient Tuning (PET) has gained attention for reducing the n...
3D facial avatar reconstruction has been a significant research topic in...
One challenge in text-to-image (T2I) generation is the inadvertent refle...
A critical yet frequently overlooked challenge in the field of deepfake
...
Artificial intelligence technology has been widely used in astronomy, an...
A new data-driven bilateral generalized two-dimensional quaternion princ...
Almost all advanced face swapping approaches use reconstruction as the p...
Creating a vivid video from the event or scenario in our imagination is ...
Exquisite demand exists for customizing the pretrained large text-to-ima...
Deep neural networks (DNNs) can be manipulated to exhibit specific behav...
Deepfake detection remains a challenging task due to the difficulty of
g...
The main challenge in domain generalization (DG) is to handle the
distri...
This paper presents a framework for efficient 3D clothed avatar
reconstr...
Fast adversarial training (FAT) is an efficient method to improve robust...
Link prediction aims to identify potential missing triples in knowledge
...
Image inpainting aims to fill the missing hole of the input. It is hard ...
The Natural Language for Optimization (NL4Opt) Competition was created t...
One-shot video-driven talking face generation aims at producing a synthe...
In this work, we investigate a simple and must-known conditional generat...
Data trading is essential to accelerate the development of data-driven
m...
High-fidelity facial avatar reconstruction from a monocular video is a
s...
We present VideoReTalking, a new system to edit the faces of a real-worl...
We present a novel paradigm for high-fidelity face swapping that faithfu...
Generating talking head videos through a face image and a piece of speec...
3D-aware generative adversarial networks (GANs) synthesize high-fidelity...
Despite the impressive results of arbitrary image-guided style transfer
...
Deep neural networks (DNNs) have been shown to be vulnerable to adversar...
Measuring Sentence Textual Similarity (STS) is a classic task that can b...
We describe an augmented intelligence system for simplifying and enhanci...
In modern SD-WAN networks, a global controller continuously optimizes
ap...
The kernel truncation method (KTM) is a commonly-used algorithm to compu...
Federated learning is an emerging technique for training models from
dec...
Data augmentation is an essential technique in improving the generalizat...
We propose a new framework for extracting visual information about a sce...
Fast adversarial training (FAT) effectively improves the efficiency of
s...
The popularity of machine learning has increased the risk of unfair mode...
Branch-and-bound is a systematic enumerative method for combinatorial
op...
Semi-supervised learning (SSL) has seen great strides when labeled data ...
Recent high-performing Human-Object Interaction (HOI) detection techniqu...
Unsupervised representation learning methods like SwAV are proved to be
...
Contrastive self-supervised representation learning methods maximize the...
While adversarial training and its variants have shown to be the most
ef...
In order to find the most likely failure scenarios which may occur under...
Facial Action Unit (AU) detection is a crucial task for emotion analysis...