Federated training of Graph Neural Networks (GNN) has become popular in
...
Image composition targets at synthesizing a realistic composite image fr...
Federated learning (FL) is a distributed machine learning paradigm that ...
Most state-of-the-art deep domain adaptation techniques align source and...
Deep neural networks are vulnerable to adversarial examples, dictating t...
Change detection based on remote sensing images has been a prominent are...
It is assumed that pre-training provides the feature extractor with stro...
Diffusion model based language-guided image editing has achieved great
s...
Recent object detection approaches rely on pretrained vision-language mo...
Knowledge Graph Embedding (KGE) is a fundamental technique that extracts...
We present neural frailty machine (NFM), a powerful and flexible neural
...
Graph representation plays an important role in the field of financial r...
The application of graph representation learning techniques to the area ...
With the frequent happening of privacy leakage and the enactment of priv...
Recently, diffusion frameworks have achieved comparable performance with...
Privacy in AI remains a topic that draws attention from researchers and ...
Image harmonization is a critical task in computer vision, which aims to...
Based on the significant improvement of model robustness by AT (Adversar...
We present a neural network-based system for long-term, multi-action hum...
We propose a novel attention-based 2D-to-3D pose estimation network for
...
Generally pre-training and long-time training computation are necessary ...
We present masked graph autoencoder (MaskGAE), a self-supervised learnin...
Recently, graph convolutional networks (GCNs) have shown to be vulnerabl...
Recently, various multimodal networks for Visually-Rich Document
Underst...
Despite the success of deep learning in computer vision and natural lang...
Exploiting relations among 2D joints plays a crucial role yet remains
se...
Since training a large-scale backdoored model from scratch requires a la...
Deep learning provides a promising way to extract effective representati...
Recently, Graph Neural Network (GNN) has achieved remarkable success in
...
With only bounding-box annotations in the spatial domain, existing video...
Chinese is one of the most widely used languages in the world, yet onlin...
The convention standard for object detection uses a bounding box to repr...
Object detection and counting are related but challenging problems,
espe...
Loss functions play a key role in training superior deep neural networks...
The connectionist temporal classification (CTC) enables end-to-end seque...
Egocentric videos, which mainly record the activities carried out by the...
The recurrent neural network (RNN) is appropriate for dealing with tempo...