Recent studies have utilized deep learning (DL) techniques to automatica...
The long-term goal of machine learning is to learn general visual
repres...
Zero-shot skeleton-based action recognition aims to recognize actions of...
Human motion prediction (HMP) has emerged as a popular research topic du...
Through experiments on various meta-learning methods, task samplers, and...
In recent years, self-supervised learning (SSL) has emerged as a promisi...
Diffusion models are a powerful class of generative models that can prod...
Due to limitations in data quality, some essential visual tasks are diff...
Generative Adversarial Networks (GANs) and their variants have achieved
...
Generative adversarial networks (GANs) have achieved remarkable progress...
Benefiting from the injection of human prior knowledge, graphs, as deriv...
Over past few years afterward the birth of ResNet, skip connection has b...
As a successful approach to self-supervised learning, contrastive learni...
While self-supervised learning techniques are often used to mining impli...
Few-shot learning models learn representations with limited human
annota...
The prevailing graph neural network models have achieved significant pro...
Contrastive learning (CL)-based self-supervised learning models learn vi...
Vision-language models are pre-trained by aligning image-text pairs in a...
What matters for contrastive learning? We argue that contrastive learnin...
Unsupervised domain adaptation (UDA) requires source domain samples with...
Recent works explore learning graph representations in a self-supervised...
Multi-view representation learning captures comprehensive information fr...