Video moment localization aims to retrieve the target segment of an untr...
Zero-shot skeleton-based action recognition aims to recognize actions of...
Text-to-motion generation has gained increasing attention, but most exis...
Human motion prediction (HMP) has emerged as a popular research topic du...
Molecular representation learning is a crucial task in predicting molecu...
Auto-evaluation aims to automatically evaluate a trained model on any te...
How to estimate the uncertainty of a given model is a crucial problem.
C...
Self-supervised learning has demonstrated remarkable capability in
repre...
The spatial dependence in mean has been well studied by plenty of models...
As a successful approach to self-supervised learning, contrastive learni...
While self-supervised learning techniques are often used to mining impli...
Contrastive learning (CL)-based self-supervised learning models learn vi...
Recently, significant progress has been made in masked image modeling to...
Various new scheduling problems have been arising from practical product...
Action classification has made great progress, but segmenting and recogn...
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...
Transformer-based methods have shown great potential in long-term time s...
Multi-view representation learning captures comprehensive information fr...
Convolutional neural networks use regular quadrilateral convolution kern...
Existing popular unsupervised embedding learning methods focus on enhanc...
Given a graph G = (V, E), the 3-path partition problem is to find a
mini...
A mixed shop is a manufacturing infrastructure designed to process a mix...