By contextualizing the kernel as global as possible, Modern ConvNets have shown great
potential in computer vision tasks. However, recent progress on\textit {multi-order game …

How to represent a seismic wavefield? Traditionally, while seismic wavefields are
conceptualized continuously, acquisition geometries capture seismic data discretely using 2 …

Molecular surfaces imply fingerprints of interaction patterns between proteins. However, non-
equivalent efforts have been paid to incorporating the abundant protein surface information …

Semi-supervised learning (SSL) has witnessed great progress with various improvements in
the self-training framework with pseudo labeling. The main challenge is how to distinguish …

Similar to natural language models, pre-trained genome language models are proposed to
capture the underlying intricacies within genomes with unsupervised sequence modeling …

Large language models equipped with retrieval-augmented generation (RAG) represent a
burgeoning field aimed at enhancing answering capabilities by leveraging external …

Recent developments underscore the potential of textual information in enhancing learning
models for a deeper understanding of medical visual semantics. However, language-guided …

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-
training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale …

In recent years, significant strides have been made in the field of spatiotemporal predictive
learning, a discipline that focuses on accurately forecasting future sequences based on …

This paper presents a novel Hybrid Self-Supervised and Semi-Supervised Framework for
Robust Spatio-Temporal Action Detection, which integrates the advantages of self …