As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning
(VPT) as a parameter-efficient transfer learning technique has gained attention due to its …

By mapping iterative optimization algorithms into neural networks (NNs), deep unfolding
networks (DUNs) exhibit well-defined and interpretable structures and achieve remarkable …

3D Masked Point Modeling (MPM) typically involves randomly or blockly discarding points or
patches and then reconstructing them, offering a promising avenue for exploring geometric …

Abstract Human Activity Recognition (HAR) deals with the automatic recognition of physical
activities and plays a crucial role in healthcare and sports where wearable sensors and …

Open vocabulary segmentation is a challenging task that aims to segment out the thousands
of unseen categories. Directly applying CLIP to open-vocabulary semantic segmentation is …

Subspace learning has been widely applied for joint feature extraction and dimensionality
reduction, demonstrating significant efficacy. Numerous subspace learning methods with …

In this work, we introduce the Prototypical Transformer (ProtoFormer), a general and unified
framework that approaches various motion tasks from a prototype perspective. ProtoFormer …

Heatmap-based methods have dominated the face alignment task, yet the maximum
response decoding scheme necessitates further reform. While some studies have attempted …

Few-shot open-set recognition (FSOR) is a challenging task that requires a model to
recognize known classes and identify unknown classes with limited labeled data. Existing …

This paper introduces SimpliFusion, a network designed for the fusion of infrared and visible
images, leveraging a simplified transformer architecture. SimpliFusion is engineered to …