Edutopia

Simple Swaps for Moving From Passive to Active Learning

These tips demonstrate that planning for active learning experiences doesn’t have to be time-intensive or difficult.
IEEE

Model Attention Expansion for Few-Shot Class-Incremental Learning

Abstract: Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning new knowledge from limited training examples without forgetting previous knowledge. However, we observe that ...
GitHub

D-FINE: Redefine Regression Task of DETRs as Fine‑grained Distribution Refinement

If you like D-FINE, please give us a ⭐! Your support motivates us to keep improving! D-FINE is a powerful real-time object detector that redefines the bounding box regression task in DETRs as ...
Frontiers

Brain functional activity of Parkinson’s disease patients under a virtual reality eye movement task: a functional near-infrared spectroscopy study

Objective: This study aimed to investigate the eye movement behavior characteristics and associated brain functional activity changes in Parkinson’s disease (PD) patients during a complex visual task, ...
GitHub

Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection

07.2025: Dinomaly has been integrated in Intel open-edge Anomalib in v2.1.0. Great thanks to the contributors for the nice reproduction and integration. Anomalib is a comprehensive library for ...
IEEE

RGSA: Sensor-Based Group Activity Recognition Model With Relation Gating and Spatiotemporal Attention

Abstract: Sensor-based group activity recognition (GAR) is a challenging task that requires handling complex individual actions and interindividual relations. An imperative exists to explore a ...