3 papers
cs.CV2026
MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition
Hyejeong Im, Wonseon Lim, Dae-Won Kim
Multimodal egocentric activity recognition integrates visual and inertial cues for robust first-person behavior understanding. However, deploying such systems in open-world environ…
cs.LG2026
Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge
Wonseon Lim, Jaesung Lee, Dae-Won Kim
Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational cons…
cs.LG2026
On Evaluation of Unsupervised Feature Selection for Pattern Classification
Gyu-Il Kim, Dae-Won Kim, Jaesung Lee
Unsupervised feature selection aims to identify a compact subset of features that captures the intrinsic structure of data without supervised label. Most existing studies evaluate…