3 papers
cs.CV2026
PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognition
Sanghyeon Lee, Jinwoo Kim, Jong Taek Lee
Zero-shot skeleton-based action recognition (ZSSAR) is typically treated as a skeleton-text alignment problem: encode joint-coordinate sequences, align them with language, and clas…
cs.CV2026
OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation
Sanghyeon Lee, Minwoo Lee, Euijin Shin +3
We introduce a parameter-efficient adaptation method for panel-aware in-context image generation with pre-trained diffusion transformers. The key idea is to compose learnable, pane…
cs.CV2024
Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera
Inpyo Song, Sanghyeon Lee, Minjun Joo +1
Recent advancements in computer vision have led to a renewed interest in developing assistive technologies for individuals with visual impairments. Although extensive research has…