Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
SCoPE: Training-Free Audio-Visual Event Perception via Sparse Cross-Modal Prior Exchange
Jaemo Jeong, Junho Yoon, Hyunju Kim +1
Audio-visual event perception (AVEP) determines which events occur in a video, when they occur, and whether they are audible, visible, or both. Training-free methods query new even…
cs.CV2025
DETACH : Decomposed Spatio-Temporal Alignment for Exocentric Video and Ambient Sensors with Staged Learning
Junho Yoon, Jaemo Jung, Hyunju Kim +1
Aligning egocentric video with wearable sensors have shown promise for human action recognition, but face practical limitations in user discomfort, privacy concerns, and scalabilit…
cs.CV2024
Feature Augmentation based Test-Time Adaptation
Younggeol Cho, Youngrae Kim, Junho Yoon +2
Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount…