3d human pose 1channel state information 1self-supervised learning 1simulation pipeline 1wifi-based pose estimation 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.CV2026
Multi-Agent Target-Existence Verification and Learned Mask Geometry Refinement: Winning Report of the MeViS-Text Track at the 8th LSVOS Challenge 2026
Jungyoon Lee, Gyuil Lim, Doeon Kim +1
We present the first-place solution to the MeViS-Text track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge 2026: referring video object segmentation guided by w…
cs.CV2026
WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation
Doeon Kim, Jungyoon Lee, Seongsin Kim +1
The paper introduces WiFi-JEPA, a self‑supervised method that learns representations from WiFi channel state information to estimate 3D human poses, using masked latent prediction…
cs.CV2026
Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction Download PDF
Do-Eon Kim, Dongryul Park, Seungyoung Ahn +3
Predicting electromagnetic field (EMF) strength in urban environments is essential for cellular network planning but computationally expensive with physics-based simulators. We pro…