publications

2026

1. ECCV 2026

   

   WiFi-JEPA: Self-supervised Learning for WiFi-CSI 3D Human Pose Estimation

   Doeon Kim, Jungyoon Lee, Seongheum Kim, and Seongsin Kim

   ECCV 2026, Malmö, Sweden, Jul 2026

   Abs Website

   A CSI-native self-supervised framework that learns WiFi-CSI representations by predicting masked latent embeddings rather than reconstructing raw CSI, using CSI-aware tokenization and a ray-tracing-based synthetic-CSI pretraining pipeline. It improves 3D human-pose accuracy over supervised and prior CSI baselines, including in multi-person settings.

2. Patent

   Structure-Aware Self-Supervised Learning and Link Masking-Based 3D Human Pose Estimation System and Method Using WiFi Channel State Information

   Doeon Kim, Jungyoon Lee, Seongheum Kim, and Seongsin Kim

   Jun 2026

   Korean Patent Application No. 10-2026-0102154, filed Jun. 5, 2026. Patent pending.
3. Under review

   Multimodal pretraining for radio-map estimation

   Hyunwoo Choi, Doeon Kim, and Seongsin Kim

   NeurIPS 2026 (under review), May 2026

   Abs

   A multimodal Transformer that keeps image patches as a dense spatial stream and fuses tabular antenna metadata via late cross-attention, with masked-image and masked-tabular pretraining objectives. It achieves low error across radio-map prediction settings, outperforming convolutional and Transformer baselines.

4. Preprint

   

   Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction

   Doeon Kim, Dongryul Park, Seungyoung Ahn, Namwoo Kang, Seongheum Kim, and Seongsin Kim

   arXiv, Mar 2026

   Abs PDF

   A multi-conditioned dense-prediction framework that generates urban EMF maps from building layouts and antenna configurations, using a vision-transformer backbone with feature-modulation and cross-attention conditioning and transmitter-relative spatial channels. It improves EMF-map accuracy over convolutional and unconditioned baselines.

2025

1. CEIC

   

   Multimodal Physical Data Fusion using ViT for 5G Electromagnetic Field Estimation

   Doeon Kim and Seongsin Kim

   CEIC, Jeju, Korea, Dec 2025
2. IEEE Access

   

   Estimation of Electromagnetic Field Strength: Experiments Using Vision Transformers

   Doeon Kim, Dongryul Park, Jinbae Seo, Hyungchan Cho, Seungyoung Ahn, Namwoo Kang, and Seongsin Kim

   IEEE Access, Oct 2025

   Abs PDF

   A systematic study of Vision Transformer architectures for predicting 5G electromagnetic-field strength from physically-informed, ray-tracing-generated inputs (building maps, antenna radiation patterns, base-station parameters). Among the compared models an HRFormer-based predictor achieves the best masked MAE of 5.45%, about a 31% error reduction over a U-Net baseline.

2024

1. KIIS

   

   Tiny Object Detection Method Based on Cross Attention of Heterogeneous Feature Maps

   Seungchan Kwon, Doeon Kim, Gyuil Lim, Youngjun Han, and Seongsin Kim

   KIIS Autumn Conference, Gangneung, Korea, Nov 2024