Junha Song

4 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner

Venues

CVPR (2) ECCV (1) IJCAI (1)

Top co-authors

In So Kweon (2) Jaegul Choo (2) Thijs Kooi (1) Chaoning Zhang (1) Tae Soo Kim (1) Jungsoo Lee (1) Chenshuang Zhang (1) John Seon Keun Yi (1) Taehwan Kim (1) Gunhee Nam (1)

Research topics

Computer Vision (2) Machine Learning (2) Learning Types (2) Artificial Intelligence (1) Deep Learning (1) Application Areas (1) Core AI (1) Generation (1) Optimization & Theory (1) Processing (1)

Keywords

model compression (1) representation learning (1) continual learning (1) catastrophic forgetting (1) image captioning (1) test-time adaptation (1) memory efficiency (1) multimodal language model (1) masked autoencoder (1) pretext task (1) masked image modeling (1) visual self-supervised learning (1) multimodal self-refinement (1)

Papers

MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning CVPR 2026 Is user feedback always informative? Retrieval Latent Defending for Semi-Supervised Domain Adaptation without Source Data ECCV 2024 A Survey on Masked Autoencoder for Visual Self-supervised Learning IJCAI 2023 EcoTTA: Memory-Efficient Continual Test-Time Adaptation via Self-Distilled Regularization CVPR 2023