← Authors

Dongjin Kim

11 papers · 2023–2026 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (24) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (54) πŸ’Ž Century Club (10)

Conferences

AAAI (3) CVPR (3) ICCV (2) ICLR (1) ICML (1) NIPS (1)

Top co-authors

Tae Hyun Kim (6) Jung Uk Kim (3) Muhammad Kashif Ali (3) Sung Jin Um (3) Sangmin Lee (3) Sungyong Baik (2) Suhyun Kim (2) Gyeong Eun Gong (1) Cheonjun Park (1) Jaekyun Ko (1)

Research topics

Processing (1)

Keywords

multimodal learning (3) image restoration (3) latent space (2) sound source localization (2) contrastive learning (2) video understanding (1) scene understanding (1) image generation (1) video highlight detection (1) batch normalization (1) audio-visual learning (1) test-time adaptation (1) data augmentation (1) video restoration (1) flow matching (1) object localization (1) neural network optimization (1) image denoising (1) object detection (1) feature extraction (1)

Papers

Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-Resolution AAAI 2026
Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection AAAI 2025
Object-aware Sound Source Localization via Audio-Visual Scene Understanding CVPR 2025
IDF: Iterative Dynamic Filtering Networks for Generalizable Image Denoising ICCV 2025
REPrune: Channel Pruning via Kernel Representative Selection AAAI 2024
Harnessing Meta-Learning for Improving Full-Frame Video Stabilization CVPR 2024
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows ICLR 2024
Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge CVPR 2024
Tanh Works Better with Asymmetry NIPS 2023
Task Agnostic Restoration of Natural Video Dynamics ICCV 2023
Learning Controllable Degradation for Real-World Super-Resolution via Constrained Flows ICML 2023