From the 1 of 10 linked papers with an AI index.
10 papers
What Remains Normal? Clean Images Miss Useful Near-Defect Normal Patches for Anomaly Detection
Joongwon Chae, Runming Wang, Peiwu Qin
Memory-based anomaly detectors store nominal training patches and score test patches against this memory. A patch selected for coverage therefore becomes a nor- mal reference witho…
What Memory Composition Does Not Tell Us About Anomaly Detection
Joongwon Chae, Runming Wang, Peiwu Qin
Memory-based anomaly detectors store nominal training patches and score test patches against this memory. A patch selected for coverage therefore becomes a nor- mal reference witho…
Auditable Context-Aware HFMD Forecasting with Structured LLM Agents
Joongwon Chae, Runming Wang, Chen Xiong +5
The paper introduces a neuro‑symbolic system that uses two LLM‑driven agents to interpret contextual factors (e.g., school calendars, weather, policy reports) and combine them with…
Memory-SAM: Human-Prompt-Free Tongue Segmentation via Retrieval-to-Prompt
Joongwon Chae, Lihui Luo, Xi Yuan +4
Accurate tongue segmentation is crucial for reliable TCM analysis. Supervised models require large annotated datasets, while SAM-family models remain prompt-driven. We present Memo…
ProCon: Projection-Consistency Memory for Training-Free Anomaly Detection
Joongwon Chae, Lihui Luo, Yang Liu +4
Memory-based anomaly detection is attractive because it localizes defects from normal images without training a decoder or synthesizing pseudo anomalies. However, most memory metho…
MMIR-TCM: Memory-Integrated Multimodal Inference and Retrieval for TCM Clinical Decision Support
Lihui Luo, Joongwon Chae, Ziyan Chen +13
Traditional Chinese Medicine (TCM) diagnosis, particularly through tongue inspection, faces persistent challenges in subjectivity and reproducibility. The application of multimodal…