9 papers · 1 filter
OphBiWSSD: Scaling Temporal Action Localization in Ophthalmic Surgeries with Bidirectional Weight-tied State Space Duality
Yang Liu, Qionghong Ma, Joongwon Chae +10
High-frequency surgical maneuvers in ophthalmology necessitate high-fidelity temporal modeling, yet characterizing long-range procedural dependencies remains computationally prohib…
What Remains Normal? Clean Images Miss Useful Near-Defect Normal Patches for Anomaly Detection
Joongwon Chae, Runming Wang, Peiwu Qin
Normal-only industrial anomaly detectors use patches from clean training images as normal references or reconstruction targets. This assumes that clean patches are sufficient for t…
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…
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…
StructCore: Structure-Aware Image-Level Scoring for Training-Free Unsupervised Anomaly Detection
Joongwon Chae, Lihui Luo, Yang Liu +8
Max pooling is the de facto standard for converting anomaly score maps into image-level decisions in memory-bank-based unsupervised anomaly detection (UAD). However, because it rel…
GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection
Joongwon Chae, Lihui Luo, Yang Liu +8
Feature-based anomaly detection is widely adopted in industrial inspection due to the strong representational power of large pre-trained vision encoders. While most existing method…
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…
Grid-augmented vision: A simple yet effective approach for enhanced spatial understanding in multi-modal agents
Joongwon Chae, Zhenyu Wang, Lian Zhang +2
Recent advances in multimodal models have demonstrated impressive capabilities in object recognition and scene understanding. However, these models often struggle with precise spat…
SJTU:Spatial judgments in multimodal models towards unified segmentation through coordinate detection
Joongwon Chae, Zhenyu Wang, Peiwu Qin
Despite significant advances in vision-language understanding, implementing image segmentation within multimodal architectures remains a fundamental challenge in modern artificial…