We present SAM3Dual, our third-place solution to the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. SAM3Dual is a training-free inference extension of pretrained SAM 3 that explicitly separates temporal memory into a short-term branch for recent observations and a long-ter...
Jeongrae Kim, Chaehyun Kim, Changwon Lim· 0 citations
Medical image captioning requires translating heterogeneous visual evidence into concise clinical descriptions, where errors in findings, assertion states, or anatomical relations can alter clinical meaning despite surface-level fluency. Sequence-level policy optimization can directly optimize complete captions, but co...
Hyun Jun Kim, Heeseung Shin, Changwon Lim· 0 citations
A continuity-driven representation regularization framework that exploits normal-dominant regions as dense auxiliary supervision for industrial defect detection, particularly when annotated data are scarce is proposed.
Minjong Kim, Hyun Jun Kim, Jeongrae Kim et al.· 0 citations
This report summarizes the 8th Large-scale Video Object Segmentation (LSVOS) Challenge, held in conjunction with ECCV 2026. The challenge evaluates video segmentation in three complementary settings: complex semi-supervised video object segmentation on MOSEv2, text-guided referring video object segmentation on MeViSv2-...
Chang Liu, Heng-Hui Ding, Ling-Yi Hong et al.· 0 citations
SAM2Dual is proposed, a training-free, plug-and-play inference-time enhancement that improves long-video robustness without updating model weights and Text-Aware Memory is presented, which extracts a compact word-level cue from early frames and uses text embeddings to reweight memory contributions based on semantic com...
A framework that strengthens clinical alignment by separating and enhancing training-time alignment and inference-time alignment is proposed and experiments show that complementary visual representations with a multi-encoder design and concept-level auxiliary learning help preserve clinically meaningful information.
Yunseo Lee, Hyun Jun Kim, Heeseung Shin et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
