Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Minseok Joo

Minseok Joo

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

Vision×1

Frequent co-authors

Dogyun Park1×
Taehoon Lee1×
Kyujin Lee1×
Hyunwoo J. Kim1×

Research Timeline

2026
Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

The paper proposes COVRAG, a depth-based memory retrieval framework that maximizes the coverage of target-view regions to significantly improve long-term geometric consistency in autoregressive long video generation.

Highlighted terms show continued research focus across papers

Papers

cs.CVRecentJun 1, 2026

Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation

Minseok Joo, Dogyun Park, Taehoon Lee, Kyujin Lee +1 more

The paper proposes COVRAG, a depth-based memory retrieval framework that maximizes the coverage of target-view regions to significantly improve long-term geometric consistency in autoregressive long v…

View →