8 citations
- Korea Advanced Institute of Science and TechnologyKR10 papers
- King Abdullah University of Science and TechnologySA2 papers
- Changwon National UniversityKR1 paper
- Chosun UniversityKR1 paper
- Gist (Czechia)CZ1 paper
- Hispanics in PhilanthropyUS1 paper
- HyPerComp Engineering (United States)US1 paper
- Hyperion Technologies (Canada)CA1 paper
- Ministry of Information, Communications and TechnologySZ1 paper
- Sogang UniversityKR1 paper
- University High SchoolUS1 paper
- University of OxfordGB1 paper
5 papers · 1 filter
Splat-based 3D Scene Reconstruction with Extreme Motion-blur
Hyeonjoong Jang, Dongyoung Choi, Donggun Kim +2
We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim ill…
EgoGapBench: Benchmarking Egocentric Action Selection in Multi-Agent Scenes
Jihyeok Jung, Jeewu Lee, Sanghyeop Kim +2
Existing egocentric benchmarks have primarily constructed the egocentric setting from first-person-view data, which makes it difficult to evaluate egocentric perspective itself in…
ProtoKV: Streaming Video Understanding under Delayed Query with Summary-State Memory
Le Tu Ngoc Minh, Jinyeong Lim, Dongsu Han
Streaming video understanding (SVU) must answer queries that arrive asynchronously while visual tokens stream continuously under strict GPU-memory and query-time latency budgets. A…
Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization
Paul Hyunbin Cho, Jinhyuk Jang, SeokYoung Lee +7
Diffusion-based lip synchronization models achieve strong visual quality and audio-visual alignment, but full-sequence bidirectional attention and many denoising steps make them im…
CXR-LT 2026 Challenge: Projection-Aware Multi-Label and Zero-Shot Chest X-Ray Classification
Juno Cho, Dohui Kim, Mingeon Kim +3
This challenge tackles multi-label classification for known chest X-ray (CXR) lesions and zero-shot classification for unseen ones. To handle diverse CXR projections, we integrate…