4 papers
ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
Hosu Lee, Junho Kim, Hyunjun Kim +1
Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame s…
STRIDE: When to Speak Meets Sequence Denoising for Streaming Video Understanding
Junho Kim, Hosu Lee, James M. Rehg +2
Recent progress in video large language models (Video-LLMs) has enabled strong offline reasoning over long and complex videos. However, real-world deployments increasingly require…
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
Junho Kim, Hyunjun Kim, Hosu Lee +1
Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory over…
Look Every Frame All at Once: Video-Mamba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
Hosu Lee, Junho Kim, Hyunjun Kim +1
With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computatio…