Minho Shim

4

Papers

12

Total Citations

Papers (4)

Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs

Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval

Decomposed Cross-Modal Distillation for RGB-Based Temporal Action Detection

READ: Reciprocal Attention Discriminator for Image-to-Video Re-Identification