Joon-Young Lee

12

Papers

273

Total Citations

Papers (12)

Putting the Object Back into Video Object Segmentation

Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models

Generative Video Propagation

FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

MaGGIe: Masked Guided Gradual Human Instance Matting

Seurat: From Moving Points to Depth

Elevating Flow-Guided Video Inpainting with Reference Generation

Video Color Grading via Look-Up Table Generation

Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation

Exploring Temporally-Aware Features for Point Tracking

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

EntitySAM: Segment Everything in Video