Joon-Young Lee

48

Papers

567

Total Citations

Papers (48)

URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale Benchmark

Putting the Object Back into Video Object Segmentation

What do I Annotate Next? An Empirical Study of Active Learning for Action Localization

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

Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence

Learning Video Representations From Correspondence Proposals

Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks

Deep Video Inpainting

Video Panoptic Segmentation

Active Speakers in Context

Learning Visual Emotion Representations From Web Data

Exemplar-Based Open-Set Panoptic Segmentation Network

Learning To Associate Every Segment for Video Panoptic Segmentation

Polygonal Point Set Tracking

Per-Clip Video Object Segmentation

Unsupervised Learning of Debiased Representations With Pseudo-Attributes

A Generalized Framework for Video Instance Segmentation

Mask-Guided Matting in the Wild

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

Complementary Sets of Shutter Sequences for Motion Deblurring

Reflectance Capture Using Univariate Sampling of BRDFs

Exploring Temporally-Aware Features for Point Tracking

Video Object Segmentation Using Space-Time Memory Networks

Hierarchical Memory Matching Network for Video Object Segmentation

Tracking Anything with Decoupled Video Segmentation

Long-range Multimodal Pretraining for Movie Understanding

XMem++: Production-level Video Segmentation From Few Annotated Frames

The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing

Tracking by Associating Clips

Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection

One-Trimap Video Matting

Onion-Peel Networks for Deep Video Completion

EntitySAM: Segment Everything in Video

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

Robust and Consistent Online Video Instance Segmentation via Instance Mask Propagation

One-Day Outdoor Photometric Stereo via Skylight Estimation

Automatic Content-Aware Color and Tone Stylization

Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions

Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks

Distort-and-Recover: Color Enhancement Using Deep Reinforcement Learning

Fast Video Object Segmentation by Reference-Guided Mask Propagation

VITA: Video Instance Segmentation via Object Token Association