Ho Kei Cheng

ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks

arXiv 2026

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

ICCV 2025

SAM 3: Segment Anything with Concepts

arXiv 2025

MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

CVPR 2025 1

Tracking Anything with Decoupled Video Segmentation

ICCV 2023 1

Putting the Object Back into Video Object Segmentation

CVPR 2024 1

XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

arXiv 2022

Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

NeurIPS 2021 12

Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion

CVPR 2021 1

CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

cascadepsp-toward-class-agnostic-and-very-1

Alexander Schwing

Chi-Keung Tang

Yu-Wing Tai

Brian Price

Joon-Young Lee

Seoung Wug Oh

Aishwarya Kamath

Akio Hayakawa

Alexander G. Schwing

Andrew Huang