AIConfPaper
← Search

Ho Kei Cheng

10 accepted papers

2026

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

Samin Mahdizadeh Sani, Max Ku, Nima Jamali, Matina Mahdizadeh Sani, Paria Khoshtab, Wei-Chieh Sun +20
ICLR 2026poster

Advances in diffusion, autoregressive, and hybrid models have enabled high-quality image synthesis for tasks such as text-to-image, editing, and reference-guided composition. Yet, existing benchmarks remain limited, either focus on isolated tasks, cover only narrow domains, or provide opaque scores…

Cited by 0Source ↗code ↗Scholar ↗
2026

SAM 3: Segment Anything with Concepts

Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris Coll-Vinent +32
ICLR 2026poster

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short noun phrases (e.g., “yellow school bus”), image exemplars, or a combination of both. Promptable Concept Segmentation (P…

Cited by 687Source ↗code ↗Scholar ↗
2025

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

Ho Kei Cheng, Masato Ishii, Akio Hayakawa, Takashi Shibuya, Alexander Schwing, Yuki Mitsufuji
CVPR 2025poster

We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework (MMAudio). In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

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

Ho Kei Cheng, Alexander Schwing
ICCV 2025poster

Minibatch optimal transport coupling straightens paths in unconditional flow matching. This leads to computationally less demanding inference as fewer integration steps and less complex numerical solvers can be employed when numerically solving an ordinary differential equation at test time. However…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Putting the Object Back into Video Object Segmentation

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Joon-Young Lee, Alexander Schwing
CVPR 2024highlight

We present Cutie a video object segmentation (VOS) network with object-level memory reading which puts the object representation from memory back into the video object segmentation result. Recent works on VOS employ bottom-up pixel-level memory reading which struggles due to matching noise especiall…

Cited by 98Source ↗PDF ↗code ↗Scholar ↗
2023

Tracking Anything with Decoupled Video Segmentation

Ho Kei Cheng, Seoung Wug Oh, Brian Price, Alexander Schwing, Joon-Young Lee
ICCV 2023poster

Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmen…

Cited by 269PDF ↗code ↗Scholar ↗
2022

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

Ho Kei Cheng, Alexander G. Schwing
ECCV 2022poster

"We present XMem, a video object segmentation architecture for long videos with unified feature memory stores inspired by the Atkinson-Shiffrin memory model. Prior work on video object segmentation typically only uses one type of feature memory. For videos longer than a minute, a single feature memo…

Cited by 480Source ↗PDF ↗code ↗Scholar ↗
2021

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

Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang
CVPR 2021poster

We present Modular interactive VOS (MiVOS) framework which decouples interaction-to-mask and mask propagation, allowing for higher generalizability and better performance. Trained separately, the interaction module converts user interactions to an object mask, which is then temporally propagated by…

Cited by 256PDF ↗code ↗Scholar ↗
2021

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

Ho Kei Cheng, Yu-Wing Tai, Chi-Keung Tang
NeurIPS 2021poster

This paper presents a simple yet effective approach to modeling space-time correspondences in the context of video object segmentation. Unlike most existing approaches, we establish correspondences directly between frames without re-encoding the mask features for every object, leading to a highly ef…

Cited by 398Source ↗PDF ↗code ↗Scholar ↗
2020

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

Ho Kei Cheng, Jihoon Chung, Yu-Wing Tai, Chi-Keung Tang
CVPR 2020poster

State-of-the-art semantic segmentation methods were almost exclusively trained on images within a fixed resolution range. These segmentations are inaccurate for very high-resolution images since using bicubic upsampling of low-resolution segmentation does not adequately capture high-resolution detai…

Cited by 289PDF ↗code ↗Scholar ↗