Quhui Ke — accepted AI-conference papers

2026

SegPVSG: Panoptic Video Scene Graph Generation via Temporal Focusing and Generative Augmentation

YiKai Li, Quhui Ke, Jinglin Liang, Zhiyuan Zhang, Zhidi Lin, Shuangping Huang

ICML 2026poster

Panoptic Video Scene Graph Generation (PVSG) aims to identify relations between pixel-level entities in a video, serving as a novel paradigm for structured video parsing. However, this task faces two key challenges. First, the interactions between entities are temporally fragmented and sparse, meani…

Cited by 0 Source ↗Scholar ↗

2024

One-Shot Diffusion Mimicker for Handwritten Text Generation

Gang Dai, Yifan Zhang, Quhui Ke, Qiangya Guo, Shuangping Huang*

ECCV 2024poster

"Existing handwritten text generation methods often require more than ten handwriting samples as style references. However, in practical applications, users tend to prefer a handwriting generation model that operates with just a single reference sample for its convenience and efficiency. This approa…

Cited by 14 Source ↗PDF ↗code ↗Scholar ↗