Pheng-Ann Heng
The Chinese University of Hong Kong
744 Papers
3.5K Citations
Pheng-Ann Heng is an academic researcher from The Chinese University of Hong Kong. The author has contributed to research in topics: Computer science & Segmentation. The author has an hindex of 75, co-authored 646 publications. Previous affiliations of Pheng-Ann Heng include Stanford University & Zhejiang University.
Chat about Author
Papers
Reconfigurable interlocking furniture
TL;DR: This paper presents computational methods as tools to assist the design and construction of reconfigurable assemblies, typically for furniture, and forms the backward interlocking and multi-key interlocking models, with which to iteratively plan the joints consistently over multiple forms.
AGNet: Attention-Guided Network for Surgical Tool Presence Detection
Xiaowei Hu,Lequan Yu,Hao Chen,Jing Qin,Pheng-Ann Heng +4 more
- 14 Sep 2017
TL;DR: The proposed attention-guided network (AGNet) achieves state-of-the-art performance on m2cai16-tool dataset and surpasses the winner in 2016 by a significant margin.
PFA-ScanNet: Pyramidal Feature Aggregation with Synergistic Learning for Breast Cancer Metastasis Analysis
Zixu Zhao,Huangjing Lin,Hao Chen,Pheng-Ann Heng +3 more
- 13 Oct 2019
TL;DR: Wang et al. as mentioned in this paper proposed a novel pyramid feature aggregation scan network (PFA-ScanNet) for robust and fast analysis of breast cancer metastasis from whole slide images (WSIs).
Segmentation of human skull in MRI using statistical shape information from CT data
TL;DR: To automatically segment the skull from the MRI data using a model‐based three‐dimensional segmentation scheme with real-time information about skull volume and skull structure is presented.
Improving AlphaFlow for Efficient Protein Ensembles Generation
Shaoning Li,Mingyu Li,Yusong Wang,Xinheng He,Nanning Zheng,Jian Zhang,Pheng-Ann Heng +6 more
TL;DR: This study improves AlphaFlow for efficient protein ensemble generation by introducing AlphaFlow-Lit, a feature-conditioned generative model that accelerates sampling by 47 times, outperforming its distilled version and achieving comparable results to AlphaFlow.