Binxiao Huang

Binxiao Huang

Auto-generated profile, based on publicly available information

Binxiao Huang

The University of Hong Kong

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2022
Verified
Book Chapter
Closed access
PDF file
CLChang Liu
Chang Liu
XQXiaoyan Qian
Xiaoyan Qian
BHBinxiao Huang
Binxiao Huang
XQXiaojuan Qi
Xiaojuan Qi
ELEdmund Lam
Edmund Lam
NWNgai Wong
Ngai Wong

5 November 2024
Verified
Book Chapter
Closed access
PDF file
SYSidi Yang
Sidi Yang
BHBinxiao Huang
Binxiao Huang
MCMingdeng Cao
Mingdeng Cao
YJYatai Ji
Yatai Ji
HGHanzhong Guo
Hanzhong Guo
YYYujiu Yang
Yujiu Yang

24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
JLJason Chun Lok Li
Jason Chun Lok Li
CLChang Liu
Chang Liu
BHBinxiao Huang
Binxiao Huang
NWNgai Wong
Ngai Wong
Existing approaches to Implicit Neural Representation (INR) can be interpreted as a global scene representation via a linear combination of Fourier bases of different frequencies. However, such universal basis functions can limit the representation capability in local regions where a specific component is unnecessary, resulting in unpleasant artifacts. To this end, we introduce a learnable spatial mask that effectively dispatches distinct Fourier bases into respective regions. This translates into collaging Fourier patches, thus enabling an accurate representation of complex signals. Comprehensive experiments demonstrate the superior reconstruction quality of the proposed approach over existing baselines across various INR tasks, including image fitting, video representation, and 3D shape representation. Our method outperforms all other baselines, improving the image fitting PSNR by over 3dB and 3D reconstruction to 98.81 IoU and 0.0011 Chamfer Distance.

27 October 2025
Verified
Conference Paper
Open access
YCYuxin Cheng
Yuxin Cheng
BHBinxiao Huang
Binxiao Huang
WZWenyong Zhou
Wenyong Zhou
TWTaiqiang Wu
Taiqiang Wu
Zhengwu LiuZhengwu Liu
Zhengwu Liu
NWNgai Wong
Ngai Wong

14 November 2023 in arXiv
Verified
Preprint
Open access
PDF file
RLRui Lin
Rui Lin
JLJason Chun Lok Li
Jason Chun Lok Li
JZJiajun Zhou
Jiajun Zhou
BHBinxiao Huang
Binxiao Huang
JRJie Ran
Jie Ran
NWNgai Wong
Ngai Wong
Most deep neural networks (DNNs) consist fundamentally of convolutional and/or fully connected layers, wherein the linear transform can be cast as the product between a filter matrix and a data matrix obtained by arranging feature tensors into columns. The lately proposed deformable butterfly (DeBut) decomposes the filter matrix into generalized, butterflylike factors, thus achieving network compression orthogonal to the traditional ways of pruning or low-rank decomposition. This work reveals an intimate link between DeBut and a systematic hierarchy of depthwise and pointwise convolutions, which explains the empirically good performance of DeBut layers. By developing an automated DeBut chain generator, we show for the first time the viability of homogenizing a DNN into all DeBut layers, thus achieving an extreme sparsity and compression. Various examples and hardware benchmarks verify the advantages of All-DeBut networks. In particular, we show it is possible to compress a PointNet to < 5% parameters with < 5% accuracy drop, a record not achievable by other compression schemes.

13 September 2026
Verified
Book Chapter
Closed access
PDF file
ZAZhilin Ai
Zhilin Ai
BLBoyu Li
Boyu Li
SYSidi Yang
Sidi Yang
WSWenqing Shi
Wenqing Shi
WZWenyong Zhou
Wenyong Zhou
NWNgai Wong
Ngai Wong