12 citations
- Nanyang Technological UniversitySG3 papers
- Aalto UniversityFI1 paper
- Alibaba Group (Cayman Islands)KY1 paper
- Alibaba Group (United States)US1 paper
- BC Children's HospitalCA1 paper
- Chinese University of Hong KongHK1 paper
- Hong Kong Polytechnic UniversityHK1 paper
- Joint NTU-UBC Research Centre of Excellence in Active Living for the ElderlySG1 paper
- Macau University of Science and TechnologyMO1 paper
- Microsoft (United States)US1 paper
- Mitchell InstituteUS1 paper
- Monash UniversityAU1 paper
6 papers
A Survey on 3D Skeleton Based Person Re-Identification: Taxonomy, Advances, Challenges, and Interdisciplinary Prospects
Haocong Rao, Chunyan Miao
Person re-identification via 3D skeletons is an important emerging research area that attracts increasing attention within the pattern recognition community. With distinctive advan…
Comprehensive framework for evaluation of deep neural networks in detection and quantification of lymphoma from PET/CT images: clinical insights, pitfalls, and observer agreement analyses
Shadab Ahamed, Yixi Xu, Sara Kurkowska +12
This study addresses critical gaps in automated lymphoma segmentation from PET/CT images, focusing on issues often overlooked in existing literature. While deep learning has been a…
Neural Parametric Surfaces for Shape Modeling
Lei Yang, Yongqing Liang, Xin Li +6
The recent surge of utilizing deep neural networks for geometric processing and shape modeling has opened up exciting avenues. However, there is a conspicuous lack of research effo…
CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning
Chenyu Sun, Hangwei Qian, Chunyan Miao
In reinforcement learning (RL), it is challenging to learn directly from high-dimensional observations, where data augmentation has recently been shown to remedy this via encoding…
Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework
Jiawen Kang, Zehui Xiong, Chunxiao Jiang +6
The emerging Federated Edge Learning (FEL) technique has drawn considerable attention, which not only ensures good machine learning performance but also solves "data island" proble…
Hybrid Channel Pre-Inversion and Interference Alignment Strategies
David Karpuk, Peter Moss
In this paper we consider strategies for MIMO interference channels which combine the notions of interference alignment and channel pre-inversion. Users collaborate to form data-sh…