Source Themes

Wearable-based behaviour interpolation for semi-supervised human activity recognition
Attention for semi-supervised human activity recognition
Haoran Duan, Shidong Wang, Varun Ojha, Shizheng Wang, Yawen Huang, Yang Long, Rajiv Ranjan, Yefeng Zheng
PDF Cite DOI
Wearable-based behaviour interpolation for semi-supervised human activity recognition
MRL-Seg: Overcoming Imbalance in Medical Image Segmentation with Multi-Step Reinforcement Learning
Medical image segmentation is a critical task for clinical diagnosis and research. However, dealing with highly imbalanced data remains …
Feiyang Yang, Xiongfei Li, Haoran Duan, Feilong Xu, Yawen Huang, Xiaoli Zhang, Yang Long, Yefeng Zheng
PDF DOI
MRL-Seg: Overcoming Imbalance in Medical Image Segmentation with Multi-Step Reinforcement Learning
A Self-supervised Residual Feature Learning Model for Multi-focus Image Fusion
Multi-focus image fusion (MFIF) attempts to achieve an “all-focused” image from multiple source images with the same scene but …
Zeyu Wang, Xiongfei Li, Haoran Duan, Xiaoli Zhang
PDF DOI
A Self-supervised Residual Feature Learning Model for Multi-focus Image Fusion
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
With increasing concerns over data privacy and model copyrights, especially in the context of collaborations between AI service …
Fan Wan, Xingyu Miao, Haoran Duan, Jingjing Deng, Rui Gao, Yang Long
PDF DOI
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields
Most of the existing works on arbitrary 3D NeRF style transfer required retraining on each single style condition. This work aims to …
Xingyu Miao, Yang Bai, Haoran Duan, Fan Wan, Yawen Huang, Yang Long, Yefeng Zheng
PDF DOI
ConRF: Zero-shot Stylization of 3D Scenes with Conditioned Radiation Fields
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
The goal of our work is to generate high-quality novel views from monocular videos of complex and dynamic scenes. Prior methods, such …
Xingyu Miao, Yang Bai, Haoran Duan, Yawen Huang, Fan Wan, Yang Long, Yefeng Zheng
PDF DOI
CTNeRF: Cross-Time Transformer for Dynamic Neural Radiance Field from Monocular Video
Dynamic Unary Convolution in Transformers
Hybrid Transformer with help of convolution operations for various tasks.
Haoran Duan, Yang Long, Shidong Wang, Haofeng Zhang, Chris G Willcocks, Ling Shao
PDF Cite DOI
Dynamic Unary Convolution in Transformers
Rules for Expectation: Learning to Generate Rules via Social Environment Modelling
The evolution of natural life is guided by a perpetually adaptive set of rules, encompassing natural laws, human policies, and game …
Jiyao Pu, Haoran Duan, Junzhe Zhao, Yang Long
PDF DOI
Rules for Expectation: Learning to Generate Rules via Social Environment Modelling
UniHead: Unifying Multi-Perception for Detection Heads
The detection head constitutes a pivotal component within object detectors, tasked with executing both classification and localization …
Hantao Zhou, Rui Yang, Yachao Zhang, Haoran Duan, Yawen Huang, Runze Hu, Xiu Li, Yefeng Zheng
PDF Code DOI
UniHead: Unifying Multi-Perception for Detection Heads
Dynamic visual-guided selection for zero-shot learning
Zero-shot learning (ZSL) methods currently employed to identify seen or unseen classes rely on semantic attribute prototypes or class …
Fan Wan, Xingyu Miao, Haoran Duan, Jingjing Deng, Rui Gao, Yang Long
PDF DOI
Dynamic visual-guided selection for zero-shot learning