14 citations · 64 across the 14 of their papers we have counts for
14 papers
WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration
Xinxing Cheng, Xi Jia, Wenqi Lu +4
Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense d…
Rediscovering BCE Loss for Uniform Classification
Qiufu Li, Xi Jia, Jiancan Zhou +2
This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sa…
UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition
Qiufu Li, Xi Jia, Jiancan Zhou +2
Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require…
Recovering high-quality FODs from a reduced number of diffusion-weighted images using a model-driven deep learning architecture
J Bartlett, C E Davey, L A Johnston +1
Fibre orientation distribution (FOD) reconstruction using deep learning has the potential to produce accurate FODs from a reduced number of diffusion-weighted images (DWIs), decrea…
Fourier-Net+: Leveraging Band-Limited Representation for Efficient 3D Medical Image Registration
Xi Jia, Alexander Thorley, Alberto Gomez +3
U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields, which for high-resolution volumetric image data is a resource-in…
Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline
Tiantian Geng, Teng Wang, Jinming Duan +2
Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos o…
Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation
Wei Chen, Xi Jia, Zhongqun Zhang +4
In this paper, we propose a novel 3D graph convolution based pipeline for category-level 6D pose and size estimation from monocular RGB-D images. The proposed method leverages an e…
Fourier-Net: Fast Image Registration with Band-limited Deformation
Xi Jia, Joseph Bartlett, Wei Chen +6
Unsupervised image registration commonly adopts U-Net style networks to predict dense displacement fields in the full-resolution spatial domain. For high-resolution volumetric imag…
U-Net vs Transformer: Is U-Net Outdated in Medical Image Registration?
Xi Jia, Joseph Bartlett, Tianyang Zhang +3
Due to their extreme long-range modeling capability, vision transformer-based networks have become increasingly popular in deformable image registration. We believe, however, that…
Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration
Alexander Thorley, Xi Jia, Hyung Jin Chang +8
Deterministic approaches using iterative optimisation have been historically successful in diffeomorphic image registration (DiffIR). Although these approaches are highly accurate,…
Learning a Model-Driven Variational Network for Deformable Image Registration
Xi Jia, Alexander Thorley, Wei Chen +9
Data-driven deep learning approaches to image registration can be less accurate than conventional iterative approaches, especially when training data is limited. To address this wh…
FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism
Wei Chen, Xi Jia, Hyung Jin Chang +3
In this paper, we focus on category-level 6D pose and size estimation from monocular RGB-D image. Previous methods suffer from inefficient category-level pose feature extraction wh…
Geometry Constrained Weakly Supervised Object Localization
Weizeng Lu, Xi Jia, Weicheng Xie +3
We propose a geometry constrained network, termed GC-Net, for weakly supervised object localization (WSOL). GC-Net consists of three modules: a detector, a generator and a classifi…
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
Wei Chen, Xi Jia, Hyung Jin Chang +2
In this paper, we propose a novel real-time 6D object pose estimation framework, named G2L-Net. Our network operates on point clouds from RGB-D detection in a divide-and-conquer fa…