Search Results for author:
Found 66 papers, 27 papers with code
Binomial Self-compensation for Motion Error in Dynamic 3D Scanning
Phase shifting profilometry (PSP) is favored in high-precision 3D scanning due to its high accuracy, robustness, and pixel-wise property.
A diffusion MRI tractography atlas for concurrent white matter mapping across Eastern and Western populations
However, a comprehensive investigation into WM fiber tracts between Eastern and Western populations is challenged due to the lack of a cross-population WM atlas and the large site-specific variability of dMRI data.
RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection
In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two encoders.
Ranked #2 on
3D Object Detection
on nuscenes Camera-Radar
PASTA: Towards Flexible and Efficient HDR Imaging Via Progressively Aggregated Spatio-Temporal Alignment
Leveraging Transformer attention has led to great advancements in HDR deghosting.
S^2MVTC: a Simple yet Efficient Scalable Multi-View Tensor Clustering
Specifically, we first construct the embedding feature tensor by stacking the embedding features of different views into a tensor and rotating it.
Deep unfolding Network for Hyperspectral Image Super-Resolution with Automatic Exposure Correction
In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR).
Inverse-Free Fast Natural Gradient Descent Method for Deep Learning
Firstly, we reformulate the gradient preconditioning formula in the natural gradient descent (NGD) as a weighted sum of per-sample gradients using the Sherman-Morrison-Woodbury formula.
TERM Model: Tensor Ring Mixture Model for Density Estimation
However, a substantial number of potential tensor permutations can lead to a tensor network with the same structure but varying expressive capabilities.
A Novel Deep Clustering Framework for Fine-Scale Parcellation of Amygdala Using dMRI Tractography
The amygdala plays a vital role in emotional processing and exhibits structural diversity that necessitates fine-scale parcellation for a comprehensive understanding of its anatomico-functional correlations.
Phase Guided Light Field for Spatial-Depth High Resolution 3D Imaging
On 3D imaging, light field cameras typically are of single shot, and however, they heavily suffer from low spatial resolution and depth accuracy.
Federated Deep Multi-View Clustering with Global Self-Supervision
Second, the storage and usage of data from multiple clients in a distributed environment can lead to incompleteness of multi-view data.
Low-Rank Multitask Learning based on Tensorized SVMs and LSSVMs
In contrast to previous MTL frameworks, our decision function in the dual induces a weighted kernel function with a task-coupling term characterized by the similarities of the task-specific factors, better revealing the explicit relations across tasks in MTL.
Tensor Regression
Tensors, as high dimensional extensions of vectors, are considered as natural representations of high dimensional data.
Feature Modulation Transformer: Cross-Refinement of Global Representation via High-Frequency Prior for Image Super-Resolution
Transformer-based methods have exhibited remarkable potential in single image super-resolution (SISR) by effectively extracting long-range dependencies.
Ranked #26 on
Image Super-Resolution
on Set14 - 4x upscaling
Multi-view MERA Subspace Clustering
Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor.
Illumination-insensitive Binary Descriptor for Visual Measurement Based on Local Inter-patch Invariance
Existing binary descriptors may not perform well for long-term visual measurement tasks due to their sensitivity to illumination variations.
Level-line Guided Edge Drawing for Robust Line Segment Detection
Line segment detection plays a cornerstone role in computer vision tasks.
Adaptively Topological Tensor Network for Multi-view Subspace Clustering
Therefore, a pre-defined tensor decomposition may not fully exploit low rank information for a certain dataset, resulting in sub-optimal multi-view clustering performance.
A Comprehensive Review of Image Line Segment Detection and Description: Taxonomies, Comparisons, and Challenges
The challenges in existing methods and corresponding insights for potentially solving them are also provided to inspire researchers.
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training
However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not environmental-friendly with much power cost.
Tensorized LSSVMs for Multitask Regression
Multitask learning (MTL) can utilize the relatedness between multiple tasks for performance improvement.
FedTADBench: Federated Time-Series Anomaly Detection Benchmark
We would like to answer the following questions: (1)How is the performance of time series anomaly detection algorithms when meeting federated learning?
Deep Negative Correlation Classification
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Tucker-O-Minus Decomposition for Multi-view Tensor Subspace Clustering
To alleviate these problems, we propose a new tensor decomposition called Tucker-O-Minus Decomposition (TOMD) for multi-view clustering.
KUNet: Imaging Knowledge-Inspired Single HDR Image Reconstruction
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions.
Learning Nonlocal Sparse and Low-Rank Models for Image Compressive Sensing
Furthermore, we present a unified framework for incorporating various GSR and LR models and discuss the relationship between GSR and LR models.
Semi-tensor Product-based TensorDecomposition for Neural Network Compression
Tucker decomposition, Tensor Train (TT) and Tensor Ring (TR) are common decomposition for low rank compression of deep neural networks.
Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detection
Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data.
Supervised Anomaly Detection
Weakly-supervised Anomaly Detection
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models.
Real-World Single Image Super-Resolution: A Brief Review
More specifically, this review covers the critical publically available datasets and assessment metrics for RSISR, and four major categories of RSISR methods, namely the degradation modeling-based RSISR, image pairs-based RSISR, domain translation-based RSISR, and self-learning-based RSISR.
Scalable Deep Compressive Sensing
In this paper, we develop a general framework named scalable deep compressive sensing (SDCS) for the scalable sampling and reconstruction (SSR) of all existing end-to-end-trained models.
Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration
In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.
Decision-based Universal Adversarial Attack
A single perturbation can pose the most natural images to be misclassified by classifiers.
Siamese Network for RGB-D Salient Object Detection and Beyond
Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.
Ranked #3 on
RGB-D Salient Object Detection
on STERE
Deep Embedded Multi-view Clustering with Collaborative Training
Firstly, the embedded representations of multiple views are learned individually by deep autoencoders.
Hyperspectral Image Denoising with Partially Orthogonal Matrix Vector Tensor Factorization
In this paper, we present a HSI restoration method named smooth and robust low rank tensor recovery.
Bayesian Low Rank Tensor Ring Model for Image Completion
Low rank tensor ring model is powerful for image completion which recovers missing entries in data acquisition and transformation.
Unsupervised Feature Selection via Multi-step Markov Transition Probability
Our main contributions are a novel feature section approach which uses multi-step transition probability to characterize the data structure, and three algorithms proposed from the positive and negative aspects for keeping data structure.
Disentanglement Then Reconstruction: Learning Compact Features for Unsupervised Domain Adaptation
By this reconstructor, we can construct prototypes for the original features using class prototypes and domain prototypes correspondingly.
Learning Various Length Dependence by Dual Recurrent Neural Networks
Many variants of RNN have been proposed to solve the gradient problems of training RNNs and process long sequences.
The Power of Triply Complementary Priors for Image Compressive Sensing
In this paper, we propose a joint low-rank and deep (LRD) image model, which contains a pair of triply complementary priors, namely \textit{external} and \textit{internal}, \textit{deep} and \textit{shallow}, and \textit{local} and \textit{non-local} priors.
ProbaNet: Proposal-balanced Network for Object Detection
Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall performance.
AMP-Net: Denoising based Deep Unfolding for Compressive Image Sensing
By unfolding the iterative optimization algorithm for model-based methods onto networks, deep unfolding methods have the good interpretation of model-based methods and the high speed of classical deep network methods.
Frequency-Weighted Robust Tensor Principal Component Analysis
The newly obtained frequency-weighted RTPCA can be solved by alternating direction method of multipliers, and it is the first time that frequency analysis is taken in tensor principal component analysis.
DaST: Data-free Substitute Training for Adversarial Attacks
In this paper, we propose a data-free substitute training method (DaST) to obtain substitute models for adversarial black-box attacks without the requirement of any real data.
Adversarial Imitation Attack
Then, the adversarial examples generated by the imitation model are utilized to fool the attacked model.
A Unified Framework for Coupled Tensor Completion
To let coupled tensors help each other for missing component estimation, in this paper we utilize TR for coupled completion by sharing parts of the latent factors.
Distribution-Aware Coordinate Representation for Human Pose Estimation
Interestingly, we found that the process of decoding the predicted heatmaps into the final joint coordinates in the original image space is surprisingly significant for human pose estimation performance, which nevertheless was not recognised before.
Ranked #2 on
Multi-Person Pose Estimation
on MS COCO
(using extra training data)
C3AE: Exploring the Limits of Compact Model for Age Estimation
Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models.
Ranked #3 on
Age Estimation
on FGNET
Robust Low-Rank Tensor Ring Completion
To further deal with its sensitivity to sparse component as it does in tensor principle component analysis, we propose robust tensor ring completion (RTRC), which separates latent low-rank tensor component from sparse component with limited number of measurements.
Low-rank Tensor Grid for Image Completion
The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones.
Provable Tensor Ring Completion
Tensor completion recovers a multi-dimensional array from a limited number of measurements.
From Rank Estimation to Rank Approximation: Rank Residual Constraint for Image Restoration
Towards this end, we first obtain a good reference of the original image groups by using the image NSS prior, and then the rank residual of the image groups between this reference and the degraded image is minimized to achieve a better estimate to the desired image.
Image Ordinal Classification and Understanding: Grid Dropout with Masking Label
Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset.
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
Experimental results have shown that the proposed IndRNN is able to process very long sequences (over 5000 time steps), can be used to construct very deep networks (21 layers used in the experiment) and still be trained robustly.
Ranked #10 on
Language Modelling
on Penn Treebank (Character Level)
Hole Filling with Multiple Reference Views in DIBR View Synthesis
In this paper, we first examine the view interpolation with multiple reference views, demonstrating that the problem of emerging holes in a target virtual view can be greatly alleviated by making good use of other neighboring complementary views in addition to its two (commonly used) most neighboring primary views.
A Benchmark for Sparse Coding: When Group Sparsity Meets Rank Minimization
Sparse coding has achieved a great success in various image processing tasks.
A Fully Trainable Network with RNN-based Pooling
Such a network with learnable pooling function is referred to as a fully trainable network (FTN).
Towards thinner convolutional neural networks through Gradually Global Pruning
Deep network pruning is an effective method to reduce the storage and computation cost of deep neural networks when applying them to resource-limited devices.
Attribute-controlled face photo synthesis from simple line drawing
In this paper, we propose a deep generative model to synthesize face photo from simple line drawing controlled by face attributes such as hair color and complexion.
Iterative Block Tensor Singular Value Thresholding for Extraction of Low Rank Component of Image Data
In this paper, we propose a new robust TPCA method to extract the princi- pal components of the multi-way data based on tensor singular value decomposition.
A Comparative Study for the Nuclear Norms Minimization Methods
Inspired by enhancing sparsity of the weighted L1-norm minimization in comparison with L1-norm minimization in sparse representation, we thus explain that WNNM is more effective than NMM.
Every Filter Extracts A Specific Texture In Convolutional Neural Networks
We also demonstrate that style of images could be a combination of these texture primitives.
3D Keypoint Detection Based on Deep Neural Network with Sparse Autoencoder
Researchers have proposed various methods to extract 3D keypoints from the surface of 3D mesh models over the last decades, but most of them are based on geometric methods, which lack enough flexibility to meet the requirements for various applications.
Mesh Interest Point Detection Based on Geometric Measures and Sparse Refinement
Three dimensional (3D) interest point detection plays a fundamental role in 3D computer vision and graphics.
