Search Results for author:
Found 58 papers, 24 papers with code
DrasCLR: A Self-supervised Framework of Learning Disease-related and Anatomy-specific Representation for 3D Medical Images
Extensive experiments on large-scale computer tomography (CT) datasets of lung images show that our method improves the performance of many downstream prediction and segmentation tasks.
MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring
However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information.
Measuring tail risk at high-frequency: An $L_1$-regularized extreme value regression approach with unit-root predictors
Studying the high-frequency extreme losses of nine large liquid U. S. stocks using 42 liquidity and volatility predictors, we find the severity of extreme losses to be well predicted by low levels of price impact in period of high volatility of liquidity and volatility.
DGFont++: Robust Deformable Generative Networks for Unsupervised Font Generation
Moreover, we introduce contrastive self-supervised learning to learn a robust style representation for fonts by understanding the similarity and dissimilarities of fonts.
Towards Long-term Autonomy: A Perspective from Robot Learning
In the future, service robots are expected to be able to operate autonomously for long periods of time without human intervention.
Self-Supervised Continual Graph Learning in Adaptive Riemannian Spaces
On the one hand, existing methods work with the zero-curvature Euclidean space, and largely ignore the fact that curvature varies over the coming graph sequence.
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels
The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions.
A Dual-scale Lead-seperated Transformer With Lead-orthogonal Attention And Meta-information For Ecg Classification
Auxiliary diagnosis of cardiac electrophysiological status can be obtained through the analysis of 12-lead electrocardiograms (ECGs).
IoU-Enhanced Attention for End-to-End Task Specific Object Detection
Without densely tiled anchor boxes or grid points in the image, sparse R-CNN achieves promising results through a set of object queries and proposal boxes updated in the cascaded training manner.
A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
To bridge this gap, we make the first attempt to study the problem of self-supervised temporal graph representation learning in the general Riemannian space, supporting the time-varying curvature to shift among hyperspherical, Euclidean and hyperbolic spaces.
Cross Attention Based Style Distribution for Controllable Person Image Synthesis
In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer.
Federated Selective Aggregation for Knowledge Amalgamation
The goal of FedSA is to train a student model for a new task with the help of several decentralized teachers, whose pre-training tasks and data are different and agnostic.
Context-aware Self-supervised Learning for Medical Images Using Graph Neural Network
We use graph neural networks to incorporate the relationship between different anatomical regions.
QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation
By constraining features from the same location to be closer than those from different ones, it implicitly ensures the result to take content from the source.
Style Transformer for Image Inversion and Editing
Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously.
A Self-supervised Mixed-curvature Graph Neural Network
Instead of working on one single constant-curvature space, we construct a mixed-curvature space via the Cartesian product of multiple Riemannian component spaces and design hierarchical attention mechanisms for learning and fusing the representations across these component spaces.
Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training
Recently, vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in the realm of computer vision (CV).
Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation
Image manipulation with StyleGAN has been an increasing concern in recent years. Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images. However, due to the limited semantic and spatial manipulation precision in these latent spaces, the existing endeavors are defeated in fine-grained StyleGAN image manipulation, i. e., local attribute translation. To address this issue, we discover attribute-specific control units, which consist of multiple channels of feature maps and modulation styles.
Artificial Neural Network and Its Application Research Progress in Chemical Process
Most chemical processes, such as distillation, absorption, extraction, and catalytic reactions, are extremely complex processes that are affected by multiple factors.
LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation
Image-to-image (I2I) translation is usually carried out among discrete domains.
Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
The two types of synthesis, either label- or reference-based, have substantial differences.
EventPoint: Self-Supervised Interest Point Detection and Description for Event-based Camera
We propose a new time-surface-like event stream representation method called Tencode.
Can contrastive learning avoid shortcut solutions?
However, we observe that the contrastive loss does not always sufficiently guide which features are extracted, a behavior that can negatively impact the performance on downstream tasks via "shortcuts", i. e., by inadvertently suppressing important predictive features.
Tree-Like Decision Distillation
Knowledge distillation pursues a diminutive yet well-behaved student network by harnessing the knowledge learned by a cumbersome teacher model.
DG-Font: Deformable Generative Networks for Unsupervised Font Generation
Font generation is a challenging problem especially for some writing systems that consist of a large number of characters and has attracted a lot of attention in recent years.
Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions.
NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation
Benefiting from the NDT representation and NDT-Transformer network, the learned global descriptors are enriched with both geometrical and contextual information.
Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery
To recover from high uncertainty cases, the robot monitors its uncertainty along a trajectory and explores possible actions in the state-action space to bring itself to a more certain state.
ID-Unet: Iterative Soft and Hard Deformation for View Synthesis
View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition.
Adaptive Random Bandwidth for Inference in CAViaR Models
This paper investigates the size performance of Wald tests for CAViaR models (Engle and Manganelli, 2004).
Context Matters: Graph-based Self-supervised Representation Learning for Medical Images
Experiments on large-scale Computer Tomography (CT) datasets of lung images show that our approach compares favorably to baseline methods that do not account for the context.
Content-based Analysis of the Cultural Differences between TikTok and Douyin
Short-form video social media shifts away from the traditional media paradigm by telling the audience a dynamic story to attract their attention.
Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
Finally, the selected neighbors across different relations are aggregated together.
Ranked #4 on
Node Classification
on Amazon-Fraud
Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
During training, we adopt a hierarchical structure that simultaneously generates a low-resolution version of the image and a randomly selected sub-volume of the high-resolution image.
Novel View Synthesis on Unpaired Data by Conditional Deformable Variational Auto-Encoder
Novel view synthesis often needs the paired data from both the source and target views.
Progressive Multi-stage Feature Mix for Person Re-Identification
In this work, we propose a Progressive Multi-stage feature Mix network (PMM), which enables the model to find out the more precise and diverse features in a progressive manner.
Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification
This paper proposes to learn the sample posterior and the class prior distribution in the latent space, so that not only representative features but also the uncertainty can be built by the model.
Localising Faster: Efficient and precise lidar-based robot localisation in large-scale environments
More importantly, the Gaussian method (i. e. deep probabilistic localisation) and non-Gaussian method (i. e. MCL) can be integrated naturally via importance sampling.
Graph-Bert: Only Attention is Needed for Learning Graph Representations
We have tested the effectiveness of GRAPH-BERT on several graph benchmark datasets.
Ranked #28 on
Node Classification
on Cora
Improving End-to-End Object Tracking Using Relational Reasoning
Relational reasoning, the ability to model interactions and relations between objects, is valuable for robust multi-object tracking and pivotal for trajectory prediction.
Disentangling the Spatial Structure and Style in Conditional VAE
Depending on whether the label is related with the spatial structure, the output $z_s$ from the condition mapping network is used either as a style code or a spatial structure code.
Imagine That! Leveraging Emergent Affordances for 3D Tool Synthesis
In this paper we explore the richness of information captured by the latent space of a vision-based generative model.
Imagine That! Leveraging Emergent Affordances for Tool Synthesis in Reaching Tasks
In this paper we investigate an artificial agent's ability to perform task-focused tool synthesis via imagination.
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
To this end, we introduce a dual-step strategy that first extracts the task-specific knowledge from the heterogeneous teachers sharing the same sub-task, and then amalgamates the extracted knowledge to build the student network.
End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
The majority of contemporary object-tracking approaches do not model interactions between objects.
Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensions
But different from CVAE, we present a method for disentangling the latent space into the label relevant and irrelevant dimensions, $\bm{\mathrm{z}}_s$ and $\bm{\mathrm{z}}_u$, for a single input.
Amalgamating Knowledge towards Comprehensive Classification
We propose in this paper to study a new model-reusing task, which we term as \emph{knowledge amalgamation}.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Exploring Correlations in Multiple Facial Attributes through Graph Attention Network
Estimating multiple attributes from a single facial image gives comprehensive descriptions on the high level semantics of the face.
Recurrent-OctoMap: Learning State-based Map Refinement for Long-Term Semantic Mapping with 3D-Lidar Data
Most existing semantic mapping approaches focus on improving semantic understanding of single frames, rather than 3D refinement of semantic maps (i. e. fusing semantic observations).
Learning monocular visual odometry with dense 3D mapping from dense 3D flow
Dense 2D flow and a depth image are generated from monocular images by sub-networks, which are then used by a 3D flow associated layer in the L-VO network to generate dense 3D flow.
3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data
Our approach, T-Pose-LSTM (Temporal 3DOF-Pose Long-Short-Term Memory), is trained using long-term data from real-world robot deployments and aims to learn context-dependent (environment- and time-specific) human activities.
Dense RGB-D semantic mapping with Pixel-Voxel neural network
For intelligent robotics applications, extending 3D mapping to 3D semantic mapping enables robots to, not only localize themselves with respect to the scene's geometrical features but also simultaneously understand the higher level meaning of the scene contexts.
Single-Shot Clothing Category Recognition in Free-Configurations with Application to Autonomous Clothes Sorting
Our visual feature is robust to deformable shapes and our approach is able to recognise the category of unknown clothing in unconstrained and random configurations.
Weakly-supervised DCNN for RGB-D Object Recognition in Real-World Applications Which Lack Large-scale Annotated Training Data
We also propose a novel way to pretrain a DCNN for the depth modality, by training on virtual depth images projected from CAD models.
A fully end-to-end deep learning approach for real-time simultaneous 3D reconstruction and material recognition
We present the results of experiments, in which we trained our system to perform real-time 3D semantic reconstruction for 23 different materials in a real-world application.
An Automated CNN Recommendation System for Image Classification Tasks
In order to solve this problem, we proposed an automated CNN recommendation system for image classification task.
Robot Vision Architecture for Autonomous Clothes Manipulation
The experimental results show that the proposed dual-arm flattening using stereo vision system remarkably outperforms the single-arm flattening and widely-cited Kinect-based sensing system for dexterous manipulation tasks.
