Search Results for author:
Found 64 papers, 13 papers with code
Higher-order Organization in the Human Brain from Matrix-Based Rényi's Entropy
To address this problem, we applied multivariate mutual information, specifically, Total Correlation and Dual Total Correlation to reveal higher-order information in the brain.
POSGen: Personalized Opening Sentence Generation for Online Insurance Sales
Such personalized opening sentence generation is challenging because (i) there are limited historical samples for conversation topic recommendation in online insurance sales and (ii) existing text generation schemes often fail to support customized topic ordering based on user preferences.
Continual learning on deployment pipelines for Machine Learning Systems
Following the development of digitization, a growing number of large Original Equipment Manufacturers (OEMs) are adapting computer vision or natural language processing in a wide range of applications such as anomaly detection and quality inspection in plants.
Robust One-shot Segmentation of Brain Tissues via Image-aligned Style Transformation
In this paper, we propose a novel image-aligned style transformation to reinforce the dual-model iterative learning for robust one-shot segmentation of brain tissues.
Joint Secure Communication and Radar Beamforming: A Secrecy-Estimation Rate-Based Design
For the AN-aided SRM, by leveraging alternating optimization similar closed-form solution is obtained for the beamformer and the AN covariance matrix.
Break The Spell Of Total Correlation In betaTCVAE
This paper proposes a way to break the spell of total correlation in betaTCVAE based on the motivation of the total correlation decomposition.
Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions
The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS).
Bridging CLIP and StyleGAN through Latent Alignment for Image Editing
More specifically, our efforts consist of three parts: 1) a data-free training strategy to train latent mappers to bridge the latent space of CLIP and StyleGAN; 2) for more precise mapping, temporal relative consistency is proposed to address the knowledge distribution bias problem among different latent spaces; 3) to refine the mapped latent in s space, adaptive style mixing is also proposed.
Functional Connectome of the Human Brain with Total Correlation
In this work we build on this idea to infer a large scale (whole brain) connectivity network based on Total Correlation and show the possibility of using this kind of networks as biomarkers of brain alterations.
Functional Connectivity in Visual Areas from Total Correlation
In this multivariate setting (three nodes with multidimensional signals), we derive analytical results for the three-way Total Correlation and for all possible pairwise Mutual Information measures.
Semi-supervised Ranking for Object Image Blur Assessment
Based on this dataset, we propose a method to obtain the blur scores only with the pairwise rank labels as supervision.
Accurate Scoliosis Vertebral Landmark Localization on X-ray Images via Shape-constrained Multi-stage Cascaded CNNs
Vertebral landmark localization is a crucial step for variant spine-related clinical applications, which requires detecting the corner points of 17 vertebrae.
Multi-scale frequency separation network for image deblurring
MSFS-Net introduces the frequency separation module (FSM) into an encoder-decoder network architecture to capture the low- and high-frequency information of image at multiple scales.
A Comparative Study of Feature Expansion Unit for 3D Point Cloud Upsampling
Recently, deep learning methods have shown great success in 3D point cloud upsampling.
Noise Perturbation for Saliency Prediction with Psychophysical Synthetic Images
The primary goal of this study is to investigate the performance of saliency prediction in CNN and classic models with psychophysical synthetic images under noise perturbation.
Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
Hyperspectral image produces high spectral resolution at the sacrifice of spatial resolution.
Weakly Supervised Regional and Temporal Learning for Facial Action Unit Recognition
Automatic facial action unit (AU) recognition is a challenging task due to the scarcity of manual annotations.
Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression
In this paper, we emphatically summarize that learning an adaptive label distribution on ordinal regression tasks should follow three principles.
ITTR: Unpaired Image-to-Image Translation with Transformers
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data.
Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning
Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed.
CRIS: CLIP-Driven Referring Image Segmentation
In addition, we present text-to-pixel contrastive learning to explicitly enforce the text feature similar to the related pixel-level features and dissimilar to the irrelevances.
Ranked #5 on
Referring Expression Segmentation
on RefCOCO+ val
BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation
Specifically, we first train a self-supervised style encoder on the generic artistic dataset to extract the representations of arbitrary styles.
Joint Progressive and Coarse-to-fine Registration of Brain MRI via Deformation Field Integration and Non-Rigid Feature Fusion
Registration of brain MRI images requires to solve a deformation field, which is extremely difficult in aligning intricate brain tissues, e. g., subcortical nuclei, etc.
Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition
Based on these two self-supervised auxiliary tasks, local features, mutual relation and motion cues of AUs are better captured in the backbone network with the proposed regional and temporal based auxiliary task learning (RTATL) framework.
Exploring Set Similarity for Dense Self-supervised Representation Learning
By considering the spatial correspondence, dense self-supervised representation learning has achieved superior performance on various dense prediction tasks.
Federated Meta Learning Enhanced Acoustic Radio Cooperative Framework for Ocean of Things Underwater Acoustic Communications
In summary, the proposed ARC/FML for OoT is a promising scheme for information exchange across water and air.
Explainable Hierarchical Imitation Learning for Robotic Drink Pouring
To accurately pour drinks into various containers is an essential skill for service robots.
Symbol-Level Precoding Through the Lens of Zero Forcing and Vector Perturbation
We examine how insights arising from this perturbed ZF and VP interpretations can be leveraged to i) substantially simplify the optimization of certain SLP design criteria, namely, total or peak power minimization subject to SEP quality guarantees; and ii) draw connections with some existing SLP designs.
Contrast Sensitivity Functions in Autoencoders
Three decades ago, Atick et al. suggested that human frequency sensitivity may emerge from the enhancement required for a more efficient analysis of retinal images.
Multi-Level Adaptive Region of Interest and Graph Learning for Facial Action Unit Recognition
In order to incorporate the intra-level AU relation and inter-level AU regional relevance simultaneously, a multi-level AU relation graph is constructed and graph convolution is performed to further enhance AU regional features of each level.
Gravitational effect of a plasma on the shadow of Schwarzschild black holes
Considering a Schwarzschild black hole surrounded by a fully ionized hydrogen plasma, we study the refractive effect and the pure gravitational effect of the plasma on the shadow.
General Relativity and Quantum Cosmology Astrophysics of Galaxies
Image deblurring based on lightweight multi-information fusion network
In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion without a large amount of information loss.
Magnetoelectric coupling and decoupling in multiferroic hexagonal YbFeO3 thin films
The coupling between ferroelectric and magnetic orders in multiferroic materials and the nature of magnetoelectric (ME) effects are enduring experimental challenges.
Materials Science Other Condensed Matter
A Psychophysical Oriented Saliency Map Prediction Model
Finally, the proposed model also can be applied to spatial-temporal saliency prediction and got better performance.
Experimental Evidence that Zn Impurities Pin Pair-Density-Wave Order in La$_{2-x}$Ba$_x$CuO$_4$
Both Zn-doping and $c$-axis magnetic fields have been observed to increase the spin stripe order in La$_{2-x}$Ba$_x$CuO$_4$ with $x$ close to 1/8.
Superconductivity
Loop-induced $ZZ$ production at the LHC: an improved description by matrix-element matching
Loop-induced $ZZ$ production can be enhanced by the large gluon flux at the LHC, and thus should be taken into account in relevant experimental analyses.
High Energy Physics - Phenomenology High Energy Physics - Experiment
One-Bit Symbol-Level Precoding for MU-MISO Downlink with Intelligent Reflecting Surface
This paper considers symbol-level precoding (SLP) for multiuser multi-input single-output (MISO) downlink transmission with the aid of intelligent reflecting surface (IRS).
Siamese Keypoint Prediction Network for Visual Object Tracking
Visual object tracking aims to estimate the location of an arbitrary target in a video sequence given its initial bounding box.
Minimizing Age-of-Information for Fog Computing-supported Vehicular Networks with Deep Q-learning
Connected vehicular network is one of the key enablers for next generation cloud/fog-supported autonomous driving vehicles.
AliCoCo: Alibaba E-commerce Cognitive Concept Net
However, user needs in e-commerce are still not well defined, and none of the existing ontologies has the enough depth and breadth for universal user needs understanding.
Rapid Whole Slide Imaging via Learning-based Two-shot Virtual Autofocusing
Whole slide imaging (WSI) is an emerging technology for digital pathology.
Trend and forecasting of the COVID-19 outbreak in China
By using the public data from Jan. 20 to Feb. 11, 2020, we perform data-driven analysis and forecasting on the COVID-19 epidemic in mainland China, especially Hubei province.
Minimum Symbol-Error Probability Symbol-Level Precoding with Intelligent Reflecting Surface
Recently, the use of intelligent reflecting surface (IRS) has gained considerable attention in wireless communications.
Spatial-Spectral Residual Network for Hyperspectral Image Super-Resolution
Deep learning-based hyperspectral image super-resolution (SR) methods have achieved great success recently.
Sum Rate Maximization for Multiuser MISO Downlink with Intelligent Reflecting Surface
The intelligent reflecting surface (IRS) is a planar array with massive reconfigurable passive elements, which can align the reflecting signals at the receivers via controlling the phase shifts at each element independently.
Machine Learning-based Signal Detection for PMH Signals in Load-modulated MIMO System
By leveraging machine learning, the proposed detection scheme can accurately obtain information of the channel from a few of the received symbols with little resource cost and achieve comparable detection results as that of the optimal ML detector.
Adversarial Training Methods for Network Embedding
To improve this strategy, we further propose an interpretable adversarial training method by enforcing the reconstruction of the adversarial examples in the discrete graph domain.
Latency Minimization for Multiuser Computation Offloading in Fog-Radio Access Networks
This paper considers computation offloading in fog-radio access networks (F-RAN), where multiple user equipments (UEs) offload their computation tasks to the F-RAN through a number of fog nodes.
Depth Restoration: A fast low-rank matrix completion via dual-graph regularization
As a real scenes sensing approach, depth information obtains the widespread applications.
Hyperspectral Super-Resolution via Global-Local Low-Rank Matrix Estimation
Hyperspectral super-resolution (HSR) is a problem that aims to estimate an image of high spectral and spatial resolutions from a pair of co-registered multispectral (MS) and hyperspectral (HS) images, which have coarser spectral and spatial resolutions, respectively.
Correlated Logistic Model With Elastic Net Regularization for Multilabel Image Classification
In this paper, we present correlated logistic (CorrLog) model for multilabel image classification.
Adapting Stochastic Block Models to Power-Law Degree Distributions
Stochastic block models (SBMs) have been playing an important role in modeling clusters or community structures of network data.
StyleRemix: An Interpretable Representation for Neural Image Style Transfer
Multi-Style Transfer (MST) intents to capture the high-level visual vocabulary of different styles and expresses these vocabularies in a joint model to transfer each specific style.
End-to-end Hand Mesh Recovery from a Monocular RGB Image
In this paper, we present a HAnd Mesh Recovery (HAMR) framework to tackle the problem of reconstructing the full 3D mesh of a human hand from a single RGB image.
Polarization Fraction Measurement in same sign WW scattering using Deep Learning
Studying the longitudinally polarized fraction of $W^\pm W^\pm$ scattering at the LHC is crucial to examine the unitarization mechanism of the vector boson scattering amplitude through Higgs and possible new physics.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Receiver Design for Faster-than-Nyquist Signaling: Deep-learning-based Architectures
Additionally, we propose a DL-based joint signal detection and decoding for FTN signaling to replace the complete baseband part in traditional FTN receivers.
Computer-aided diagnosis of lung carcinoma using deep learning - a pilot study
Aim: Early detection and correct diagnosis of lung cancer are the most important steps in improving patient outcome.
Optimize transfer learning for lung diseases in bronchoscopy using a new concept: sequential fine-tuning
To help doctors to be more selective on biopsies and provide a second opinion on diagnosis, in this work, we propose a computer-aided diagnosis (CAD) system for lung diseases including cancers and tuberculosis (TB).
Influence Maximization with \varepsilon-Almost Submodular Threshold Functions
Influence maximization is the problem of selecting $k$ nodes in a social network to maximize their influence spread.
Adversarial Network Embedding
Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization.
Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising
In the guaranteed delivery scenario, ad exposures (which are also called impressions in some works) to users are guaranteed by contracts signed in advance between advertisers and publishers.
Conditional Graphical Lasso for Multi-Label Image Classification
Multi-label image classification aims to predict multiple labels for a single image which contains diverse content.
Combination of Diverse Ranking Models for Personalized Expedia Hotel Searches
The ICDM Challenge 2013 is to apply machine learning to the problem of hotel ranking, aiming to maximize purchases according to given hotel characteristics, location attractiveness of hotels, user's aggregated purchase history and competitive online travel agency information for each potential hotel choice.
