Search Results for author:
Found 241 papers, 64 papers with code
Real-time Decolorization using Dominant Colors
Decolorization is the process to convert a color image or video to its grayscale version, and it has received great attention in recent years.
Parallax-tolerant Image Stitching
We then pre-align input images using the optimal homography and further use content-preserving warping to locally refine the alignment.
Casual Stereoscopic Panorama Stitching
The stitching of the right views is formulated as a labeling problem that is constrained by the stitching of the left views to make the left- and right-view panorama consistent to avoid retinal rivalry.
Fusing Subcategory Probabilities for Texture Classification
Texture, as a fundamental characteristic of objects, has attracted much attention in computer vision research.
Variational inference for rare variant detection in deep, heterogeneous next-generation sequencing data
The detection of rare variants is important for understanding the genetic heterogeneity in mixed samples.
Estimation of Passenger Route Choice Pattern Using Smart Card Data for Complex Metro Systems
Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities.
Stealing Machine Learning Models via Prediction APIs
In such attacks, an adversary with black-box access, but no prior knowledge of an ML model's parameters or training data, aims to duplicate the functionality of (i. e., "steal") the model.
Indoor Space Recognition using Deep Convolutional Neural Network: A Case Study at MIT Campus
In this paper, we propose a robust and parsimonious approach using Deep Convolutional Neural Network (DCNN) to recognize and interpret interior space.
A global optimization algorithm for sparse mixed membership matrix factorization
Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity.
Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization
We propose a new model based on the deconvolutional networks and SAX discretization to learn the representation for multivariate time series.
Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification
Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts.
A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
For the second target, a novel CNN-based universal framework is proposed to process the VHR satellite images and generate the land-use, urban density, and population distribution maps.
A Joint Identification Approach for Argumentative Writing Revisions
This paper proposes an approach that identifies the revision location and the revision type jointly to solve the issue of error propagation.
Doubly Robust Data-Driven Distributionally Robust Optimization
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms.
Data-driven Optimal Cost Selection for Distributionally Robust Optimization
Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems.
A Corpus of Annotated Revisions for Studying Argumentative Writing
This paper presents ArgRewrite, a corpus of between-draft revisions of argumentative essays.
SAR Target Recognition Using the Multi-aspect-aware Bidirectional LSTM Recurrent Neural Networks
However, there is a limitation in current deep learning based ATR solution that each learning process only handle one SAR image, namely learning the static scattering information, while missing the space-varying information.
DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
Semantic segmentation is a fundamental research in remote sensing image processing.
Locally-Transferred Fisher Vectors for Texture Classification
Texture classification has been extensively studied in computer vision.
Parameter-free $\ell_p$-Box Decoding of LDPC Codes
The Alternating Direction Method of Multipliers (ADMM) decoding of Low Density Parity Check (LDPC) codes has received many attentions due to its excellent performance at the error floor region.
Information Theory Information Theory
SeqFace: Make full use of sequence information for face recognition
Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years.
Ranked #1 on
Face Verification
on YouTube Faces DB
Ekiden: A Platform for Confidentiality-Preserving, Trustworthy, and Performant Smart Contract Execution
Smart contracts are applications that execute on blockchains.
Cryptography and Security
TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
Hyperspectral image classification via a random patches network
Due to the remarkable achievements obtained by deep learning methods in the fields of computer vision, an increasing number of researches have been made to apply these powerful tools into hyperspectral image (HSI) classification.
High-speed Tracking with Multi-kernel Correlation Filters
In this paper, we will introduce the MKL into KCF in a different way than MKCF.
Memristor-based Deep Convolution Neural Network: A Case Study
In this paper, we firstly introduce a method to efficiently implement large-scale high-dimensional convolution with realistic memristor-based circuit components.
Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes
We consider optimal transport based distributionally robust optimization (DRO) problems with locally strongly convex transport cost functions and affine decision rules.
Optimization and Control Primary: 90C15, Secondary: 65K05, 90C47
Nonconvex and Nonsmooth Sparse Optimization via Adaptively Iterative Reweighted Methods
We propose a general formulation of nonconvex and nonsmooth sparse optimization problems with convex set constraint, which can take into account most existing types of nonconvex sparsity-inducing terms, bringing strong applicability to a wide range of applications.
Quantifying Legibility of Indoor Spaces Using Deep Convolutional Neural Networks: Case Studies in Train Stations
Evaluating legibility is particularly desirable in indoor spaces, since it has a large impact on human behavior and the efficiency of space utilization.
Noise-Tolerant Paradigm for Training Face Recognition CNNs
Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR).
A Distributionally Robust Boosting Algorithm
Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation.
MediaPipe: A Framework for Building Perception Pipelines
A developer can use MediaPipe to build prototypes by combining existing perception components, to advance them to polished cross-platform applications and measure system performance and resource consumption on target platforms.
Distributed, Parallel, and Cluster Computing
Predicting Treatment Initiation from Clinical Time Series Data via Graph-Augmented Time-Sensitive Model
Many computational models were proposed to extract temporal patterns from clinical time series for each patient and among patient group for predictive healthcare.
A Survey of Deep Learning-based Object Detection
Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in peoples life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class.
Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation
First, images from each domain are embedded into two spaces, a shared domain-invariant content space and a domain-specific style space.
Edge AIBench: Towards Comprehensive End-to-end Edge Computing Benchmarking
In edge computing scenarios, the distribution of data and collaboration of workloads on different layers are serious concerns for performance, privacy, and security issues.
Performance Distributed, Parallel, and Cluster Computing
Nuclei Segmentation via a Deep Panoptic Model with Semantic Feature Fusion
Automated detection and segmentation of individual nuclei in histopathology images is important for cancer diagnosis and prognosis.
Domain-Agnostic Learning with Anatomy-Consistent Embedding for Cross-Modality Liver Segmentation
For the DA task, our DALACE model outperformed CycleGAN, TD-GAN , and DADR with DSC of 0. 847 compared to 0. 721, 0. 793 and 0. 806.
ACFNet: Attentional Class Feature Network for Semantic Segmentation
Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective.
ViSTRA2: Video Coding using Spatial Resolution and Effective Bit Depth Adaptation
Our results show consistent and significant compression gains against HM and VVC based on Bj{\o}negaard Delta measurements, with average BD-rate savings of 12. 6% (PSNR) and 19. 5% (VMAF) over HM and 5. 5% (PSNR) and 8. 6% (VMAF) over VTM.
Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set
In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint.
Hepatocellular Carcinoma Intra-arterial Treatment Response Prediction for Improved Therapeutic Decision-Making
This work proposes a pipeline to predict treatment response to intra-arterial therapy of patients with Hepatocellular Carcinoma (HCC) for improved therapeutic decision-making.
Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks
We demonstrated the proposed methods with implementations of a 4-layer CNN on MNIST and ResNet(20, 32, and 56) on CIFAR-10.
Defects Mitigation in Resistive Crossbars for Analog Vector Matrix Multiplication
With storage and computation happening at the same place, computing in resistive crossbars minimizes data movement and avoids the memory bottleneck issue.
Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation
Most deep image smoothing operators are always trained repetitively when different explicit structure-texture pairs are employed as label images for each algorithm configured with different parameters.
Residual-Recursion Autoencoder for Shape Illustration Images
Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products.
Efficient Scenario Generation for Heavy-tailed Chance Constrained Optimization
We consider a generic class of chance-constrained optimization problems with heavy-tailed (i. e., power-law type) risk factors.
Optimization and Control Probability
AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
An end-to-end benchmark is a distillation of the essential attributes of an industry-scale application.
Multi-branch and Multi-scale Attention Learning for Fine-Grained Visual Categorization
Therefore, our multi-branch and multi-scale learning network(MMAL-Net) has good classification ability and robustness for images of different scales.
Ranked #4 on
Fine-Grained Image Classification
on FGVC Aircraft
Fine-Grained Image Classification
Fine-Grained Image Recognition
+3
BVI-CC: A Dataset for Research on Video Compression and Quality Assessment
The compression efficiency of the codecs was evaluated with commonly used objective quality metrics, and the subjective quality of their reconstructed content was also evaluated through psychophysical experiments.
BVI-DVC: A Training Database for Deep Video Compression
Deep learning methods are increasingly being applied in the optimisation of video compression algorithms and can achieve significantly enhanced coding gains, compared to conventional approaches.
TRAKO: Efficient Transmission of Tractography Data for Visualization
Fiber tracking produces large tractography datasets that are tens of gigabytes in size consisting of millions of streamlines.
AIBench Training: Balanced Industry-Standard AI Training Benchmarking
We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent.
Unsupervised Instance Segmentation in Microscopy Images via Panoptic Domain Adaptation and Task Re-weighting
More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images.
Encoding in the Dark Grand Challenge: An Overview
In this paper, we present an overview of the proposed challenge, and test state-of-the-art methods that will be part of the benchmark methods at the stage of the participants' deliverable assessment.
Defending Model Inversion and Membership Inference Attacks via Prediction Purification
Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence scores predicted by the target classifier.
FiberStars: Visual Comparison of Diffusion Tractography Data between Multiple Subjects
Tractography from high-dimensional diffusion magnetic resonance imaging (dMRI) data allows brain's structural connectivity analysis.
Active Fuzzing for Testing and Securing Cyber-Physical Systems
Cyber-physical systems (CPSs) in critical infrastructure face a pervasive threat from attackers, motivating research into a variety of countermeasures for securing them.
Integrating global spatial features in CNN based Hyperspectral/SAR imagery classification
In addition, a dual-branch convolutional neural network (CNN) classification method is designed in combination with the global information to mine the pixel features of the image.
MultiResolution Attention Extractor for Small Object Detection
Small objects are difficult to detect because of their low resolution and small size.
Distributionally Robust Batch Contextual Bandits
Leveraging this evaluation scheme, we further propose a novel learning algorithm that is able to learn a policy that is robust to adversarial perturbations and unknown covariate shifts with a performance guarantee based on the theory of uniform convergence.
BlazePose: On-device Real-time Body Pose tracking
We present BlazePose, a lightweight convolutional neural network architecture for human pose estimation that is tailored for real-time inference on mobile devices.
Ranked #1 on
3D Pose Estimation
on Google-Yoga
MediaPipe Hands: On-device Real-time Hand Tracking
We present a real-time on-device hand tracking pipeline that predicts hand skeleton from single RGB camera for AR/VR applications.
MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering
Each MFRB extracts features from multiple convolutional layers using dense connections and a multi-level residual learning structure.
Video compression with low complexity CNN-based spatial resolution adaptation
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder.
Joint Bandwidth Allocation and Path Selection in WANs with Path Cardinality Constraints
Almost all existing works deal with such a problem using relaxation techniques to transform it to be a convex optimization problem.
PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images
In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.
P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions
Learning deep neural network (DNN) classifier with noisy labels is a challenging task because the DNN can easily over-fit on these noisy labels due to its high capability.
Video Compression with CNN-based Post Processing
In recent years, video compression techniques have been significantly challenged by the rapidly increased demands associated with high quality and immersive video content.
A simulation environment for drone cinematography
Methods for environmental image capture, 3D reconstruction (photogrammetry) and the creation of foreground assets are presented along with a flexible and user-friendly simulation interface.
Distributionally Robust Local Non-parametric Conditional Estimation
Conditional estimation given specific covariate values (i. e., local conditional estimation or functional estimation) is ubiquitously useful with applications in engineering, social and natural sciences.
CVEGAN: A Perceptually-inspired GAN for Compressed Video Enhancement
We propose a new Generative Adversarial Network for Compressed Video quality Enhancement (CVEGAN).
Hole-Doped Room-Temperature Superconductivity in H$_{3}$S$_{1-x}$Z$_x$ (Z=C, Si)
We examine the effects of the low-level substitution of S atoms by C and Si atoms on the superconductivity of H$_3$S with the $Im\bar{3}m$ structure at megabar pressure.
Superconductivity Materials Science
Two-fluid Modeling of Acoustic Wave Propagation in Gravitationally Stratified Isothermal Media
In the present numerical simulations, the initial density is specified to reach hydrostatic equilibrium, and as a comparison, chemical equilibrium is also taken into account to provide a density profile that differs from typical hydrostatic equilibrium profiles.
Plasma Physics Solar and Stellar Astrophysics
Room-Temperature Superconductivity in Boron-Nitrogen Doped Lanthanum Superhydride
Recent theoretical and experimental studies of hydrogen-rich materials at megabar pressures (i. e., >100 GPa) have led to the discovery of very high-temperature superconductivity in these materials.
Superconductivity Materials Science
Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification
At the network search stage, the DCNNs are fine-tuned with the full training set in order to select the model with the highest BACC.
Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets.
Speech Emotion Recognition with Multiscale Area Attention and Data Augmentation
In this paper, we apply multiscale area attention in a deep convolutional neural network to attend emotional characteristics with varied granularities and therefore the classifier can benefit from an ensemble of attentions with different scales.
CellTrack R-CNN: A Novel End-To-End Deep Neural Network for Cell Segmentation and Tracking in Microscopy Images
Cell segmentation and tracking in microscopy images are of great significance to new discoveries in biology and medicine.
Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases
The rapid development of remote sensing techniques provides rich, large-coverage, and high-temporal information of the ground, which can be coupled with the emerging deep learning approaches that enable latent features and hidden geographical patterns to be extracted.
Three-dimensional charge density wave and robust zero-bias conductance peak inside the superconducting vortex core of a kagome superconductor CsV$_3$Sb$_5$
The transition-metal-based kagome metals provide a versatile platform for correlated topological phases hosting various electronic instabilities.
Superconductivity Strongly Correlated Electrons
Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning
We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms.
Enhancing VMAF through New Feature Integration and Model Combination
VMAF is a machine learning based video quality assessment method, originally designed for streaming applications, which combines multiple quality metrics and video features through SVM regression.
VMAF-based Bitrate Ladder Estimation for Adaptive Streaming
In HTTP Adaptive Streaming, video content is conventionally encoded by adapting its spatial resolution and quantization level to best match the prevailing network state and display characteristics.
A Subjective Study on Videos at Various Bit Depths
Bit depth adaptation, where the bit depth of a video sequence is reduced before transmission and up-sampled during display, can potentially reduce data rates with limited impact on perceptual quality.
Robustifying Conditional Portfolio Decisions via Optimal Transport
Despite the non-linearity of the objective function in the probability measure, we show that the distributionally robust portfolio allocation with side information problem can be reformulated as a finite-dimensional optimization problem.
Individually Fair Gradient Boosting
Gradient boosting is a popular method for machine learning from tabular data, which arise often in applications where algorithmic fairness is a concern.
Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection
Despite significant progress in neural abstractive summarization, recent studies have shown that the current models are prone to generating summaries that are unfaithful to the original context.
Quantitative mapping of the brain's structural connectivity using diffusion MRI tractography: a review
Diffusion magnetic resonance imaging (dMRI) tractography is an advanced imaging technique that enables in vivo mapping of the brain's white matter connections at macro scale.
Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
In this paper we propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks.
Deception Detection in Videos using the Facial Action Coding System
We specifically use long short-term memory (LSTM) which we trained using the real-life trial dataset and it provided one of the best facial only approaches to deception detection.
A Deep Value-network Based Approach for Multi-Driver Order Dispatching
In this work, we propose a deep reinforcement learning based solution for order dispatching and we conduct large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method achieves significant improvement on both total driver income and user experience related metrics.
On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
Perceptually-inspired super-resolution of compressed videos
Spatial resolution adaptation is a technique which has often been employed in video compression to enhance coding efficiency.
An adaptive Lagrange multiplier determination method for rate-distortion optimisation in hybrid video codecs
This paper describes an adaptive Lagrange multiplier determination method for rate-quality optimisation in video compression.
Quality assessment methods for perceptual video compression
This paper describes a quality assessment model for perceptual video compression applications (PVM), which stimulates visual masking and distortion-artefact perception using an adaptive combination of noticeable distortions and blurring artefacts.
Learning Temporal Consistency for Low Light Video Enhancement From Single Images
Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.
Deep Fiber Clustering: Anatomically Informed Unsupervised Deep Learning for Fast and Effective White Matter Parcellation
White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.
An explainable two-dimensional single model deep learning approach for Alzheimer's disease diagnosis and brain atrophy localization
In this research, we propose a novel end-to-end deep learning approach for automated diagnosis of AD and localization of important brain regions related to the disease from sMRI data.
On Sample Based Explanation Methods for NLP: Faithfulness, Efficiency and Semantic Evaluation
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness.
SR-HetGNN:Session-based Recommendation with Heterogeneous Graph Neural Network
The current studies generally learn user preferences according to the transitions of items in the user's session sequence.
Ultralow complexity long short-term memory network for fiber nonlinearity mitigation in coherent optical communication systems
In this paper, we propose a center-oriented long short-term memory network (Co-LSTM) incorporating a simplified mode with a recycling mechanism in the equalization operation, which can mitigate fiber nonlinearity in coherent optical communication systems with ultralow complexity.
OpenClinicalAI: enabling AI to diagnose diseases in real-world clinical settings
In the real-world clinical setting, OpenClinicalAI significantly outperforms the state-of-the-art AI system.
DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis
With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.
Efficient Context-Aware Network for Abdominal Multi-organ Segmentation
For the context block, we propose strip pooling module to capture anisotropic and long-range contextual information, which exists in abdominal scene.
Coded Computation across Shared Heterogeneous Workers with Communication Delay
In this work, we consider a multi-master heterogeneous-worker distributed computing scenario, where multiple matrix multiplication tasks are encoded and allocated to workers for parallel computation.
Grasp-Oriented Fine-grained Cloth Segmentation without Real Supervision
We show that training our network solely with synthetic data and the proposed DA yields results competitive with models trained on real data.
Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trends
In order to improve the speed of B&B algorithms, learning techniques have been introduced in this algorithm recently.
CN-Motifs Perceptive Graph Neural Networks
Graph neural networks (GNNs) have been the dominant approaches for graph representation learning.
Ranked #8 on
Node Classification
on Pubmed
Can Graph Neural Networks Learn to Solve MaxSAT Problem?
With the rapid development of deep learning techniques, various recent work has tried to apply graph neural networks (GNNs) to solve NP-hard problems such as Boolean Satisfiability (SAT), which shows the potential in bridging the gap between machine learning and symbolic reasoning.
ViSTRA3: Video Coding with Deep Parameter Adaptation and Post Processing
This paper presents a deep learning-based video compression framework (ViSTRA3).
ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
Video frame interpolation (VFI) is currently a very active research topic, with applications spanning computer vision, post production and video encoding.
Ranked #1 on
Video Frame Interpolation
on SNU-FILM (easy)
Empirical Analysis of EIP-1559: Transaction Fees, Waiting Time, and Consensus Security
However, a systematic evaluation of the real-world impact of TFMs is still absent.
SupWMA: Consistent and Efficient Tractography Parcellation of Superficial White Matter with Deep Learning
Most parcellation methods focus on the deep white matter (DWM), while fewer methods address the superficial white matter (SWM) due to its complexity.
Model and predict age and sex in healthy subjects using brain white matter features: A deep learning approach
The human brain's white matter (WM) structure is of immense interest to the scientific community.
Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
This paper presents a new deformable convolution-based video frame interpolation (VFI) method, using a coarse to fine 3D CNN to enhance the multi-flow prediction.
A Subjective Quality Study for Video Frame Interpolation
Video frame interpolation (VFI) is one of the fundamental research areas in video processing and there has been extensive research on novel and enhanced interpolation algorithms.
RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
In recent years, deep learning techniques have shown significant potential for improving video quality assessment (VQA), achieving higher correlation with subjective opinions compared to conventional approaches.
Double Thompson Sampling in Finite stochastic Games
This algorithm achieves a total regret bound of $\tilde{\mathcal{O}}(D\sqrt{SAT})$in time horizon $T$ with $S$ states, $A$ actions and diameter $D$.
A CNN-based Post-Processor for Perceptually-Optimized Immersive Media Compression
In recent years, resolution adaptation based on deep neural networks has enabled significant performance gains for conventional (2D) video codecs.
Mixed Reality Depth Contour Occlusion Using Binocular Similarity Matching and Three-dimensional Contour Optimisation
To evaluate the effectiveness of the algorithm, we demonstrate a time con-sumption statistical analysis for each stage of the DCO algorithm execution.
SkillNet-NLU: A Sparsely Activated Model for General-Purpose Natural Language Understanding
The key feature of our approach is that it is sparsely activated guided by predefined skills.
STICC: A multivariate spatial clustering method for repeated geographic pattern discovery with consideration of spatial contiguity
In this paper, we propose a Spatial Toeplitz Inverse Covariance-Based Clustering (STICC) method that considers both attributes and spatial relationships of geographic objects for multivariate spatial clustering.
Global Attitude Synchronization of Networked Rigid Bodies Under Directed Topologies
Simulations for networked spacecraft are presented to show the global synchronization performances under different directed topologies.
SAD: A Large-scale Dataset towards Airport Detection in Synthetic Aperture Radar Images
As a result, deep learning methods have not been fully used in airport detection tasks.
Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer
Based on the insight that mass data is sufficient and shares the same knowledge structure with non-mass data of identifying the malignancy of a lesion based on the ultrasound image, we propose a novel transfer learning framework to enhance the generalizability of the DNN model for non-mass BUS with the help of mass BUS.
SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model.
Deep fiber clustering: Anatomically informed fiber clustering with self-supervised deep learning for fast and effective tractography parcellation
In this work, we propose a novel deep learning framework for white matter fiber clustering, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances.
Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
Recently, industrial recommendation services have been boosted by the continual upgrade of deep learning methods.
One Model, Multiple Modalities: A Sparsely Activated Approach for Text, Sound, Image, Video and Code
Moreover, our model supports self-supervised pretraining with the same sparsely activated way, resulting in better initialized parameters for different modalities.
A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding
However, due to the large diversity of geographic context and acquisition conditions, the captured SVI always contains various distracting objects (e. g., pedestrians and vehicles), which will distract human visual attention from efficiently finding the destination in the last few meters.
Enhancing VVC with Deep Learning based Multi-Frame Post-Processing
This paper describes a CNN-based multi-frame post-processing approach based on a perceptually-inspired Generative Adversarial Network architecture, CVEGAN.
Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification
This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties.
CAINNFlow: Convolutional block Attention modules and Invertible Neural Networks Flow for anomaly detection and localization tasks
Detection of object anomalies is crucial in industrial processes, but unsupervised anomaly detection and localization is particularly important due to the difficulty of obtaining a large number of defective samples and the unpredictable types of anomalies in real life.
TractoFormer: A Novel Fiber-level Whole Brain Tractography Analysis Framework Using Spectral Embedding and Vision Transformers
Whole brain tractography (WBT) data contains over hundreds of thousands of individual fiber streamlines (estimated brain connections), and this data is usually parcellated to create compact representations for data analysis applications such as disease classification.
White Matter Tracts are Point Clouds: Neuropsychological Score Prediction and Critical Region Localization via Geometric Deep Learning
In this paper, we propose a deep-learning-based framework for neuropsychological score prediction using microstructure measurements estimated from diffusion magnetic resonance imaging (dMRI) tractography, focusing on predicting performance on a receptive vocabulary assessment task based on a critical fiber tract for language, the arcuate fasciculus (AF).
FD-GATDR: A Federated-Decentralized-Learning Graph Attention Network for Doctor Recommendation Using EHR
In the past decade, with the development of big data technology, an increasing amount of patient information has been stored as electronic health records (EHRs).
FloLPIPS: A Bespoke Video Quality Metric for Frame Interpoation
Video frame interpolation (VFI) serves as a useful tool for many video processing applications.
Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions
We propose a novel two-stage deep-learning-based framework, Superficial White Matter Analysis (SupWMA), that performs an efficient and consistent parcellation of 198 SWM clusters from whole-brain tractography.
Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation
In this work, we modify the MFRNet network architecture to enable multiple frame processing, and the new network, multi-frame MFRNet, has been integrated into the EBDA framework using two Versatile Video Coding (VVC) host codecs: VTM 16. 2 and the Fraunhofer Versatile Video Encoder (VVenC 1. 4. 0).
Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction
Based on this measure, we also design a computation-efficient client sampling strategy, such that the actively selected clients will generate a more class-balanced grouped dataset with theoretical guarantees.
BVI-VFI: A Video Quality Database for Video Frame Interpolation
In order to narrow this research gap, we have developed a new video quality database named BVI-VFI, which contains 540 distorted sequences generated by applying five commonly used VFI algorithms to 36 diverse source videos with various spatial resolutions and frame rates.
GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal
In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset.
TractoSCR: A Novel Supervised Contrastive Regression Framework for Prediction of Neurocognitive Measures Using Multi-Site Harmonized Diffusion MRI Tractography
We propose a novel deep regression method, namely TractoSCR, that allows full supervision for contrastive learning in regression tasks using diffusion MRI tractography.
Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
In addition, we observe that existing algorithms have a performance drop with the mitigated data leakage issue.
Memory recall by controlling chaos
By incorporating feedback loops, that engender amplification and damping so that output is not proportional to input, the biological neural networks become highly nonlinear and thus very likely chaotic in nature.
Age Prediction Performance Varies Across Deep, Superficial, and Cerebellar White Matter Connections
The brain's white matter (WM) undergoes developmental and degenerative processes during the human lifespan.
Line Drawing Guided Progressive Inpainting of Mural Damages
Mural image inpainting refers to repairing the damage or missing areas in a mural image to restore the visual appearance.
DeepRGVP: A Novel Microstructure-Informed Supervised Contrastive Learning Framework for Automated Identification Of The Retinogeniculate Pathway Using dMRI Tractography
The retinogeniculate pathway (RGVP) is responsible for carrying visual information from the retina to the lateral geniculate nucleus.
Tractography-Based Parcellation of Cerebellar Dentate Nuclei via a Deep Nonnegative Matrix Factorization Clustering Method
In this paper, we investigate a deep nonnegative matrix factorization clustering method (DNMFC) for parcellation of the human DN based on its structural connectivity using diffusion MRI tractography.
Purifier: Defending Data Inference Attacks via Transforming Confidence Scores
Besides, our further experiments show that PURIFIER is also effective in defending adversarial model inversion attacks and attribute inference attacks.
Text-Guided Mask-free Local Image Retouching
In the realm of multi-modality, text-guided image retouching techniques emerged with the advent of deep learning.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
Learning Rain Location Prior for Nighttime Deraining
This learned prior contains location information of rain streaks and, when injected into deraining models, can significantly improve their performance.
Urban Visual Intelligence: Studying Cities with AI and Street-level Imagery
The visual dimension of cities has been a fundamental subject in urban studies, since the pioneering work of scholars such as Sitte, Lynch, Arnheim, and Jacobs.
TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography
This work shows the potential of incorporating anatomical information, especially known anatomical similarities between input features, to guide convolutions in neural networks.
DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model
Speech-driven gesture synthesis is a field of growing interest in virtual human creation.
SimCGNN: Simple Contrastive Graph Neural Network for Session-based Recommendation
Session-based recommendation (SBR) problem, which focuses on next-item prediction for anonymous users, has received increasingly more attention from researchers.
ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation
Currently, one of the major challenges in deep learning-based video frame interpolation (VFI) is the large model sizes and high computational complexity associated with many high performance VFI approaches.
Few-shots Portrait Generation with Style Enhancement and Identity Preservation
Nowadays, the wide application of virtual digital human promotes the comprehensive prosperity and development of digital culture supported by digital economy.
GeoLab: Geometry-based Tractography Parcellation of Superficial White Matter
Superficial white matter (SWM) has been less studied than long-range connections despite being of interest to clinical research, andfew tractography parcellation methods have been adapted to SWM.
Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially, giving rise to a new paradigm, namely self-supervised continual learning (SSCL).
LDMVFI: Video Frame Interpolation with Latent Diffusion Models
Existing works on video frame interpolation (VFI) mostly employ deep neural networks that are trained by minimizing the L1, L2, or deep feature space distance (e. g. VGG loss) between their outputs and ground-truth frames.
Fiber Tract Shape Measures Inform Prediction of Non-Imaging Phenotypes
In this paper, we investigate the potential of fiber tract shape features for predicting non-imaging phenotypes, both individually and in combination with traditional features.
Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
With the help of the Internet and communication terminal, Mpox-AISM can perform a real-time, low-cost, and convenient diagnosis for earlier-stage mpox in various real-world settings, thereby effectively curbing the spread of mpox virus.
A Registration- and Uncertainty-based Framework for White Matter Tract Segmentation With Only One Annotated Subject
Our method is constructed by proposed registration-based peak augmentation (RPA) and uncertainty-based refining (URe) modules.
Co-GRU Enhanced End-to-End Design for Long-haul Coherent Transmission Systems
In recent years, the end-to-end (E2E) scheme based on deep learning (DL) has been proposed as a potential scheme to jointly optimize the encoder and the decoder parameters of the optical communication system.
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer
TransMix uses unreliable attention maps to compute mixed attention labels that can affect the model.
Ranked #1 on
Data Augmentation
on ImageNet
A fast and flexible algorithm for microstructure reconstruction combining simulated annealing and deep learning
The proposed algorithm is flexible and can complete training and reconstruction in a short time with only one two-dimensional image.
UPDExplainer: an Interpretable Transformer-based Framework for Urban Physical Disorder Detection Using Street View Imagery
Experimental results on the re-annotated Place Pulse 2. 0 dataset demonstrate promising detection performance of the proposed method, with an accuracy of 79. 9%.
Understand Waiting Time in Transaction Fee Mechanism: An Interdisciplinary Perspective
Our study identified NFT drops as a unique source of market congestion -- holiday effects -- beyond trend and season effects.
Label-Free Multi-Domain Machine Translation with Stage-wise Training
Our model is composed of three parts: a backbone model, a domain discriminator taking responsibility to discriminate data from different domains, and a set of experts that transfer the decoded features from generic to specific.
Doppler-Resilient Design of CAZAC Sequences for mmWave/THz Sensing Applications
For an arbitrary-length ZC sequence, a feasible range of the root index is derived to satisfy the requirement of PSLR within the scope of RoI.
FGAM:Fast Adversarial Malware Generation Method Based on Gradient Sign
Adversarial attacks are to deceive the deep learning model by generating adversarial samples.
Reconstructing the somatotopic organization of the corticospinal tract remains a challenge for modern tractography methods
The corticospinal tract (CST) is a critically important white matter fiber tract in the human brain that enables control of voluntary movements of the body.
HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation
Learning-based video compression is currently a popular research topic, offering the potential to compete with conventional standard video codecs.
Ranked #1 on
Video Reconstruction
on UVG
SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Traditional multitask learning methods basically can only exploit common knowledge in task- or language-wise, which lose either cross-language or cross-task knowledge.
Identification of Causal Relationship between Amyloid-beta Accumulation and Alzheimer's Disease Progression via Counterfactual Inference
Alzheimer's disease (AD) is a neurodegenerative disorder that is beginning with amyloidosis, followed by neuronal loss and deterioration in structure, function, and cognition.
OpenClinicalAI: An Open and Dynamic Model for Alzheimer's Disease Diagnosis
Thus, the AD diagnosis task is tangled and coupled with the diagnosis strategy formulation.
TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance
We evaluate the effectiveness of the proposed method by predicting individual performance on two neuropsychological assessments of language using a dataset of 20 association white matter fiber tracts from 806 subjects from the Human Connectome Project.
Generative Pretraining in Multimodality
We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context.
Ranked #1 on
Visual Question Answering
on VQA v2
ATWM: Defense against adversarial malware based on adversarial training
In order to defend against malware attacks, researchers have proposed many Windows malware detection models based on deep learning.
Data-Driven Optimal Control of Tethered Space Robot Deployment with Learning Based Koopman Operator
To avoid complex constraints of the traditional nonlinear method for tethered space robot (TSR) deployment, this paper proposes a data-driven optimal control framework with an improved deep learning based Koopman operator that could be applied to complex environments.
TractCloud: Registration-free tractography parcellation with a novel local-global streamline point cloud representation
TractCloud achieves efficient and consistent whole-brain white matter parcellation across the lifespan (from neonates to elderly subjects, including brain tumor patients) without the need for registration.
Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Community
The research field of Information Retrieval (IR) has evolved significantly, expanding beyond traditional search to meet diverse user information needs.
Deep neural networks from the perspective of ergodic theory
The design of deep neural networks remains somewhat of an art rather than precise science.
Unleashing the Strengths of Unlabeled Data in Pan-cancer Abdominal Organ Quantification: the FLARE22 Challenge
The best-performing algorithms successfully generalized to holdout external validation sets, achieving a median DSC of 89. 5\%, 90. 9\%, and 88. 3\% on North American, European, and Asian cohorts, respectively.
Audio is all in one: speech-driven gesture synthetics using WavLM pre-trained model
Firstly, considering that speech audio not only contains acoustic and semantic features but also conveys personality traits, emotions, and more subtle information related to accompanying gestures, we pioneer the adaptation of WavLM, a large-scale pre-trained model, to extract low-level and high-level audio information.
MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition
In the analysis and ablation study, we demonstrate that our method compared with previous work can effectively increase the diversity of experts, significantly reduce the variance of the model, and improve recognition accuracy.
Ranked #5 on
Long-tail Learning
on CIFAR-10-LT (ρ=50)
Ear-Keeper: Real-time Diagnosis of Ear Lesions Utilizing Ultralight-Ultrafast ConvNet and Large-scale Ear Endoscopic Dataset
Deep learning-based ear disease diagnosis technology has proven effective and affordable.
