Search Results for author:
Found 267 papers, 77 papers with code
ReDro: Efficiently Learning Large-sized SPD Visual Representation
When learning this representation in deep networks, eigen-decomposition of covariance matrix is usually needed for a key step called matrix normalisation.
ASCM: An Answer Space Clustered Prompting Method without Answer Engineering
We also propose a stable semi-supervised method named stair learning (SL) that orderly distills knowledge from better models to weaker models.
基于预训练语言模型的案件要素识别方法(A Method for Case Factor Recognition Based on Pre-trained Language Models)
案件要素识别指将案件描述中重要事实描述自动抽取出来, 并根据领域专家设计的要素体系进行分类, 是智慧司法领域的重要研究内容。基于传统神经网络的文本编码难以提取深层次特征, 基于阈值的多标签分类难以捕获标签间依赖关系, 因此本文提出了基于预训练语言模型的多标签文本分类模型。该模型采用以Layer-attentive策略进行特征融合的语言模型作为编码器, 使用基于LSTM的序列生成模型作为解码器。在“CAIL2019”数据集上进行实验, 该方法比基于循环神经网络的算法在F1值上最高可提升7. 6%, 在相同超参数设置下比基础语言模型(BERT)提升约3. 2%。
RotateCT: Knowledge Graph Embedding by Rotation and Coordinate Transformation in Complex Space
Knowledge graph embedding, which aims to learn representations of entities and relations in knowledge graphs, finds applications in various downstream tasks.
CMLCompiler: A Unified Compiler for Classical Machine Learning
Without a unified framework, the hybrid deployments of deep learning (DL) and CML also suffer from severe performance and portability issues.
High-level semantic feature matters few-shot unsupervised domain adaptation
However, the goal of FS-UDA and FSL are relevant yet distinct, since FS-UDA aims to classify the samples in target domain rather than source domain.
A GOA-Based Fault-Tolerant Trajectory Tracking Control for an Underwater Vehicle of Multi-Thruster System without Actuator Saturation
This paper proposes an intelligent fault-tolerant control (FTC) strategy to tackle the trajectory tracking problem of an underwater vehicle (UV) under thruster damage (power loss) cases and meanwhile resolve the actuator saturation brought by the vehicle's physical constraints.
Quality at the Tail
However, we found that the inference quality of state-of-the-art and state-of-the-practice in practical applications has a long tail distribution.
a cognitive frequency allocation strategy for multi-carrier radar against communication interference
To address this challenge, we use a novel iteratively selecting technique which breaks a difficult decision task into several easy tasks.
ToL: A Tensor of List-Based Unified Computation Model
This article presents a unified computation model with generalized expression ability and a concise set of primitive operators for programming high-level algorithms.
Domain Generalization by Learning and Removing Domain-specific Features
With the images output by the encoder-decoder network, another classifier is designed to learn the domain-invariant features to conduct image classification.
Generalizing Math Word Problem Solvers via Solution Diversification
In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator.
Recent Advances in RecBole: Extensions with more Practical Considerations
In order to show the recent update in RecBole, we write this technical report to introduce our latest improvements on RecBole.
Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models
In this paper, we propose a new model architecture with alignment-enriched tuning (dubbed AETNet) upon pre-trained document image models, to adapt downstream tasks with the joint task-specific supervised and alignment-aware contrastive objective.
A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix
In this study, we present a new unified contrastive learning representation framework (named UniCLR) suitable for all the above four kinds of methods from a novel perspective of basic affinity matrix.
Explainable and Safe Reinforcement Learning for Autonomous Air Mobility
Although DRL has achieved important advancements in this field, the existing works pay little attention to the explainability and safety issues related to DRL controllers, particularly the safety under adversarial attacks.
A Review of Intelligent Music Generation Systems
Intelligent music generation, one of the most popular subfields of computer creativity, can lower the creative threshold for non-specialists and increase the efficiency of music creation.
Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis
In this work, we propose a novel Syntax-guided Domain Adaptation Model, named SDAM, for more effective cross-domain ABSA.
A Case Study of Chinese Sentiment Analysis on Social Media Reviews Based on LSTM
Finally, sentiment analysis results were obtained by analyzing the comments with the LSTM model.
Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective
We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items.
Uncertainty-DTW for Time Series and Sequences
Dynamic Time Warping (DTW) is used for matching pairs of sequences and celebrated in applications such as forecasting the evolution of time series, clustering time series or even matching sequence pairs in few-shot action recognition.
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition
To factor out misalignment between query and support sequences of 3D body joints, we propose an advanced variant of Dynamic Time Warping which jointly models each smooth path between the query and support frames to achieve simultaneously the best alignment in the temporal and simulated camera viewpoint spaces for end-to-end learning under the limited few-shot training data.
Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection
To address these drawbacks, we propose a Time-rEversed diffusioN tEnsor Transformer (TENET), which i) forms high-order tensor representations that capture multi-way feature occurrences that are highly discriminative, and ii) uses a transformer that dynamically extracts correlations between the query image and the entire support set, instead of a single average-pooled support embedding.
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models
Motivated by such considerations, we propose a collaborative optimization for PLMs that integrates static model compression and dynamic inference acceleration.
Recommendation with User Active Disclosing Willingness
Recommender system has been deployed in a large amount of real-world applications, profoundly influencing people's daily life and production. Traditional recommender models mostly collect as comprehensive as possible user behaviors for accurate preference estimation.
TPU-MLIR: A Compiler For TPU Using MLIR
Multi-level intermediate representations (MLIR) show great promise for reducing the cost of building domain-specific compilers by providing a reusable and extensible compiler infrastructure.
S2WAT: Image Style Transfer via Hierarchical Vision Transformer using Strips Window Attention
This paper presents a new hierarchical vision Transformer for image style transfer, called Strips Window Attention Transformer (S2WAT), which serves as an encoder of encoder-transfer-decoder architecture.
Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecture
Synthetic voice and splicing audio clips have been generated to spoof Internet users and artificial intelligence (AI) technologies such as voice authentication.
Cloud-based Automatic Speech Recognition Systems for Southeast Asian Languages
This paper provides an overall introduction of our Automatic Speech Recognition (ASR) systems for Southeast Asian languages.
Pronunciation Modeling of Foreign Words for Mandarin ASR by Considering the Effect of Language Transfer
This paper focuses on examining the phonetic effect of language transfer in automatic speech recognition.
Pseudo-Label Generation and Various Data Augmentation for Semi-Supervised Hyperspectral Object Detection
To overcome these difficulties, this paper first select fewer but suitable data augmentation methods to improve the accuracy of the supervised model based on the labeled training set, which is suitable for the characteristics of hyperspectral images.
On Embeddings and Inverse Embeddings of Input Design for Regularized System Identification
For the emerging regularized system identification, the study on input design has just started, and it is often formulated as a non-convex optimization problem that minimizes a scalar measure of the Bayesian mean squared error matrix subject to certain constraints, and the state-of-art method is the so-called quadratic mapping and inverse embedding (QMIE) method, where a time domain inverse embedding (TDIE) is proposed to find the inverse of the quadratic mapping.
GaitFM: Fine-grained Motion Representation for Gait Recognition
Gait recognition aims at identifying individual-specific walking patterns, which is highly dependent on the observation of the different periodic movements of each body part.
A deep variational free energy approach to dense hydrogen
We present a deep generative model-based variational free energy approach to the equations of state of dense hydrogen.
Explanation Guided Contrastive Learning for Sequential Recommendation
Recently, contrastive learning has been applied to the sequential recommendation task to address data sparsity caused by users with few item interactions and items with few user adoptions.
Improving Compositional Generalization in Math Word Problem Solving
To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods.
A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints
Decentralized optimization with orthogonality constraints is found widely in scientific computing and data science.
A Medical Semantic-Assisted Transformer for Radiographic Report Generation
Automated radiographic report generation is a challenging cross-domain task that aims to automatically generate accurate and semantic-coherence reports to describe medical images.
Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy
Second, to reduce the accuracy loss led by differential privacy noise and the huge communication overhead of MPL, we propose two optimization methods for the training process of MPL: (1) the data-independent feature extraction method, which aims to simplify the trained model structure; (2) the local data-based global model initialization method, which aims to speed up the convergence of the model training.
Scalable and Sparsity-Aware Privacy-Preserving K-means Clustering with Application to Fraud Detection
The second type is provable secure but is inefficient and even helpless for the large-scale data sparsity scenario.
Instance Image Retrieval by Learning Purely From Within the Dataset
Although achieving promising results, this approach is restricted by two issues: 1) the domain gap between benchmark datasets and the dataset of a given retrieval task; 2) the required auxiliary dataset cannot be readily obtained.
RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning
In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-supervised learning (SSL), which is a hyperparameter-free framework that is independent of confidence threshold and works with both the matched (conventionally) and the mismatched class distributions.
Primitive Graph Learning for Unified Vector Mapping
Then, we convert vector shape prediction, regularization, and topology reconstruction into a unique primitive graph learning problem.
FactorVAE: A Probabilistic Dynamic Factor Model Based on Variational Autoencoder for Predicting Cross-Sectional Stock Returns
As an asset pricing model in economics and finance, factor model has been widely used in quantitative investment.
Attitude estimation from vector measurements: Necessary and sufficient conditions and convergent observer design
The paper addresses the problem of attitude estimation for rigid bodies using (possibly time-varying) vector measurements, for which we provide a necessary and sufficient condition of distinguishability.
Constructing Cross-lingual Consumer Health Vocabulary with Word-Embedding from Comparable User Generated Content
To analyze the health consumer-generated content (HCGC) from the OHCs, identifying the colloquial medical expressions used by laypeople is a critical challenge.
TC-SfM: Robust Track-Community-Based Structure-from-Motion
Specifically, a novel structure is proposed, namely, {\textit{track-community}}, in which each community consists of a group of tracks and represents a local segment in the scene.
Contrastive Centroid Supervision Alleviates Domain Shift in Medical Image Classification
Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world data differ in imaging equipment manufacturer, image acquisition protocol, patient populations, etc.
Fast and Arbitrary Beam Pattern Design for RIS-Assisted Terahertz Wireless Communication
Reconfigurable intelligent surface (RIS) can assist terahertz wireless communication to restore the fragile line-of-sight links and facilitate beam steering.
Predicting Time-to-conversion for Dementia of Alzheimer's Type using Multi-modal Deep Survival Analysis
Combining MRI and genetic features improved survival prediction over using either modality alone, but adding CDC to any combination of features only worked as well as using only CDC features.
Revealing the CO2 emission reduction of ridesplitting and its determinants based on real-world data
Integrating the trip data with the COPERT model, this study calculates the CO2 emissions of shared rides (ridesplitting) and their substituted single rides (regular ridesourcing) to estimate the CO2 emission reduction of each ridesplitting trip.
MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization
The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.
Topological EEG Nonlinear Dynamics Analysis for Emotion Recognition
The proposed work is the first investigation in the emotion recognition oriented EEG topological feature analysis, which brought a novel insight into the brain neural system nonlinear dynamics analysis and feature extraction.
Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition
Given this observation, we devised a graph-inspired deep learning approach toward the sensor-based HAR tasks, which was further used to build a deep transfer learning model toward giving a tentative solution for these two challenging problems.
Machine Learning Based Multimodal Neuroimaging Genomics Dementia Score for Predicting Future Conversion to Alzheimer's Disease
Using a pre-defined 0. 5 threshold on DAT scores, we predicted whether or not a subject would develop DAT in the future.
Two-stream Hierarchical Similarity Reasoning for Image-text Matching
Second, previous approaches only consider learning single-stream similarity alignment (i. e., image-to-text level or text-to-image level), which is inadequate to fully use similarity information for image-text matching.
CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
In each non-output layer of the GCN, this framework uses a hub attention mechanism to assign new weights to connected non-hub vertices based on their common information with hub vertices.
Active and Passive Hybrid Detection Method for Power CPS False Data Injection Attacks with Improved AKF and GRU-CNN
Taking account of the fact that the existing knowledge-driven detection process for FDIAs has been in a passive detection state for a long time and ignores the advantages of data-driven active capture of features, an active and passive hybrid detection method for power CPS FDIAs with improved adaptive Kalman filter (AKF) and convolutional neural networks (CNN) is proposed in this paper.
AD-NEGF: An End-to-End Differentiable Quantum Transport Simulator for Sensitivity Analysis and Inverse Problems
Since proposed in the 70s, the Non-Equilibrium Green Function (NEGF) method has been recognized as a standard approach to quantum transport simulations.
Graph Neural Network with Curriculum Learning for Imbalanced Node Classification
Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification.
Self-consistent Gradient-like Eigen Decomposition in Solving Schrödinger Equations
The Schr\"odinger equation is at the heart of modern quantum mechanics.
A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification
Different from the conventional data augmentation, the proposed domain-aware mix-normalization to enhance the diversity of features during training from the normalization view of the neural network, which can effectively alleviate the model overfitting to the source domains, so as to boost the generalization capability of the model in the unseen domain.
Indirect Adaptive Control of Nonlinearly Parameterized Nonlinear Dissipative Systems
In this note we address the problem of indirect adaptive (regulation or tracking) control of nonlinear, input affine dissipative systems.
$m^\ast$ of two-dimensional electron gas: a neural canonical transformation study
The quasiparticle effective mass $m^\ast$ of interacting electrons is a fundamental quantity in the Fermi liquid theory.
Kernelized Few-Shot Object Detection With Efficient Integral Aggregation
We design a Kernelized Few-shot Object Detector by leveraging kernelized matrices computed over multiple proposal regions, which yield expressive non-linear representations whose model complexity is learned on the fly.
DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning
Consistency-based Semi-supervised learning (SSL) has achieved promising performance recently.
StyTr2: Image Style Transfer With Transformers
The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content.
Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function
In this paper, we focus on the decentralized optimization problem over the Stiefel manifold, which is defined on a connected network of $d$ agents.
Integrating Quantum Processor Device and Control Optimization in a Gradient-based Framework
In a quantum processor, the device design and external controls together contribute to the quality of the target quantum operations.
3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve
In this paper, we propose a Few-shot Learning pipeline for 3D skeleton-based action recognition by Joint tEmporal and cAmera viewpoiNt alIgnmEnt (JEANIE).
A Multi-View Framework for BGP Anomaly Detection via Graph Attention Network
As the default protocol for exchanging routing reachability information on the Internet, the abnormal behavior in traffic of Border Gateway Protocols (BGP) is closely related to Internet anomaly events.
Analysis and Evaluation of Kinect-based Action Recognition Algorithms
Human action recognition still exists many challenging problems such as different viewpoints, occlusion, lighting conditions, human body size and the speed of action execution, although it has been widely used in different areas.
Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework
A significance of our work lies in that it shows the potential of unsupervised domain generalization for person ReID and sets a strong baseline for the further research on this topic.
Learning Dynamic Compact Memory Embedding for Deformable Visual Object Tracking
To address this issue, segmentation-based trackers have been proposed that employ per-pixel matching to improve the tracking performance of deformable objects effectively.
Block-Sparse Recovery Network for Two-Dimensional Harmonic Retrieval
As a typical signal processing problem, multidimensional harmonic retrieval (MHR) has been adapted to a wide range of applications in signal processing.
A Novel Sample-efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Cardiac Catheterization Robots
Robotic catheterization is typically used for percutaneous coronary intervention procedures nowadays and it involves steering flexible endovascular tools to open up occlusion in the coronaries.
R4: A Framework for Route Representation and Route Recommendation
For user representation, we utilize a series of historical navigation to extract user preference.
Graph Partner Neural Networks for Semi-Supervised Learning on Graphs
Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification.
High-order Tensor Pooling with Attention for Action Recognition
We aim at capturing high-order statistics of feature vectors formed by a neural network, and propose end-to-end second- and higher-order pooling to form a tensor descriptor.
Ranked #2 on
Scene Recognition
on YUP++
(using extra training data)
Differential Privacy with Manifold Data Dependency
In this paper, we study dataset processing mechanisms generated by linear queries in the presence of manifold data dependency.
Distributed Zeroth-Order Optimization: Convergence Rates That Match Centralized Counterpart
Zeroth-order optimization has become increasingly important in complex optimization and machine learning when cost functions are impossible to be described in closed analytical forms.
Heterologous Normalization
Specifically, it calculates the mean like Batch Normalization to maintain the advantage of Batch Normalization.
Network Learning in Quadratic Games from Fictitious Plays
Next, in view of the inherent stability and sparsity constraints for the network interaction structure, we propose a stable and sparse system identification framework for learning the interaction graph from full player action observations.
A hierarchical residual network with compact triplet-center loss for sketch recognition
Last but not least, the compact triplet-center loss is proposed specifically for the sketch recognition task.
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.
Progressive Hard-case Mining across Pyramid Levels for Object Detection
Based on focal loss with ATSS-R50, our approach achieves 40. 5 AP, surpassing the state-of-the-art QFL (Quality Focal Loss, 39. 9 AP) and VFL (Varifocal Loss, 40. 1 AP).
LibFewShot: A Comprehensive Library for Few-shot Learning
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
MWPToolkit: An Open-Source Framework for Deep Learning-Based Math Word Problem Solvers
Over the last few years, there are a growing number of datasets and deep learning-based methods proposed for effectively solving MWPs.
Ranked #6 on
Math Word Problem Solving
on Math23K
Observability is Sufficient for the Design of Globally Exponentially Convergent State Observers for State-affine Nonlinear Systems
In this paper we are interested in the problem of state observation of state-affine nonlinear systems.
Identifiability Implies Robust, Globally Exponentially Convergent On-line Parameter Estimation: Application to Model Reference Adaptive Control
The estimators are shown to be robust to additive measurement noise and--not necessarily slow--parameter variations.
Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Training
One-shot neural architecture search (NAS) applies weight-sharing supernet to reduce the unaffordable computation overhead of automated architecture designing.
Cascade Bagging for Accuracy Prediction with Few Training Samples
To alleviate this problem, we propose a novel framework to train an accuracy predictor under few training samples.
Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
Inspired by the recent local descriptor based few-shot learning (FSL), our general UDA model is fully built upon local descriptors (LDs) for image classification and domain adaptation.
MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving
Math word problem (MWP) solving faces a dilemma in number representation learning.
Ranked #3 on
Math Word Problem Solving
on MathQA
Trade When Opportunity Comes: Price Movement Forecasting via Locality-Aware Attention and Iterative Refinement Labeling
To address this issue, we propose a novel price movement forecasting framework, called Locality-Aware Attention and Iterative Refinement Labeling(LARA), which consists of two main components: 1)Locality-aware attention automatically extracts the potentially profitable samples by attending to surrounding class-aware label information.
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.
Hand Image Understanding via Deep Multi-Task Learning
To further improve the performance of these tasks, we propose a novel Hand Image Understanding (HIU) framework to extract comprehensive information of the hand object from a single RGB image, by jointly considering the relationships between these tasks.
Triplet is All You Need with Random Mappings for Unsupervised Visual Representation Learning
However, this type of methods, such as SimCLR and MoCo, relies heavily on a large number of negative pairs and thus requires either large batches or memory banks.
A Self-Boosting Framework for Automated Radiographic Report Generation
On one hand, the image-text matching branch helps to learn highly text-correlated visual features for the report generation branch to output high quality reports.
Signal Acquisition of Luojia-1A Low Earth Orbit Navigation Augmentation System with Software Defined Receiver
The performance of those integration algorithms on expanding the successful acquisition time range is verified by the real data collected from the Luojia-1A satellite.
RFCBF: enhance the performance and stability of Fast Correlation-Based Filter
Feature selection is a preprocessing step which plays a crucial role in the domain of machine learning and data mining.
StyTr$^2$: Image Style Transfer with Transformers
The goal of image style transfer is to render an image with artistic features guided by a style reference while maintaining the original content.
Hybrid gene selection approach using XGBoost and multi-objective genetic algorithm for cancer classification
In the second stage, XGBoost-MOGA searches for an optimal gene subset based on the most relevant genes's group using a multi-objective optimization genetic algorithm.
A Novel Framework Integrating AI Model and Enzymological Experiments Promotes Identification of SARS-CoV-2 3CL Protease Inhibitors and Activity-based Probe
The identification of protein-ligand interaction plays a key role in biochemical research and drug discovery.
Investigating Math Word Problems using Pretrained Multilingual Language Models
In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective.
Machine Translation
Pretrained Multilingual Language Models
+1
Ab-initio study of interacting fermions at finite temperature with neural canonical transformation
The variational density matrix is parametrized by a permutation equivariant many-body unitary transformation together with a discrete probabilistic model.
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
Recent skeleton-based action recognition methods extract features from 3D joint coordinates as spatial-temporal cues, using these representations in a graph neural network for feature fusion to boost recognition performance.
Ranked #11 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases.
Ranked #6 on
Long-tail Learning
on CIFAR-100-LT (ρ=10)
Shift-and-Balance Attention
The attention branch is gated using the Sigmoid function and multiplied by the feature map's trunk branch.
DeepStyle: User Style Embedding for Authorship Attribution of Short Texts
Authorship attribution (AA), which is the task of finding the owner of a given text, is an important and widely studied research topic with many applications.
Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
For learning pseudo mask generator from the auxiliary dataset, we present a bi-level optimization formulation.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Network Representation Learning: From Traditional Feature Learning to Deep Learning
Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data.
Coordinated Cyber-Attack Detection Model of Cyber-Physical Power System Based on the Operating State Data Link
Existing coordinated cyber-attack detection methods have low detection accuracy and efficiency and poor generalization ability due to difficulties dealing with unbalanced attack data samples, high data dimensionality, and noisy data sets.
HPC AI500: Representative, Repeatable and Simple HPC AI Benchmarking
Recent years witness a trend of applying large-scale distributed deep learning algorithms (HPC AI) in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality.
Image Classification
Performance
Modeling Method for the Coupling Relations of Microgrid Cyber-Physical Systems Driven by Hybrid Spatiotemporal Events
Considering the constraints of the temporal conversion of information flow and energy flow, a microgrid CPS coupling model is established, the effectiveness of which is verified by simulating false data injection attack (FDIA) scenarios.
Unified First-Principles Study of the Anomalous Hall Effect Based on Exact Muffin-Tin Orbitals
Based on the exact muffin-tin orbitals (EMTOs), we developed a first-principles method to calculate the current operators and investigated the anomalous Hall effect in bcc Fe as an example, with which we successfully separated the skew scattering contribution from the side jump and intrinsic contributions by fitting the scaling law with the introduction of sparse impurities.
Materials Science Mesoscale and Nanoscale Physics
Pruning and Quantization for Deep Neural Network Acceleration: A Survey
We discuss trade-offs in element-wise, channel-wise, shape-wise, filter-wise, layer-wise and even network-wise pruning.
BV-Person: A Large-Scale Dataset for Bird-View Person Re-Identification
In this work we introduce a new ReID task, bird-view person ReID, which aims at searching for a person in a gallery of horizontal-view images with the query images taken from a bird's-eye view, i. e., an elevated view of an object from above.
Optimizing Information Bottleneck in Reinforcement Learning: A Stein Variational Approach
We also show that our method achieves better performance than VIB and mutual information neural estimation (MINE), two other popular approaches to optimize the information bottleneck framework in supervised learning.
Pretrain-to-Finetune Adversarial Training via Sample-wise Randomized Smoothing
For certification, we carefully allocate specific robust regions for each test sample.
LoFGAN: Fusing Local Representations for Few-Shot Image Generation
Given only a few available images for a novel unseen category, few-shot image generation aims to generate more data for this category.
Tensor Representations for Action Recognition
In this paper, we propose novel tensor representations for compactly capturing such higher-order relationships between visual features for the task of action recognition.
Ranked #2 on
Skeleton Based Action Recognition
on UT-Kinect
Finite Simple Groups: Factorizations, Regular Subgroups, and Cayley Graphs
This paper addresses the factorization problem of almost simple groups, studies regular subgroups of quasiprimitive permutation groups, and characterizes $s$-arc transitive Cayley graphs of finite simple groups.
Group Theory
Learning geometry-image representation for 3D point cloud generation
We study the problem of generating point clouds of 3D objects.
Visual place recognition: A survey from deep learning perspective
Visual place recognition has attracted widespread research interest in multiple fields such as computer vision and robotics.
Decoding PPP Corrections from BDS B2b Signals Using a Software-defined Receiver: an Initial Performance Evaluation
With the rapid development of China's BeiDou Navigation Satellite System(BDS), the application of real-time precise point positioning (RTPPP) based on BDS has become an active research area in the field of Global Navigation Satellite System (GNSS).
w-Net: Dual Supervised Medical Image Segmentation Model with Multi-Dimensional Attention and Cascade Multi-Scale Convolution
Non-local attention and feature learning by multi-scale methods are widely used to model network, which drives progress in medical image segmentation.
ASMFS: Adaptive-Similarity-based Multi-modality Feature Selection for Classification of Alzheimer's Disease
With the increasing amounts of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become an important research direction in medical image analysis.
S3ML: A Secure Serving System for Machine Learning Inference
We present S3ML, a secure serving system for machine learning inference in this paper.
Supervised Learning with Projected Entangled Pair States
Tensor networks, a model that originated from quantum physics, has been gradually generalized as efficient models in machine learning in recent years.
Biomedical named entity recognition using BERT in the machine reading comprehension framework
Using the sequence labeling framework to implement biomedical named entity recognition (BioNER) is currently a conventional method.
When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control
In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security.
Shifu2: A Network Representation Learning Based Model for Advisor-advisee Relationship Mining
The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines.
Tropical Tensor Network for Ground States of Spin Glasses
We present a unified exact tensor network approach to compute the ground state energy, identify the optimal configuration, and count the number of solutions for spin glasses.
Statistical Mechanics Quantum Physics Computation
MODEL: Motif-based Deep Feature Learning for Link Prediction
Link prediction plays an important role in network analysis and applications.
Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image
As a result, it exploits more discriminative features for DR grading.
Residual-CycleGAN based Camera Adaptation for Robust Diabetic Retinopathy Screening
How can we train a classification model on labeled fundus images ac-quired from only one camera brand, yet still achieves good performance on im-ages taken by other brands of cameras?
Robust Retinal Vessel Segmentation from a Data Augmentation Perspective
In this paper, we propose two new data augmentation modules, namely, channel-wise random Gamma correction and channel-wise random vessel augmentation.
Graph-to-Tree Learning for Solving Math Word Problems
While the recent tree-based neural models have demonstrated promising results in generating solution expression for the math word problem (MWP), most of these models do not capture the relationships and order information among the quantities well.
Ranked #6 on
Math Word Problem Solving
on MAWPS
Human Activity Recognition based on Dynamic Spatio-Temporal Relations
In the proposed method, an activity is divided into several successive actions represented by spatio temporal patterns, and the evolution of these actions are captured by a sequential model.
SeqXFilter: A Memory-efficient Denoising Filter for Dynamic Vision Sensors
We not only give the visual denoising effect of the filter but also use two metrics for quantitatively analyzing the filter's performance.
Large-Scale Secure XGB for Vertical Federated Learning
Privacy-preserving machine learning has drawn increasingly attention recently, especially with kinds of privacy regulations come into force.
Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks
To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN).
Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains.
AIBench Scenario: Scenario-distilling AI Benchmarking
We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark.
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.
Continuous matrix product operator approach to finite temperature quantum states
We present an algorithm for studying quantum systems at finite temperature using continuous matrix product operator representation.
Strongly Correlated Electrons Statistical Mechanics Computational Physics
Class Distribution Alignment for Adversarial Domain Adaptation
To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains.
Secret Sharing based Secure Regressions with Applications
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.
A Noise Filter for Dynamic Vision Sensors using Self-adjusting Threshold
Neuromorphic event-based dynamic vision sensors (DVS) have much faster sampling rates and a higher dynamic range than frame-based imagers.
Emerging Technologies Signal Processing
A Neural Architecture Search based Framework for Liquid State Machine Design
By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity.
Exploration of Input Patterns for Enhancing the Performance of Liquid State Machines
To mitigate the difficulty in effectively dealing with huge input spaces of LSM, and to find that whether input reduction can enhance LSM performance, we explore several input patterns, namely fullscale, scanline, chessboard, and patch.
DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
Neural Architecture Search (NAS) has shown great potentials in automatically designing scalable network architectures for dense image predictions.
Ranked #7 on
Semantic Segmentation
on Cityscapes test
Multi-AI competing and winning against humans in iterated Rock-Paper-Scissors game
We model and predict human competition behavior by combining many Markov Models with different fixed memory lengths (abbreviated as "multi-AI"), and develop an architecture of multi-AI with changeable parameters to adapt to different competition strategies.
Extended Batch Normalization
To alleviate the problem caused by small batch size, extended batch normalization computes the standard deviation along the (N, C, H, W) dimensions, thus enlarges the number of samples from which the standard deviation is computed.
Ranked #59 on
Image Classification
on STL-10
Industrial Scale Privacy Preserving Deep Neural Network
Deep Neural Network (DNN) has been showing great potential in kinds of real-world applications such as fraud detection and distress prediction.
Exploration of Surgeons' Natural Skills for Robotic Catheterization
Despite having the robotic catheter systems which have recently emerged as safe way of performing cardiovascular interventions, a number of important challenges are yet to be investigated.
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.
Asymmetric Distribution Measure for Few-shot Learning
Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.
How Distance Transform Maps Boost Segmentation CNNs: An Empirical Study
The \emph{second contribution} is that we systematically evaluated five benchmark methods on two representative public datasets.
Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors
In this paper, we build on a concept of self-supervision by taking RGB frames as input to learn to predict both action concepts and auxiliary descriptors e. g., object descriptors.
Ranked #1 on
Scene Recognition
on YUP++
(using extra training data)
Solving Quantum Statistical Mechanics with Variational Autoregressive Networks and Quantum Circuits
We extend the ability of unitary quantum circuits by interfacing it with classical autoregressive neural networks.
Quantum Physics
Yao.jl: Extensible, Efficient Framework for Quantum Algorithm Design
We introduce Yao, an extensible, efficient open-source framework for quantum algorithm design.
Quantum Physics Strongly Correlated Electrons Computational Physics
ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard
21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.
Application of Word2vec in Phoneme Recognition
At the same time, in order to solve the problem of overfitting in the 61 phoneme recognition model on TIMIT dataset, we propose a new training method.
BenchCouncil's View on Benchmarking AI and Other Emerging Workloads
This paper outlines BenchCouncil's view on the challenges, rules, and vision of benchmarking modern workloads like Big Data, AI or machine learning, and Internet Services.
Differentiable Meta-learning Model for Few-shot Semantic Segmentation
To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.
Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge
Furthermore, the Gaussian probability distribution can effectively improve the extraction performance of sentences with overlapping relations in biomedical relation extraction tasks.
Deep Learning based HEp-2 Image Classification: A Comprehensive Review
This paper provides a comprehensive review of the existing deep learning based HEp-2 cell image classification methods.
Defensive Few-shot Adversarial Learning
In this paper, instead of assuming such a distribution consistency, we propose to make this assumption at a task-level in the episodic training paradigm in order to better transfer the defense knowledge.
End-to-end speech enhancement based on discrete cosine transform
Previous speech enhancement methods focus on estimating the short-time spectrum of speech signals due to its short-term stability.
Ranked #17 on
Speech Enhancement
on DEMAND
Sound Audio and Speech Processing