Search Results for author:
Found 164 papers, 30 papers with code
Discriminative Partial Domain Adversarial Network
Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain.
Applications of Large Language Models in Data Processing: Innovative Approaches to Segmenting and Renewing Information
This paper is the first to enhance specific-domain code generation effectiveness from this perspective.
YUAN 2.0: A Large Language Model with Localized Filtering-based Attention
In this work, the Localized Filtering-based Attention (LFA) is introduced to incorporate prior knowledge of local dependencies of natural language into Attention.
Towards Graph-Aware Diffusion Modeling for Collaborative Filtering
Recovering masked feedback with neural models is a popular paradigm in recommender systems.
Toward Generative Data Augmentation for Traffic Classification
Data Augmentation (DA)-augmenting training data with synthetic samples-is wildly adopted in Computer Vision (CV) to improve models performance.
Minimax Optimal Transfer Learning for Kernel-based Nonparametric Regression
This paper focuses on investigating the transfer learning problem within the context of nonparametric regression over a reproducing kernel Hilbert space.
Hyperspectral Image Fusion via Logarithmic Low-rank Tensor Ring Decomposition
On the other hand, the tensor nuclear norm (TNN)-based approaches have recently demonstrated to be more efficient on keeping high-dimensional low-rank structures in tensor recovery.
NeuroQuantify -- An Image Analysis Software for Detection and Quantification of Neurons and Neurites using Deep Learning
The segmentation of cells and neurites in microscopy images of neuronal networks provides valuable quantitative information about neuron growth and neuronal differentiation, including the number of cells, neurites, neurite length and neurite orientation.
Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift
Two types of covariate shift problems are the focus of this paper and the sharp convergence rates are established for a general loss function to provide a unified theoretical analysis, which concurs with the optimal results in literature where the squared loss is used.
CoPAL: Corrective Planning of Robot Actions with Large Language Models
In the pursuit of fully autonomous robotic systems capable of taking over tasks traditionally performed by humans, the complexity of open-world environments poses a considerable challenge.
Spatiotemporal Image Reconstruction to Enable High-Frame Rate Dynamic Photoacoustic Tomography with Rotating-Gantry Volumetric Imagers
Aim: The aim of this study is to develop a spatiotemporal image reconstruction (STIR) method for dynamic PACT that can be applied to commercially available volumetric PACT imagers that employ a sequential scanning strategy.
Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation
Over the last years we witnessed a renewed interest toward Traffic Classification (TC) captivated by the rise of Deep Learning (DL).
DeepVol: A Pre-Trained Universal Asset Volatility Model
This paper introduces DeepVol, a pre-trained deep learning volatility model that is more general than traditional econometric models.
U-SEANNet: A Simple, Efficient and Applied U-Shaped Network for Diagnosis of Nasal Diseases on Nasal Endoscopic Images
Our findings suggest U-SEANNet is the state-of-the-art model for nasal diseases diagnosis in endoscopic images.
Robust retrieval of material chemical states in X-ray microspectroscopy
X-ray microspectroscopic techniques are essential for studying morphological and chemical changes in materials, providing high-resolution structural and spectroscopic information.
Certifying the Fairness of KNN in the Presence of Dataset Bias
We propose a method for certifying the fairness of the classification result of a widely used supervised learning algorithm, the k-nearest neighbors (KNN), under the assumption that the training data may have historical bias caused by systematic mislabeling of samples from a protected minority group.
Systematic Testing of the Data-Poisoning Robustness of KNN
In other words, they cannot falsify the truly-non-robust cases.
Bayesian inference for data-efficient, explainable, and safe robotic motion planning: A review
Fifth, we systematically present the hybridization of Bayesian inference and RL which is a promising direction to improve the convergence of RL for better motion planning.
DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration
With the two cascaded subtasks, DRM-IR first dynamically models the task-specific degradation based on a reference image pair and further restores the image with the collected degradation statistics.
The Staged Knowledge Distillation in Video Classification: Harmonizing Student Progress by a Complementary Weakly Supervised Framework
Our proposed substage-based distillation approach has the potential to inform future research on label-efficient learning for video data.
Generalized Time Warping Invariant Dictionary Learning for Time Series Classification and Clustering
Dictionary learning is an effective tool for pattern recognition and classification of time series data.
Practice with Graph-based ANN Algorithms on Sparse Data: Chi-square Two-tower model, HNSW, Sign Cauchy Projections
In this paper, we report our exploration of efficient search in sparse data with graph-based ANN algorithms (e. g., HNSW, or SONG which is the GPU version of HNSW), which are popular in industrial practice, e. g., search and ads (advertising).
Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification
The popularity of Deep Learning (DL), coupled with network traffic visibility reduction due to the increased adoption of HTTPS, QUIC and DNS-SEC, re-ignited interest towards Traffic Classification (TC).
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
In this paper, we propose Speech-text dialog Pre-training for spoken dialog understanding with ExpliCiT cRoss-Modal Alignment (SPECTRA), which is the first-ever speech-text dialog pre-training model.
Ranked #1 on
Multimodal Sentiment Analysis
on MOSI
Emotion Recognition in Conversation
Multimodal Intent Recognition
+1
Causal Document-Grounded Dialogue Pre-training
To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora.
Preference or Intent? Double Disentangled Collaborative Filtering
In this way, the low-rating items will be treated as positive samples for modeling intents while the negative samples for modeling preferences.
Towards an Accurate and Secure Detector against Adversarial Perturbations
It expands the above works on two aspects: 1) the introduced Krawtchouk basis provides better spatial-frequency discriminability and thereby is more suitable for capturing adversarial patterns than the common trigonometric or wavelet basis; 2) the extensive parameters for decomposition are generated by a pseudo-random function with secret keys, hence blocking the defense-aware adversarial attack.
Doc2SoarGraph: Discrete Reasoning over Visually-Rich Table-Text Documents with Semantic-Oriented Hierarchical Graphs
Discrete reasoning over table-text documents (e. g., financial reports) gains increasing attention in recent two years.
A Diffusion-based Method for Multi-turn Compositional Image Generation
We introduce a conditioning scheme to generate the target image based on the fusion results.
Deep Learning Enhanced Realized GARCH
We propose a new approach to volatility modeling by combining deep learning (LSTM) and realized volatility measures.
Bi-level Multi-objective Evolutionary Learning: A Case Study on Multi-task Graph Neural Topology Search
It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution.
Representing Noisy Image Without Denoising
In this paper, we explore a non-learning paradigm that aims to derive robust representation directly from noisy images, without the denoising as pre-processing.
Image Cropping With Spatial-Aware Feature and Rank Consistency
To address the first issue, we propose spatial-aware feature to encode the spatial relationship between candidate crops and aesthetic elements, by feeding the concatenation of crop mask and selectively aggregated feature maps to a light-weighted encoder.
Context-Aware Pretraining for Efficient Blind Image Decomposition
(2) The conventional paradigm usually focuses on mining the abnormal pattern of a superimposed image to separate the noise, which de facto conflicts with the primary image restoration task.
Generative Graph Neural Networks for Link Prediction
Instead of sampling positive and negative links and heuristically computing the features of their enclosing subgraphs, GraphLP utilizes the feature learning ability of deep-learning models to automatically extract the structural patterns of graphs for link prediction under the assumption that real-world graphs are not locally isolated.
State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning
The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way.
GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild
Most in-the-wild images are stored in Low Dynamic Range (LDR) form, serving as a partial observation of the High Dynamic Range (HDR) visual world.
The path integral formula for the stochastic evolutionary game dynamics in the Moran process
In this work, we introduce the formulation of the path integral approach for evolutionary game theory based on the Moran process.
Study of detecting behavioral signatures within DeepFake videos
Our results indicate that there could be a behavioral signature that is detectable from a person's movements that is separate from their visual appearance, and that this behavioral signature could be used to distinguish a deep fake from a properly captured video.
Towards Complex Document Understanding By Discrete Reasoning
Document Visual Question Answering (VQA) aims to understand visually-rich documents to answer questions in natural language, which is an emerging research topic for both Natural Language Processing and Computer Vision.
Shrinking the Semantic Gap: Spatial Pooling of Local Moment Invariants for Copy-Move Forgery Detection
In this paper, we present a very first study of trying to mitigate the semantic gap problem in copy-move forgery detection, with spatial pooling of local moment invariants for midlevel image representation.
A multivariate semi-parametric portfolio risk optimization and forecasting framework
We develop a novel multivariate semi-parametric modelling approach to portfolio Value-at-Risk (VaR) and Expected Shortfall (ES) forecasting.
FL-Tuning: Layer Tuning for Feed-Forward Network in Transformer
Specifically, we focus on layer tuning for feed-forward network in the Transformer, namely FL-tuning.
Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework
We conclude that this improvement in ASC performance comes from the regularization effect of using AET and not from the network's improved ability to discern between acoustic events.
RDU: A Region-based Approach to Form-style Document Understanding
Key Information Extraction (KIE) is aimed at extracting structured information (e. g. key-value pairs) from form-style documents (e. g. invoices), which makes an important step towards intelligent document understanding.
Attacking and Defending Deep Reinforcement Learning Policies
Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems.
Rethinking Reinforcement Learning based Logic Synthesis
Recently, reinforcement learning has been used to address logic synthesis by formulating the operator sequence optimization problem as a Markov decision process.
Using Augmented Face Images to Improve Facial Recognition Tasks
We present a framework that uses GAN-augmented images to complement certain specific attributes, usually underrepresented, for machine learning model training.
A Multi-Transformation Evolutionary Framework for Influence Maximization in Social Networks
Influence maximization is a crucial issue for mining the deep information of social networks, which aims to select a seed set from the network to maximize the number of influenced nodes.
Federated Self-Supervised Learning for Acoustic Event Classification
Standard acoustic event classification (AEC) solutions require large-scale collection of data from client devices for model optimization.
A Principled Design of Image Representation: Towards Forensic Tasks
Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society.
Rule Mining over Knowledge Graphs via Reinforcement Learning
Knowledge graphs (KGs) are an important source repository for a wide range of applications and rule mining from KGs recently attracts wide research interest in the KG-related research community.
A multi-domain VNE algorithm based on multi-objective optimization for IoD architecture in Industry 4.0
Network virtualization technology is a promising technology to support IoD, so the allocation of virtual resources becomes a crucial issue in IoD.
Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoT
Therefore, we propose a FL algorithm assisted by DRL, which can take into account the privacy and efficiency of data training of IIoT equipment.
Multi Objective Resource Optimization of Wireless Network Based on Cross Domain Virtual Network Embedding
Resource allocation in virtual network is essentially a problem of allocating underlying resources for virtual network requests (VNRs).
Dynamic Virtual Network Embedding Algorithm based on Graph Convolution Neural Network and Reinforcement Learning
Simulation experiments verified that the dynamic VNE algorithm based on RL and GCNN has good basic VNE characteristics.
Network Resource Allocation Strategy Based on Deep Reinforcement Learning
This paper proposes a two-stage VNE algorithm based on deep reinforcement learning (DRL) (TS-DRL-VNE) for the problem that the mapping result of existing heuristic algorithm is easy to converge to the local optimal solution.
IoV Scenario: Implementation of a Bandwidth Aware Algorithm in Wireless Network Communication Mode
This paper proposes a bandwidth aware multi domain virtual network embedding algorithm (BA-VNE).
Resource Management and Security Scheme of ICPSs and IoT Based on VNE Algorithm
Based on the above two problems faced by ICPSs, we propose a virtual network embedded (VNE) algorithm with computing, storage resources and security constraints to ensure the rationality and security of resource allocation in ICPSs.
Space-Air-Ground Integrated Multi-domain Network Resource Orchestration based on Virtual Network Architecture: a DRL Method
Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN's heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm.
Security-Aware Virtual Network Embedding Algorithm based on Reinforcement Learning
In addition, as the use of intelligent learning algorithm to solve the problem of VNE has become a trend, this method is gradually outdated.
LinSyn: Synthesizing Tight Linear Bounds for Arbitrary Neural Network Activation Functions
The most scalable approaches to certifying neural network robustness depend on computing sound linear lower and upper bounds for the network's activation functions.
Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition
We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
MOORe: Model-based Offline-to-Online Reinforcement Learning
With the success of offline reinforcement learning (RL), offline trained RL policies have the potential to be further improved when deployed online.
Opinion Dynamics in Financial Markets via Random Networks
We investigate the financial market dynamics by introducing a heterogeneous agent-based opinion formation model.
Network Collaborator: Knowledge Transfer Between Network Reconstruction and Community Detection
Community detection (CD) from dynamics and network reconstruction (NR) from dynamics are natural synergistic tasks that motivate the proposed evolutionary multitasking NR and CD framework, called network collaborator (NC).
Evolutionary Multitasking AUC Optimization
Inspired by the characteristic of pairwise learning, the cheap AUC optimization task with a small-scale dataset sampled from the large-scale dataset is constructed to promote the AUC accuracy of the original, large-scale, and expensive AUC optimization task.
DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training
Moreover, our case study shows that our visual solution can well reflect the characteristics of various training scenarios, showing good potential of DVI as a debugging tool for analyzing deep learning training processes.
Community detection and portfolio optimization
Community detection methods can be used to explore the structure of complex systems.
Topic Modeling Revisited: A Document Graph-based Neural Network Perspective
To this end, in this paper, we revisit the task of topic modeling by transforming each document into a directed graph with word dependency as edges between word nodes, and develop a novel approach, namely Graph Neural Topic Model (GNTM).
Portfolio optimization with idiosyncratic and systemic risks for financial networks
The two risks are measured by the idiosyncratic variance and the network clustering coefficient derived from the asset correlation networks, respectively.
SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition
The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \emph{ObtainDiamond} task with sparse rewards.
Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness
As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference.
Learning a self-supervised tone mapping operator via feature contrast masking loss
High Dynamic Range (HDR) content is becoming ubiquitous due to the rapid development of capture technologies.
Performance, Successes and Limitations of Deep Learning Semantic Segmentation of Multiple Defects in Transmission Electron Micrographs
In this work, we perform semantic segmentation of multiple defect types in electron microscopy images of irradiated FeCrAl alloys using a deep learning Mask Regional Convolutional Neural Network (Mask R-CNN) model.
Towards High-fidelity Singing Voice Conversion with Acoustic Reference and Contrastive Predictive Coding
Experiments show that, compared with the baseline models, our proposed model can significantly improve the naturalness of converted singing voices and the similarity with the target singer.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Deep Learning-Based Detection of the Acute Respiratory Distress Syndrome: What Are the Models Learning?
The acute respiratory distress syndrome (ARDS) is a severe form of hypoxemic respiratory failure with in-hospital mortality of 35-46%.
Self-Adaptive Partial Domain Adaptation
Partial Domain adaptation (PDA) aims to solve a more practical cross-domain learning problem that assumes target label space is a subset of source label space.
Towards robust and domain agnostic reinforcement learning competitions
Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field.
A Bayesian realized threshold measurement GARCH framework for financial tail risk forecasting
This paper proposes an innovative threshold measurement equation to be employed in a Realized-GARCH framework.
An Emotional Comfort Framework for Improving User Satisfaction in E-Commerce Customer Service Chatbots
E-commerce has grown substantially over the last several years, and chatbots for intelligent customer service are concurrently drawing attention.
Explainability via Interactivity? Supporting Nonexperts' Sensemaking of Pretrained CNN by Interacting with Their Daily Surroundings
Current research on Explainable AI (XAI) heavily targets on expert users (data scientists or AI developers).
TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance
In this work, we extract samples from real financial reports to build a new large-scale QA dataset containing both Tabular And Textual data, named TAT-QA, where numerical reasoning is usually required to infer the answer, such as addition, subtraction, multiplication, division, counting, comparison/sorting, and the compositions.
Ranked #1 on
Question Answering
on TAT-QA
Convolutions for Spatial Interaction Modeling
In many different fields interactions between objects play a critical role in determining their behavior.
Modelling uncertainty in financial tail risk: a forecast combination and weighted quantile approach
A novel forecast combination and weighted quantile based tail-risk forecasting framework is proposed, aiming to reduce the impact of modelling uncertainty in tail-risk forecasting.
A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
Image representation is an important topic in computer vision and pattern recognition.
An Emotion-controlled Dialog Response Generation Model with Dynamic Vocabulary
In response generation task, proper sentimental expressions can obviously improve the human-like level of the responses.
High $J_{\rm c}$ and low anisotropy of hydrogen doped NdFeAsO superconducting thin film
The anisotropic Ginzburg-Landau scaling for the angle dependence of $J_{\rm c}$ yielded temperature-dependent scaling parameters $\gamma_{\rm J}$ that decreased from 1. 6 at 30 K to 1. 3 at 5 K. This is opposite to the behaviour of NdFeAs(O, F).
Superconductivity
Contrastive Unsupervised Learning for Speech Emotion Recognition
Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication.
Ranked #2 on
Speech Emotion Recognition
on MSP-Podcast (Dominance)
(using extra training data)
Drug Package Recommendation via Interaction-aware Graph Induction
Then, the drug interaction graph will be initialized based on medical records and domain knowledge.
Multi-Task Self-Supervised Pre-Training for Music Classification
Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
The impact of $a_0^0(980)-f_0(980)$ mixing on the localized $CP$ violations of the $B^-\rightarrow K^- π^+π^-$ decay
In the framework of the QCD factorization approach, we study the localized $CP$ violations of the $B^-\rightarrow K^- \pi^+\pi^-$ decay with and without $a_0^0(980)-f_0(980)$ mixing mechanism, respectively, and find that the localized $CP$ violation can be enhanced by this mixing effect when the mass of the $\pi^+\pi^-$ pair is in the vicinity of the $f_0(980)$ resonance.
High Energy Physics - Phenomenology
Minimizing L1 over L2 norms on the gradient
Consequently, we postulate that applying L1/L2 on the gradient is better than the classic total variation (the L1 norm on the gradient) to enforce the sparsity of the image gradient.
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents.
Machine Reading Comprehension
Open-Domain Question Answering
Intragroup sparsity for efficient inference
This work studies intragroup sparsity, a fine-grained structural constraint on network weight parameters.
Active Learning for Lane Detection: A Knowledge Distillation Approach
The experiments show that our method achieves new state-of-the-art on the lane detection benchmarks.
Realization of epitaxial thin films of the superconductor K-doped BaFe$_\text{2}$As$_\text{2}$
The iron-based superconductor Ba$_{1-x}$K$_x$Fe$_\text{2}$As$_\text{2}$ is emerging as a key material for high magnetic field applications owing to the recent developments in superconducting wires and bulk permanent magnets.
Superconductivity
A comprehensive study on the semileptonic decay of heavy flavor mesons
The semileptonic decay of heavy flavor mesons offers a clean environment for extraction of the Cabibbo-Kobayashi-Maskawa (CKM) matrix elements, which describes the CP-violating and flavor changing process in the Standard Model.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling
Joint intent detection and slot filling has recently achieved tremendous success in advancing the performance of utterance understanding.
Association: Remind Your GAN not to Forget
Neural networks are susceptible to catastrophic forgetting.
Temporally-Continuous Probabilistic Prediction using Polynomial Trajectory Parameterization
To address this issue we propose a simple and general representation for temporally continuous probabilistic trajectory prediction that is based on polynomial trajectory parameterization.
NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximation
Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks.
Tail risk forecasting using Bayesian realized EGARCH models
Rigorous tail risk forecast evaluations show that the realized EGARCH models employing the standardized skewed Student-t distribution and incorporating sub-sampled realized range are favored, compared to a range of models.
Deep Learning Based Equalizer for MIMO-OFDM Systems with Insufficient Cyclic Prefix
In this paper, we study the equalization design for multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) systems with insufficient cyclic prefix (CP).
DiffRNN: Differential Verification of Recurrent Neural Networks
As the memory footprint and energy consumption of such components become a bottleneck, there is interest in compressing and optimizing such networks using a range of heuristic techniques.
Limited-angle CT reconstruction via the L1/L2 minimization
In this paper, we consider minimizing the L1/L2 term on the gradient for a limited-angle scanning problem in computed tomography (CT) reconstruction.
Bootstrapping Named Entity Recognition in E-Commerce with Positive Unlabeled Learning
Named Entity Recognition (NER) in domains like e-commerce is an understudied problem due to the lack of annotated datasets.
An Artificial-intelligence/Statistics Solution to Quantify Material Distortion for Thermal Compensation in Additive Manufacturing
In this paper, we introduce a probabilistic statistics solution or artificial intelligence (AI) approach to identify and quantify permanent (non-zero strain) continuum/material deformation only based on the scanned material data in the spatial configuration and the shape of the initial design configuration or the material configuration.
Nonparametric Expected Shortfall Forecasting Incorporating Weighted Quantiles
The proposed models are applied to 7 stock market indices and their forecasting performances are compared to those of a range of parametric, non-parametric and semi-parametric models, including GARCH, Conditional AutoRegressive Expectile (CARE), joint VaR and ES quantile regression models and simple average of quantiles.
LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network
However, to date, there have been two major drawbacks: (1) the high-precision real-valued sensing patterns proposed in the majority of existing works can prove problematic when used with computational imaging hardware such as a digital micromirror sampling device and (2) the network structures for image reconstruction involve intensive computation, which is also not suitable for hardware deployment.
Improving Recommendation Diversity by Highlighting the ExTrA Fabricated Experts
Nowadays, recommender systems (RSes) are becoming increasingly important to individual users and business marketing, especially in the online e-commerce scenarios.
TCNN: Triple Convolutional Neural Network Models for Retrieval-based Question Answering System in E-commerce
Automatic question-answering (QA) systems have boomed during last few years, and commonly used techniques can be roughly categorized into Information Retrieval (IR)-based and generation-based.
MLR: A Two-stage Conversational Query Rewriting Model with Multi-task Learning
In this paper, we propose the conversational query rewriting model - MLR, which is a Multi-task model on sequence Labeling and query Rewriting.
Suphx: Mastering Mahjong with Deep Reinforcement Learning
Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI.
Adversarial Multimodal Representation Learning for Click-Through Rate Prediction
Finally, we achieve the multimodal item representations by combining both modality-specific and modality-invariant representations.
Novelty-Prepared Few-Shot Classification
We disclose that a classically fully trained feature extractor can leave little embedding space for unseen classes, which keeps the model from well-fitting the new classes.
SetRank: A Setwise Bayesian Approach for Collaborative Ranking from Implicit Feedback
The recent development of online recommender systems has a focus on collaborative ranking from implicit feedback, such as user clicks and purchases.
Few-shot acoustic event detection via meta-learning
We study few-shot acoustic event detection (AED) in this paper.
Designing Interaction for Multi-agent Cooperative System in an Office Environment
Future intelligent system will involve very various types of artificial agents, such as mobile robots, smart home infrastructure or personal devices, which share data and collaborate with each other to execute certain tasks. Designing an efficient human-machine interface, which can support users to express needs to the system, supervise the collaboration progress of different entities and evaluate the result, will be challengeable.
Data Techniques For Online End-to-end Speech Recognition
Practitioners often need to build ASR systems for new use cases in a short amount of time, given limited in-domain data.
Semi-supervised ASR by End-to-end Self-training
While deep learning based end-to-end automatic speech recognition (ASR) systems have greatly simplified modeling pipelines, they suffer from the data sparsity issue.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Bayesian Long Short-Term Memory Model for Value at Risk and Expected Shortfall Joint Forecasting
Value-at-Risk (VaR) and Expected Shortfall (ES) are widely used in the financial sector to measure the market risk and manage the extreme market movement.
A Study of the Tasks and Models in Machine Reading Comprehension
To provide a survey on the existing tasks and models in Machine Reading Comprehension (MRC), this report reviews: 1) the dataset collection and performance evaluation of some representative simple-reasoning and complex-reasoning MRC tasks; 2) the architecture designs, attention mechanisms, and performance-boosting approaches for developing neural-network-based MRC models; 3) some recently proposed transfer learning approaches to incorporating text-style knowledge contained in external corpora into the neural networks of MRC models; 4) some recently proposed knowledge base encoding approaches to incorporating graph-style knowledge contained in external knowledge bases into the neural networks of MRC models.
NEW: A Generic Learning Model for Tie Strength Prediction in Networks
Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks.
ReluDiff: Differential Verification of Deep Neural Networks
Existing verification techniques such as Reluplex, ReluVal, and DeepPoly provide formal guarantees, but they are designed for analyzing a single network instead of the relationship between two networks.
Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network.
Vision-Based Lane-Changing Behavior Detection Using Deep Residual Neural Network
Accurate lane localization and lane change detection are crucial in advanced driver assistance systems and autonomous driving systems for safer and more efficient trajectory planning.
Data-Driven Multi-step Demand Prediction for Ride-hailing Services Using Convolutional Neural Network
In this study, a convolutional neural network (CNN)-based deep learning model is proposed for multi-step ride-hailing demand prediction using the trip request data in Chengdu, China, offered by DiDi Chuxing.
Cross-Channel Intragroup Sparsity Neural Network
Modern deep neural networks rely on overparameterization to achieve state-of-the-art generalization.
PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain
For general supervised deep learning classification algorithms, the pixel-by-pixel algorithm achieves precise yet inefficient classification with a small number of labeled pixels, whereas the pixel mapping algorithm achieves efficient yet edge-rough classification with more prior labels required.
Acoustic scene analysis with multi-head attention networks
Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns.
Improving Back-Translation with Uncertainty-based Confidence Estimation
While back-translation is simple and effective in exploiting abundant monolingual corpora to improve low-resource neural machine translation (NMT), the synthetic bilingual corpora generated by NMT models trained on limited authentic bilingual data are inevitably noisy.
Compression of Acoustic Event Detection Models With Quantized Distillation
Acoustic Event Detection (AED), aiming at detecting categories of events based on audio signals, has found application in many intelligent systems.
Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
In this paper, we propose a generalizable and transferable Multilevel Graph Convolutional neural Network (MGCN) for molecular property prediction.
Ranked #6 on
Graph Regression
on Lipophilicity
Multimodal and Multi-view Models for Emotion Recognition
Studies on emotion recognition (ER) show that combining lexical and acoustic information results in more robust and accurate models.
Joint 3D Localization and Classification of Space Debris using a Multispectral Rotating Point Spread Function
We consider the problem of joint three-dimensional (3D) localization and material classification of unresolved space debris using a multispectral rotating point spread function (RPSF).
Plane-Based Optimization of Geometry and Texture for RGB-D Reconstruction of Indoor Scenes
We present a novel approach to reconstruct RGB-D indoor scene with plane primitives.
Efficient Plane-Based Optimization of Geometry and Texture for Indoor RGB-D Reconstruction
We propose a novel approach to reconstruct RGB-D indoor scene based on plane primitives.
Compression of Acoustic Event Detection Models with Low-rank Matrix Factorization and Quantization Training
In this paper, we present a compression approach based on the combination of low-rank matrix factorization and quantization training, to reduce complexity for neural network based acoustic event detection (AED) models.
Semi-supervised Acoustic Event Detection based on tri-training
This paper presents our work of training acoustic event detection (AED) models using unlabeled dataset.
Versatile security analysis of measurement-device-independent quantum key distribution
Interestingly, we also find that phase-matching QKD using only two coherent test states is enough to overcome the fundamental rate-distance limit of QKD.
Quantum Physics
A Survey of FPGA Based Deep Learning Accelerators: Challenges and Opportunities
With the rapid development of in-depth learning, neural network and deep learning algorithms have been widely used in various fields, e. g., image, video and voice processing.
A Scale Invariant Approach for Sparse Signal Recovery
In this paper, we study the ratio of the $L_1 $ and $L_2 $ norms, denoted as $L_1/L_2$, to promote sparsity.
Novel Sparse Recovery Algorithms for 3D Debris Localization using Rotating Point Spread Function Imagery
An optical imager that exploits off-center image rotation to encode both the lateral and depth coordinates of point sources in a single snapshot can perform 3D localization and tracking of space debris.
Explicit Utilization of General Knowledge in Machine Reading Comprehension
To bridge the gap between Machine Reading Comprehension (MRC) models and human beings, which is mainly reflected in the hunger for data and the robustness to noise, in this paper, we explore how to integrate the neural networks of MRC models with the general knowledge of human beings.
Ranked #23 on
Question Answering
on SQuAD1.1 dev
The Lower The Simpler: Simplifying Hierarchical Recurrent Models
To improve the training efficiency of hierarchical recurrent models without compromising their performance, we propose a strategy named as `the lower the simpler', which is to simplify the baseline models by making the lower layers simpler than the upper layers.
Coded Illumination and Imaging for Fluorescence Based Classification
The quick detection of specific substances in objects such as produce items via non-destructive visual cues is vital to ensuring the quality and safety of consumer products.
A Semi-parametric Realized Joint Value-at-Risk and Expected Shortfall Regression Framework
One-day-ahead VaR and ES forecasting results favor the proposed models, especially when incorporating the sub-sampled Realized Variance and the sub-sampled Realized Range in the model.
Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
Semantic layouts based Image synthesizing, which has benefited from the success of Generative Adversarial Network (GAN), has drawn much attention in these days.
Pipeline Generative Adversarial Networks for Facial Images Generation with Multiple Attributes
Generative Adversarial Networks are proved to be efficient on various kinds of image generation tasks.
Discriminative Region Proposal Adversarial Networks for High-Quality Image-to-Image Translation
Image-to-image translation has been made much progress with embracing Generative Adversarial Networks (GANs).
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
After the ResNet was trained, it was applied to reconstruct the T2 mapping from simulation and in vivo human brain data.
Close Yet Distinctive Domain Adaptation
Most previous research tackle this problem in seeking a shared feature representation between source and target domains while reducing the mismatch of their data distributions.
Quasi-homography warps in image stitching
The naturalness of warps is gaining extensive attentions in image stitching.
Perception-based energy functions in seam-cutting
In this paper, we propose a novel perception-based energy function in the seam-cutting framework, which considers the nonlinearity and the nonuniformity of human perception in energy minimization.
CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis
To improve the performance and maintain the scalability, we present CNNLab, a novel deep learning framework using GPU and FPGA-based accelerators.
DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems.
A novel and automatic pectoral muscle identification algorithm for mediolateral oblique (MLO) view mammograms using ImageJ
Pectoral muscle identification is often required for breast cancer risk analysis, such as estimating breast density.
Compositional Model based Fisher Vector Coding for Image Classification
To handle this limitation, in this paper we break the convention which assumes that a local feature is drawn from one of few Gaussian distributions.
Multi-Agent Continuous Transportation with Online Balanced Partitioning
A continuous transportation task is one in which a multi-agent team visits a number of fixed locations, picks up objects, and delivers them to a final destination.
Encoding High Dimensional Local Features by Sparse Coding Based Fisher Vectors
By calculating the gradient vector of the proposed model, we derive a new fisher vector encoding strategy, termed Sparse Coding based Fisher Vector Coding (SCFVC).
