Search Results for author:
Found 79 papers, 26 papers with code
Challenges to Open-Domain Constituency Parsing
Neural constituency parsers have reached practical performance on news-domain benchmarks.
HIFI-Net: A Novel Network for Enhancement to Underwater Images
As this network make "Haar Images into Fusion Images", it is called HIFI-Net.
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
We observe that MIM essentially teaches the model to learn better middle-level interactions among patches and extract more generalized features.
Denial-of-Service Attacks on Learned Image Compression
To characterize the robustness of state-of-the-art learned image compression, we mount white and black-box attacks.
Differentially Private AUC Computation in Vertical Federated Learning
In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.
Time Series Anomaly Detection via Reinforcement Learning-Based Model Selection
Time series anomaly detection is of critical importance for the reliable and efficient operation of real-world systems.
An Early Fault Detection Method of Rotating Machines Based on Multiple Feature Fusion with Stacking Architecture
One of the key points of EFD is developing a generic model to extract robust and discriminative features from different equipment for early fault detection.
Meta-Learning Based Early Fault Detection for Rolling Bearings via Few-Shot Anomaly Detection
To address this problem, many transfer learning based EFD methods utilize historical data to learn transferable domain knowledge and conduct early fault detection on new target bearings.
neuro2vec: Masked Fourier Spectrum Prediction for Neurophysiological Representation Learning
Extensive data labeling on neurophysiological signals is often prohibitively expensive or impractical, as it may require particular infrastructure or domain expertise.
Graph-incorporated Latent Factor Analysis for High-dimensional and Sparse Matrices
A High-dimensional and sparse (HiDS) matrix is frequently encountered in a big data-related application like an e-commerce system or a social network services system.
A Multi-Metric Latent Factor Model for Analyzing High-Dimensional and Sparse data
High-dimensional and sparse (HiDS) matrices are omnipresent in a variety of big data-related applications.
A Differential Evolution-Enhanced Latent Factor Analysis Model for High-dimensional and Sparse Data
High-dimensional and sparse (HiDS) matrices are frequently adopted to describe the complex relationships in various big data-related systems and applications.
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.
Predicting Peak Day and Peak Hour of Electricity Demand with Ensemble Machine Learning
In this study, we develop a supervised machine learning approach to generate 1) the probability of the next operation day containing the peak hour of the month and 2) the probability of an hour to be the peak hour of the day.
Object Localization under Single Coarse Point Supervision
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
Representation Learning for Resource-Constrained Keyphrase Generation
State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data.
Impression Allocation and Policy Search in Display Advertising
In order to address the unstable traffic pattern challenge and achieve the optimal overall outcome, we propose a multi-agent reinforcement learning method to adjust the bids from each guaranteed contract, which is simple, converging efficiently and scalable.
Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation
The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.
Learning to Simulate Unseen Physical Systems with Graph Neural Networks
Simulation of the dynamics of physical systems is essential to the development of both science and engineering.
Gap Minimization for Knowledge Sharing and Transfer
In this paper, we introduce the notion of \emph{performance gap}, an intuitive and novel measure of the distance between learning tasks.
Conditional Approximate Normalizing Flows for Joint Multi-Step Probabilistic Forecasting with Application to Electricity Demand
In this paper, we introduce the conditional approximate normalizing flow (CANF) to make probabilistic multi-step time-series forecasts when correlations are present over long time horizons.
P2P-Loc: Point to Point Tiny Person Localization
As a result, we propose a point self-refinement approach that iteratively updates point annotations in a self-paced way.
Constrained Adaptive Projection with Pretrained Features for Anomaly Detection
Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Mixup is a popular data-dependent augmentation technique for deep neural networks, which contains two sub-tasks, mixup generation and classification.
Ranked #5 on
Image Classification
on Tiny ImageNet Classification
ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control
Traffic signal control is of critical importance for the effective use of transportation infrastructures.
FedFly: Towards Migration in Edge-based Distributed Federated Learning
However, due to mobility, devices participating in FL may leave the network during training and need to connect to a different edge server.
GenURL: A General Framework for Unsupervised Representation Learning
Specifically, we provide a general method to model data structures by adaptively combining graph distances on the feature space and predefined graphs, then propose robust loss functions to learn the low-dimensional embedding.
C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.
Ranked #4 on
Speech Recognition
on WenetSpeech
Improving Discriminative Visual Representation Learning via Automatic Mixup
In this paper, we decompose mixup into two sub-tasks of mixup generation and classification and formulate it for discriminative representations as class- and instance-level mixup.
Benchmarking Sample Selection Strategies for Batch Reinforcement Learning
Through extensive experiments on the standard batch RL datasets, we find that non-uniform sampling is also effective in batch RL settings.
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Unfortunately, most online reinforcement learning algorithms require a large number of interactions with the environment to learn a reliable control policy.
Improving Neural Machine Translation by Bidirectional Training
We present a simple and effective pretraining strategy -- bidirectional training (BiT) for neural machine translation.
The USYD-JD Speech Translation System for IWSLT 2021
Our constrained system is based on a pipeline framework, i. e. ASR and NMT.
Time Series Anomaly Detection for Smart Grids: A Survey
With the rapid increase in the integration of renewable energy generation and the wide adoption of various electric appliances, power grids are now faced with more and more challenges.
FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
Further, FedAdapt adopts reinforcement learning based optimization and clustering to adaptively identify which layers of the DNN should be offloaded for each individual device on to a server to tackle the challenges of computational heterogeneity and changing network bandwidth.
Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy
In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized.
Align Yourself: Self-supervised Pre-training for Fine-grained Recognition via Saliency Alignment
In this paper, we first point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object.
Data-driven Model Predictive and Reinforcement Learning Based Control for Building Energy Management: a Survey
Building energy management is one of the core problems in modern power grids to reduce energy consumption while ensuring occupants' comfort.
U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
On the experiment of AISHELL-1, we achieve a 4. 63\% character error rate (CER) with a non-streaming setup and 5. 05\% with a streaming setup with 320ms latency by U2++.
Unsupervised Deep Manifold Attributed Graph Embedding
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.
Ranked #2 on
Node Clustering
on Wiki
Software-Defined Edge Computing: A New Architecture Paradigm to Support IoT Data Analysis
We further present an experiment on data anomaly detection in this architecture, and the comparison between two architectures for ECG diagnosis.
Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones.
Representation range needs for 16-bit neural network training
While neural networks have been trained using IEEE-754 binary32 arithmetic, the rapid growth of computational demands in deep learning has boosted interest in faster, low precision training.
Unveiling the Power of Mixup for Stronger Classifiers
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #6 on
Image Classification
on Tiny ImageNet Classification
Virtual Reality: A Survey of Enabling Technologies and its Applications in IoT
Virtual Reality (VR) has shown great potential to revolutionize the market by providing users immersive experiences with freedom of movement.
Networking and Internet Architecture
Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models
To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i. e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance.
Environment-Aware and Training-Free Beam Alignment for mmWave Massive MIMO via Channel Knowledge Map
Two instances of CKM are proposed for beam alignment in mmWave massive MIMO systems, namely channel path map (CPM) and beam index map (BIM).
MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
In this paper, we propose an open source, production first, and production ready speech recognition toolkit called WeNet in which a new two-pass approach is implemented to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times
Then, we theoretically derive: 1) the conditions for the DP based FedAvg to converge as the number of global iterations (GI) approaches infinity; 2) the method to set the number of local iterations (LI) to minimize the negative influence of DP noises.
Unsupervised Word Alignment via Cross-Lingual Contrastive Learning
Recently, the performance of the neural word alignment models has exceeded that of statistical models.
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model.
Ranked #3 on
Speech Recognition
on AISHELL-1
Context-Aware Cross-Attention for Non-Autoregressive Translation
Non-autoregressive translation (NAT) significantly accelerates the inference process by predicting the entire target sequence.
Network Anomaly Detection Using Federated Learning and Transfer Learning
In the second learning stage, Ot uses the transfer learning method to reconstruct and re-train the model to further improve the detection performance on the specific task.
From Distributed Machine Learning To Federated Learning: In The View Of Data Privacy And Security
Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server.
Distributed, Parallel, and Cluster Computing
End-to-End Learning for Simultaneously Generating Decision Map and Multi-Focus Image Fusion Result
In this work, to handle the requirements of both output image quality and comprehensive simplicity of structure implementation, we propose a cascade network to simultaneously generate decision map and fused result with an end-to-end training procedure.
SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling
Slot filling and intent detection are two main tasks in spoken language understanding (SLU) system.
When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Network
Ultra-dense edge computing (UDEC) has great potential, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: i) efficient utilization of multiple 5G resources (e. g., computation, communication, storage and service resources); ii) low overhead offloading decision making and resource allocation strategies; and iii) privacy and security protection schemes.
DeepC2: AI-powered Covert Botnet Command and Control on OSNs
Experiments on Twitter show that command-embedded contents can be generated efficiently, and bots can find botmasters and obtain commands accurately.
EasyQuant: Post-training Quantization via Scale Optimization
The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.
Energy Model for UAV Communications: Experimental Validation and Model Generalization
In this paper, via extensive flight experiments, we aim to firstly validate the recently derived theoretical energy model for rotary-wing UAVs, and then develop a general model for those complicated flight scenarios where rigorous theoretical model derivation is quite challenging, if not impossible.
Neural Mesh Refiner for 6-DoF Pose Estimation
We utilise the overlay between the accurate mask prediction and less accurate mesh prediction to iteratively optimise the direct regressed 6D pose information with a focus on translation estimation.
DeepBrain: Towards Personalized EEG Interaction through Attentional and Embedded LSTM Learning
The "mind-controlling" capability has always been in mankind's fantasy.
Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
DeepRelations shows superior interpretability to the state-of-the-art: without compromising affinity prediction, it boosts the AUPRC of contact prediction 9. 5, 16. 9, 19. 3 and 5. 7-fold for the test, compound-unique, protein-unique, and both-unique sets, respectively.
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.
6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario.
AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework
First, the wide collection of data in the close-loop information flow of user and remote medical data center is discussed.
Omni-directional Feature Learning for Person Re-identification
Most of them focus on learning the part feature representation of person body in horizontal direction.
WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition
In this work, we first use WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and then propose a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.
Random Occlusion-recovery for Person Re-identification
As a basic task of multi-camera surveillance system, person re-identification aims to re-identify a query pedestrian observed from non-overlapping multiple cameras or across different time with a single camera.
Robust and customized methods for real-time hand gesture recognition under object-occlusion
Dynamic hand tracking and gesture recognition is a hard task since there are many joints on the fingers and each joint owns many degrees of freedom.
Human-Computer Interaction
A Multi-Agent Reinforcement Learning Method for Impression Allocation in Online Display Advertising
With this formulation, we derive the optimal impression allocation strategy by solving the optimal bidding functions for contracts.
DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
Motivation: Drug discovery demands rapid quantification of compound-protein interaction (CPI).
Budget Constrained Bidding by Model-free Reinforcement Learning in Display Advertising
Our analysis shows that the immediate reward from environment is misleading under a critical resource constraint.
Machine Learning for Building Energy and Indoor Environment: A Perspective
It is indicated that the theories and applications of machine learning method in the field of energy conservation and indoor environment are not mature, due to the difficulty of the determination for model structure with better prediction.
Kernalised Multi-resolution Convnet for Visual Tracking
Visual tracking is intrinsically a temporal problem.
Self-training semi-supervised classification based on density peaks of data
Having a multitude of unlabeled data and few labeled ones is a common problem in many practical ap- plications.
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition
Over the last few years, with the immense popularity of the Kinect, there has been renewed interest in developing methods for human gesture and action recognition from 3D skeletal data.
