Search Results for author:
Found 42 papers, 2 papers with code
Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting
In this paper, we perform the first study of forecasting traffic flow adopting Online Learning (OL) manner in FL framework and then propose a novel prediction method named Online Spatio-Temporal Correlation-based Federated Learning (FedOSTC), aiming to guarantee performance gains regardless of traffic fluctuation.
Survey of Knowledge Distillation in Federated Edge Learning
The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine Learning (ML) models without sharing their private data.
A Personalized Utterance Style (PUS) based Dialogue Strategy for Efficient Service Requirement Elicitation
Considering that traditional dialogue system with static slots cannot be directly applied to the SRE task, it is a challenge to design an efficient dialogue strategy to guide users to express their complete and accurate requirements in such a huge potential requirement space.
FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
Federated Multi-task Learning (FMTL) is proposed to train related but personalized ML models for different devices, whereas previous works suffer from excessive communication overhead during training and neglect the model heterogeneity among devices in MEC.
THUEE system description for NIST 2020 SRE CTS challenge
This paper presents the system description of the THUEE team for the NIST 2020 Speaker Recognition Evaluation (SRE) conversational telephone speech (CTS) challenge.
The SpeakIn Speaker Verification System for Far-Field Speaker Verification Challenge 2022
In the pre-training stage we reserve the speaker weights, and there are no positive samples to train them in this stage.
The SpeakIn System Description for CNSRC2022
In the SV task fixed track, our system was a fusion of five models, and two models were fused in the SV task open track.
Imbalanced Node Processing Method in Graph Neural Network Classification Task
Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task.
Towards Federated Learning against Noisy Labels via Local Self-Regularization
Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner.
FastATDC: Fast Anomalous Trajectory Detection and Classification
Here, we present a careful theoretical and empirical analysis of the ATDC algorithm, showing that the calculation of anomaly scores in both stages can be simplified, and that the second stage of the algorithm is much more important than the first stage.
HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images
In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.
Causal Estimation of Position Bias in Recommender Systems Using Marketplace Instruments
By leveraging prior experimentation, we obtain quasi-experimental variation in item rankings that is orthogonal to user relevance.
Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation
Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from clients without assembling their private data.
Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction
To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object.
Bidding Agent Design in the LinkedIn Ad Marketplace
We establish a general optimization framework for the design of automated bidding agent in dynamic online marketplaces.
The MSXF TTS System for ICASSP 2022 ADD Challenge
The end to end TTS system is VITS, and the pre-training self-supervised model is wav2vec 2. 0.
Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension
In this paper, we consider recovering $n$ dimensional signals from $m$ binary measurements corrupted by noises and sign flips under the assumption that the target signals have low generative intrinsic dimension, i. e., the target signals can be approximately generated via an $L$-Lipschitz generator $G: \mathbb{R}^k\rightarrow\mathbb{R}^{n}, k\ll n$.
LSNN Method For Scalar Nonlinear HCLs: Discrete Divergence Operator
The least-squares neural network (LSNN) method was introduced for solving scalar linear and nonlinear hyperbolic conservation laws in [6, 5].
Poformer: A simple pooling transformer for speaker verification
Most recent speaker verification systems are based on extracting speaker embeddings using a deep neural network.
DeepGOMIMO: Deep Learning-Aided Generalized Optical MIMO with CSI-Free Blind Detection
Generalized optical multiple-input multiple-output (GOMIMO) techniques have been recently shown to be promising for high-speed optical wireless communication (OWC) systems.
RitzNet: A Deep Neural Network Method for Linear Stress Problems
This paper presents RitzNet, an unsupervised learning method which takes any point in the computation domain as input, and learns a neural network model to output its corresponding function value satisfying the underlying governing PDEs.
Coordinate Descent for MCP/SCAD Penalized Least Squares Converges Linearly
Recovering sparse signals from observed data is an important topic in signal/imaging processing, statistics and machine learning.
Self-adaptive deep neural network: Numerical approximation to functions and PDEs
Designing an optimal deep neural network for a given task is important and challenging in many machine learning applications.
Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency
The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID).
Deep Learning-Aided OFDM-Based Generalized Optical Quadrature Spatial Modulation
In this paper, we propose an orthogonal frequency division multiplexing (OFDM)-based generalized optical quadrature spatial modulation (GOQSM) technique for multiple-input multiple-output optical wireless communication (MIMO-OWC) systems.
Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.
Least-Squares ReLU Neural Network (LSNN) Method For Scalar Nonlinear Hyperbolic Conservation Law
We introduced the least-squares ReLU neural network (LSNN) method for solving the linear advection-reaction problem with discontinuous solution and showed that the method outperforms mesh-based numerical methods in terms of the number of degrees of freedom.
Least-Squares ReLU Neural Network (LSNN) Method For Linear Advection-Reaction Equation
This paper studies least-squares ReLU neural network method for solving the linear advection-reaction problem with discontinuous solution.
User Intention Recognition and Requirement Elicitation Method for Conversational AI Services
In recent years, chat-bot has become a new type of intelligent terminal to guide users to consume services.
Learning Person Re-identification Models from Videos with Weak Supervision
In order to cope with this issue, we introduce the problem of learning person re-identification models from videos with weak supervision.
Multiple Instance Learning
Video-Based Person Re-Identification
NOMA for Energy-Efficient LiFi-Enabled Bidirectional IoT Communication
In order to improve the energy efficiency (EE) of the bidirectional LiFi-IoT system, non-orthogonal multiple access (NOMA) with a quality-of-service (QoS)-guaranteed optimal power allocation (OPA) strategy is applied to maximize the EE of the system.
Deep Differentiable Grasp Planner for High-DOF Grippers
We present an end-to-end algorithm for training deep neural networks to grasp novel objects.
Robotics
Deep least-squares methods: an unsupervised learning-based numerical method for solving elliptic PDEs
This paper studies an unsupervised deep learning-based numerical approach for solving partial differential equations (PDEs).
Exploiting Global Camera Network Constraints for Unsupervised Video Person Re-identification
Additionally, a cross-view matching strategy followed by global camera network constraints is proposed to explore the matching relationships across the entire camera network.
DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis.
Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution
The ground-breaking performance obtained by deep convolutional neural networks (CNNs) for image processing tasks is inspiring research efforts attempting to extend it for 3D geometric tasks.
Generating Grasp Poses for a High-DOF Gripper Using Neural Networks
The quality of the grasp poses is on par with the groundtruth poses in the dataset.
Robotics
End-to-end Speech Recognition with Adaptive Computation Steps
In this paper, we present Adaptive Computation Steps (ACS) algo-rithm, which enables end-to-end speech recognition models to dy-namically decide how many frames should be processed to predict a linguistic output.
Ranked #8 on
Speech Recognition
on AISHELL-1
ABMOF: A Novel Optical Flow Algorithm for Dynamic Vision Sensors
The precise event timing, sparse output, and wide dynamic range of the events are well suited for optical flow, but conventional optical flow (OF) algorithms are not well matched to the event stream data.
Block-Matching Optical Flow for Dynamic Vision Sensor- Algorithm and FPGA Implementation
Rapid and low power computation of optical flow (OF) is potentially useful in robotics.
Recurrent 3D Attentional Networks for End-to-End Active Object Recognition
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed.
