Search Results for author:
Found 60 papers, 11 papers with code
MTL-SLT: Multi-Task Learning for Spoken Language Tasks
The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Event-Centric Query Expansion in Web Search
In search engines, query expansion (QE) is a crucial technique to improve search experience.
CVGG-Net: Ship Recognition for SAR Images Based on Complex-Valued Convolutional Neural Network
Although convolutional neural networks have been successfully employed for SAR image target recognition, surpassing traditional algorithms, most existing research concentrates on the amplitude domain and neglects the essential phase information.
SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence
The key of our approach is to exploit an orientation estimation module with a domain adaptive discriminator to align the orientations of point cloud pairs, which significantly alleviates the mispredictions of symmetrical parts.
Ranked #1 on
3D Dense Shape Correspondence
on SHREC'19
(using extra training data)
SPHR-SAR-Net: Superpixel High-resolution SAR Imaging Network Based on Nonlocal Total Variation
High-resolution is a key trend in the development of synthetic aperture radar (SAR), which enables the capture of fine details and accurate representation of backscattering properties.
Efficient Gridless DoA Estimation Method of Non-uniform Linear Arrays with Applications in Automotive Radars
This paper focuses on the gridless direction-of-arrival (DoA) estimation for data acquired by non-uniform linear arrays (NLAs) in automotive applications.
Coincident Learning for Unsupervised Anomaly Detection
Anomaly detection is an important task for complex systems (e. g., industrial facilities, manufacturing, large-scale science experiments), where failures in a sub-system can lead to low yield, faulty products, or even damage to components.
Deep Attention-Based Alignment Network for Melody Generation from Incomplete Lyrics
We propose a deep attention-based alignment network, which aims to automatically predict lyrics and melody with given incomplete lyrics as input in a way similar to the music creation of humans.
D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
Second, the HKDL module can generate keypoint detectors in a hierarchical way, which is helpful for detecting keypoints with diverse levels of structures.
GeoMVSNet: Learning Multi-View Stereo With Geometry Perception
To intensify the full-scene geometry perception of our model, we present the depth distribution similarity loss based on the Gaussian-Mixture Model assumption.
Ranked #1 on
Point Clouds
on Tanks and Temples
A novel TomoSAR imaging method with few observations based on nested array
In this paper, we propose a nested TomoSAR technique, which introduces the nested array into TomoSAR as the baseline configuration.
ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold
In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise.
Fault Diagnosis for Power Electronics Converters based on Deep Feedforward Network and Wavelet Compression
Secondly, the wavelet transform is used to remove the redundant data of the features, and then the training sample data is greatly compressed.
Review for AI-based Open-Circuit Faults Diagnosis Methods in Power Electronics Converters
Power electronics converters have been widely used in aerospace system, DC transmission, distributed energy, smart grid and so forth, and the reliability of power electronics converters has been a hotspot in academia and industry.
M$^2$DQN: A Robust Method for Accelerating Deep Q-learning Network
Deep Q-learning Network (DQN) is a successful way which combines reinforcement learning with deep neural networks and leads to a widespread application of reinforcement learning.
Stochastic Compositional Optimization with Compositional Constraints
Stochastic compositional optimization (SCO) has attracted considerable attention because of its broad applicability to important real-world problems.
Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness
First, we provide a structured view of the relationship between clinical presence mechanisms and group-specific missingness patterns.
Interpretable Melody Generation from Lyrics with Discrete-Valued Adversarial Training
Generating melody from lyrics is an interesting yet challenging task in the area of artificial intelligence and music.
Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition
However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information.
PERT: A New Solution to Pinyin to Character Conversion Task
Pinyin to Character conversion (P2C) task is the key task of Input Method Engine (IME) in commercial input software for Asian languages, such as Chinese, Japanese, Thai language and so on.
TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network
Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations.
Gridless Tomographic SAR Imaging Based on Accelerated Atomic Norm Minimization with Efficiency
The resolving along the elevation direction can be treated as a line spectrum estimation problem.
Robust Action Gap Increasing with Clipped Advantage Learning
Advantage Learning (AL) seeks to increase the action gap between the optimal action and its competitors, so as to improve the robustness to estimation errors.
Smoothing Advantage Learning
Advantage learning (AL) aims to improve the robustness of value-based reinforcement learning against estimation errors with action-gap-based regularization.
A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with Applications in Tomographic SAR Imaging
Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e. g., CS and ANM, in terms of estimation performances.
Optimal Methods for Convex Risk Averse Distributed Optimization
Specifically, the DRAO method achieves the optimal communication complexity by assuming a certain saddle point subproblem can be easily solved in the server node.
Robust Semi-supervised Federated Learning for Images Automatic Recognition in Internet of Drones
This emerging technology relies on sharing ground truth labeled data between Unmanned Aerial Vehicle (UAV) swarms to train a high-quality automatic image recognition model.
Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition
To address this issue, we propose an end-to-end Motion-modulated Temporal Fragment Alignment Network (MTFAN) by jointly exploring the task-specific motion modulation and the multi-level temporal fragment alignment for Few-Shot Action Recognition (FSAR).
Finite Sample Analysis of Average-Reward TD Learning and $Q$-Learning
The focus of this paper is on sample complexity guarantees of average-reward reinforcement learning algorithms, which are known to be more challenging to study than their discounted-reward counterparts.
Multi-View Stereo with Transformer
It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.
Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design
In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL.
The First Airborne Experiment of Sparse Microwave Imaging: Prototype System Design and Result Analysis
In this paper we report the first airborne experiments of sparse microwave imaging, conducted in September 2013 and May 2014, using our prototype sparse microwave imaging radar system.
Feasibility study of urban flood mapping using traffic signs for route optimization
Water events are the most frequent and costliest climate disasters around the world.
On joint training with interfaces for spoken language understanding
Spoken language understanding (SLU) systems extract both text transcripts and semantics associated with intents and slots from input speech utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing
For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies.
BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices
At the hardware design level, we propose a pipelined CirCore architecture, which supports efficient block-circulant matrices computation.
High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees
In this paper, we develop a general framework to design differentially private expectation-maximization (EM) algorithms in high-dimensional latent variable models, based on the noisy iterative hard-thresholding.
Inheritance-guided Hierarchical Assignment for Clinical Automatic Diagnosis
Clinical diagnosis, which aims to assign diagnosis codes for a patient based on the clinical note, plays an essential role in clinical decision-making.
MöbiusE: Knowledge Graph Embedding on Möbius Ring
In this work, we propose a novel Knowledge Graph Embedding (KGE) strategy, called M\"{o}biusE, in which the entities and relations are embedded to the surface of a M\"{o}bius ring.
Stabilizing Q Learning Via Soft Mellowmax Operator
Learning complicated value functions in high dimensional state space by function approximation is a challenging task, partially due to that the max-operator used in temporal difference updates can theoretically cause instability for most linear or non-linear approximation schemes.
Efficient Construction of Nonlinear Models over Normalized Data
For the case of NN, we propose algorithms to train the network taking normalized data as the input.
Optimal Algorithms for Convex Nested Stochastic Composite Optimization
All these complexity results seem to be new in the literature and they indicate that the convex NSCO problem has the same order of oracle complexity as those without the nested composition in all but the strongly convex and outer-non-smooth problem.
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
To make the task truly unconstrained, we present AdaFuse, an adaptive multiview fusion method, which can enhance the features in occluded views by leveraging those in visible views.
Ranked #1 on
3D Human Pose Estimation
on Total Capture
Deep Learning for Wireless Coded Caching with Unknown and Time-Variant Content Popularity
This approach, on one hand, can learn the caching policy in continuous action space by using the actor-critic architecture.
Octa: Omissions and Conflicts in Target-Aspect Sentiment Analysis
Sentiments in opinionated text are often determined by both aspects and target words (or targets).
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations.
Ranked #1 on
3D Absolute Human Pose Estimation
on Total Capture
3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image
In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks.
Simple and Lightweight Human Pose Estimation
Specifically, our LPN-50 can achieve 68. 7 in AP score on the COCO test-dev set, with only 2. 7M parameters and 1. 0 GFLOPs, while the inference speed is 17 FPS on an Intel i7-8700K CPU machine.
Leveraging Structural and Semantic Correspondence for Attribute-Oriented Aspect Sentiment Discovery
Opinionated text often involves attributes such as authorship and location that influence the sentiments expressed for different aspects.
Multi-objective multi-generation Gaussian process optimizer for design optimization
We present a multi-objective evolutionary optimization algorithm that uses Gaussian process (GP) regression-based models to select trial solutions in a multi-generation iterative procedure.
TonY: An Orchestrator for Distributed Machine Learning Jobs
Training machine learning (ML) models on large datasets requires considerable computing power.
Limbic: Author-Based Sentiment Aspect Modeling Regularized with Word Embeddings and Discourse Relations
We propose Limbic, an unsupervised probabilistic model that addresses the problem of discovering aspects and sentiments and associating them with authors of opinionated texts.
Trifo-VIO: Robust and Efficient Stereo Visual Inertial Odometry using Points and Lines
In this paper, we present the Trifo Visual Inertial Odometry (Trifo-VIO), a tightly-coupled filtering-based stereo VIO system using both points and lines.
PIRVS: An Advanced Visual-Inertial SLAM System with Flexible Sensor Fusion and Hardware Co-Design
In this paper, we present the PerceptIn Robotics Vision System (PIRVS) system, a visual-inertial computing hardware with embedded simultaneous localization and mapping (SLAM) algorithm.
Exploring compression techniques for ROOT IO
ROOT provides an flexible format used throughout the HEP community.
Distributed, Parallel, and Cluster Computing
Learn-Memorize-Recall-Reduce A Robotic Cloud Computing Paradigm
The rise of robotic applications has led to the generation of a huge volume of unstructured data, whereas the current cloud infrastructure was designed to process limited amounts of structured data.
Identifying Significant Predictive Bias in Classifiers
We present a novel subset scan method to detect if a probabilistic binary classifier has statistically significant bias -- over or under predicting the risk -- for some subgroup, and identify the characteristics of this subgroup.
Pyramid-based Visual Tracking Using Sparsity Represented Mean Transform
Firstly, we extend the original mean shift approach to handle orientation space and scale space and name this new method as mean transform.
