Search Results for author:
Found 107 papers, 39 papers with code
Machine Translation With Weakly Paired Bilingual Documents
Neural machine translation, which achieves near human-level performance in some languages, strongly relies on the availability of large amounts of parallel sentences, which hinders its applicability to low-resource language pairs.
Streamlining Biomedical Research with Specialized LLMs
In this paper, we propose a novel system that integrates state-of-the-art, domain-specific large language models with advanced information retrieval techniques to deliver comprehensive and context-aware responses.
Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process
Terrain analysis is critical for the practical application of ground mobile robots in real-world tasks, especially in outdoor unstructured environments.
FLOAT Drone: A Fully-actuated Coaxial Aerial Robot for Close-Proximity Operations
How to endow aerial robots with the ability to operate in close proximity remains an open problem.
Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning
End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI.
neuro2voc: Decoding Vocalizations from Neural Activity
Accurate decoding of neural spike trains and relating them to motor output is a challenging task due to the inherent sparsity and length in neural spikes and the complexity of brain circuits.
Towards Aligned Data Forgetting via Twin Machine Unlearning
To achieve aligned data forgetting, we propose a Twin Machine Unlearning (TMU) approach, where a twin unlearning problem is defined corresponding to the original unlearning problem.
Are GNNs Actually Effective for Multimodal Fault Diagnosis in Microservice Systems?
Graph Neural Networks (GNNs) are widely adopted for fault diagnosis in microservice systems, premised on their ability to model service dependencies.
Enhanced MRI Representation via Cross-series Masking
In the training process, the cross-series representation is learned by utilizing the unmasked data to reconstruct the masked portions.
NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing
To address data heterogeneity issues, NebulaFL adopts a version control-based asynchronous FL training scheme in each data center to balance training time among data owners.
AI-Generated Image Quality Assessment Based on Task-Specific Prompt and Multi-Granularity Similarity
Recently, AI-generated images (AIGIs) created by given prompts (initial prompts) have garnered widespread attention.
Resolution Enhancement of Under-sampled Photoacoustic Microscopy Images using Implicit Neural Representations
Acoustic-Resolution Photoacoustic Microscopy (AR-PAM) is promising for subcutaneous vascular imaging, but its spatial resolution is constrained by the Point Spread Function (PSF).
Autoregressive Sequence Modeling for 3D Medical Image Representation
By employing an autoregressive sequence modeling task, we predict the next visual token in the sequence, which allows our model to deeply understand and integrate the contextual information inherent in 3D medical images.
Audio-Guided Fusion Techniques for Multimodal Emotion Analysis
In this paper, we propose a solution for the semi-supervised learning track (MER-SEMI) in MER2024.
Channel Modeling Framework for Both Communications and Bistatic Sensing Under 3GPP Standard
In this paper, the channel modeling framework for bistatic ISAC is considered.
Hardware Architecture Design of Model-Based Image Reconstruction Towards Palm-size Photoacoustic Tomography
We conducted experiments by FPGA implementation of the algorithm, using both phantoms and in vivo human finger data to verify the feasibility of the proposed method.
Logic Distillation: Learning from Code Function by Function for Planning and Decision-making
Subsequently, based on the function base, LD fine-tunes S-LLMs to learn the logic employed by L-LLMs in planning and decision-making.
Limited-View Photoacoustic Imaging Reconstruction Via High-quality Self-supervised Neural Representation
In this study, we introduce a self-supervised network termed HIgh-quality Self-supervised neural representation (HIS), which tackles the inverse problem of photoacoustic imaging to reconstruct high-quality photoacoustic images from sensor data acquired under limited viewpoints.
PharmaGPT: Domain-Specific Large Language Models for Bio-Pharmaceutical and Chemistry
Large language models (LLMs) have revolutionized Natural Language Processing (NLP) by minimizing the need for complex feature engineering.
Sparse-view Signal-domain Photoacoustic Tomography Reconstruction Method Based on Neural Representation
Photoacoustic tomography is a hybrid biomedical technology, which combines the advantages of acoustic and optical imaging.
Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation
This transformation enables seamless integration of 2D and 3D data, and facilitates cross-dimensional self-supervised learning for 3D medical image analysis.
Confidence-Based Task Prediction in Continual Disease Classification Using Probability Distribution
We present CTP, a task-id predictor that utilizes confidence scores, leveraging the probability distribution (logits) of the classifier to accurately determine the task-id at inference time.
Microsaccade-inspired Event Camera for Robotics
These event cameras' output is dependent on both motion and texture.
Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing
To equip the graph processing with both high accuracy and explainability, we introduce a novel approach that harnesses the power of a large language model (LLM), enhanced by an uncertainty-aware module to provide a confidence score on the generated answer.
A Hierarchical Fused Quantum Fuzzy Neural Network for Image Classification
In this paper, we proposed a novel hierarchical fused quantum fuzzy neural network (HQFNN).
Towards Dense and Accurate Radar Perception Via Efficient Cross-Modal Diffusion Model
Millimeter wave (mmWave) radars have attracted significant attention from both academia and industry due to their capability to operate in extreme weather conditions.
Learning Speed Adaptation for Flight in Clutter
Animals learn to adapt speed of their movements to their capabilities and the environment they observe.
Generating Handwritten Mathematical Expressions From Symbol Graphs: An End-to-End Pipeline
To alleviate this challenge we propose a novel end-to-end G2I generation pipeline (i. e. graph - layout - mask - image) which requires no real masks or nondifferentiable alignment between layouts and masks.
Human-Inspired Facial Sketch Synthesis with Dynamic Adaptation
Besides, different artists may use diverse drawing techniques and create multiple styles of sketches; but the style is globally consistent in a sketch.
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships.
Gradient-based adaptive wavelet de-noising method for photoacoustic imaging in vivo
The proposed de-noising method provides potential to improve the SNR of PA signal under single-shot low-power laser illumination for biomedical applications in vivo.
Machine-Learning-based Colorectal Tissue Classification via Acoustic Resolution Photoacoustic Microscopy
Colorectal cancer is a deadly disease that has become increasingly prevalent in recent years.
Bundle-specific Tractogram Distribution Estimation Using Higher-order Streamline Differential Equation
At the global level, the tractography process is simplified as the estimation of bundle-specific tractogram distribution (BTD) coefficients by minimizing the energy optimization model, and is used to characterize the relations between BTD and diffusion tensor vector under the prior guidance by introducing the tractogram bundle information to provide anatomic priors.
Score-based Generative Models for Photoacoustic Image Reconstruction with Rotation Consistency Constraints
Photoacoustic tomography (PAT) is a newly emerged imaging modality which enables both high optical contrast and acoustic depth of penetration.
LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments
The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV.
Semantic-aware Generation of Multi-view Portrait Drawings
Our motivation is that facial semantic labels are view-consistent and correlate with drawing techniques.
Masked and Adaptive Transformer for Exemplar Based Image Translation
To overcome this challenge, we improve the accuracy of matching on the one hand, and diminish the role of matching in image generation on the other hand.
Sensing with OFDM Waveform at mmWave Band based on Micro-Doppler Analysis
Joint communication and sensing (JCAS) technology has been regarded as one of the innovations in the 6G network.
Learning Combinatorial Prompts for Universal Controllable Image Captioning
To this end, we propose a novel prompt-based framework for CIC by learning Combinatorial Prompts, dubbed as ComPro.
An information-theoretic learning model based on importance sampling
A crucial assumption underlying the most current theory of machine learning is that the training distribution is identical to the test distribution.
Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when relying solely on image-level labels.
Adaptive De-noising of Photoacoustic Signal and Image based on Modified Kalman Filter
As a burgeoning medical imaging method based on hybrid fusion of light and ultrasound, photoacoustic imaging (PAI) has demonstrated high potential in various biomedical applications recently, especially in revealing the functional and molecular information to improve diagnostic accuracy.
LF-VISLAM: A SLAM Framework for Large Field-of-View Cameras with Negative Imaging Plane on Mobile Agents
As loop closure on wide-FoV panoramic data further comes with a large number of outliers, traditional outlier rejection methods are not directly applicable.
Mutual Adaptive Reasoning for Monocular 3D Multi-Person Pose Estimation
This method first uses 2. 5D pose and geometry information to infer camera-centric root depths in a forward pass, and then exploits the root depths to further improve representation learning of 2. 5D pose estimation in a backward pass.
Solution of integrals with fractional Brownian motion for different Hurst indices
In this paper, we will evaluate integrals that define the conditional expectation, variance and characteristic function of stochastic processes with respect to fractional Brownian motion (fBm) for all relevant Hurst indices, i. e. $H \in (0, 1)$.
LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative Plane
To tackle this issue, we propose LF-VIO, a real-time VIO framework for cameras with extremely large FoV.
Deep residual inception encoder-decoder network for amyloid PET harmonization
Multiple positron emission tomography (PET) tracers are available for amyloid imaging, posing a significant challenge to consensus interpretation and quantitative analysis.
ApolloRL: a Reinforcement Learning Platform for Autonomous Driving
We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving.
An effective coaxiality measurement for twist drill based on line structured light sensor
Aiming at the accurate and effective coaxiality measurement for twist drill with irregular surface, an optical measurement mechanism is proposed in this paper.
Benchmarking emergency department triage prediction models with machine learning and large public electronic health records
In this paper, based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we developed a publicly available benchmark suite for ED triage predictive models and created a benchmark dataset that contains over 400, 000 ED visits from 2011 to 2019.
Resistance-Time Co-Modulated PointNet for Temporal Super-Resolution Simulation of Blood Vessel Flows
In this paper, a novel deep learning framework is proposed for temporal super-resolution simulation of blood vessel flows, in which a high-temporal-resolution time-varying blood vessel flow simulation is generated from a low-temporal-resolution flow simulation result.
Deep Learning Adapted Acceleration for Limited-view Photoacoustic Computed Tomography
To adapt fast and high-quality reconstruction of limited-view PA data, in this paper, a model-based method that combines the mathematical variational model with deep learning is proposed to speed up and regularize the unrolled procedure of reconstruction.
Kernel Mean Estimation by Marginalized Corrupted Distributions
Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms.
TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
To simultaneously extract spatial and relational information from tables, we propose a novel neural network architecture, TabularNet.
Compressed Sensing for Photoacoustic Computed Tomography Using an Untrained Neural Network
Our method can cooperate with other existing regularization, and further improve the quality.
Photoacoustic-monitored laser treatment for tattoo removal: a feasibility study
Skin blemishes and diseases have attracted increasing research interest in recent decades, due to their growing frequency of occurrence and the severity of related diseases.
Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
Network Embedding aims to learn a function mapping the nodes to Euclidean space contribute to multiple learning analysis tasks on networks.
Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
In this paper, in order to solve the boundary discontinuity problem in OBB regression, we propose to detect SAR ships by learning polar encodings.
Visibility-aware Trajectory Optimization with Application to Aerial Tracking
The visibility of targets determines performance and even success rate of various applications, such as active slam, exploration, and target tracking.
Trajectory Planning
Robotics
Fast-Tracker 2.0: Improving Autonomy of Aerial Tracking with Active Vision and Human Location Regression
In recent years, several progressive works promote the development of aerial tracking.
Trajectory Planning
Robotics
FAST-Dynamic-Vision: Detection and Tracking Dynamic Objects with Event and Depth Sensing
The bottleneck of solving this problem is the accurate perception of rapid dynamic objects.
Motion Compensation
Robust Object Detection
+1
Robotics
Integrating Fast Regional Optimization into Sampling-based Kinodynamic Planning for Multirotor Flight
For real-time multirotor kinodynamic motion planning, the efficiency of sampling-based methods is usually hindered by difficult-to-sample homotopy classes like narrow passages.
Motion Planning
Robotics
Certification of three black boxes with unsharp measurements using $3 \rightarrow 1 $ sequential quantum random access codes
We derive optimal trade-off between the two correlation witnesses in $ 3 \rightarrow 1 $ sequential quantum random access codes (QRACs), and use the result to complete the self-testing of quantum preparations, instruments and measurements for three sequential parties.
Quantum Physics
Fully coupled functional equations for the quark sector of QCD
The components of the quark propagator obtained from our approach are in excellent agreement with the results from Schwinger-Dyson equations, the functional renormalisation group, and lattice QCD simulation, a simple benchmark observable being the chiral condensate in the chiral limit, which is computed as $(245\,\textrm{MeV})^3$.
High Energy Physics - Phenomenology High Energy Physics - Lattice High Energy Physics - Theory Nuclear Theory
Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform
Speech enhancement algorithms based on deep learning have been improved in terms of speech intelligibility and perceptual quality greatly.
Bridging Unpaired Facial Photos And Sketches By Line-drawings
In this paper, we propose a novel method to learn face sketch synthesis models by using unpaired data.
AS-Net: Fast Photoacoustic Reconstruction with Multi-feature Fusion from Sparse Data
In this paper, we firstly propose to employ a novel signal processing method to make sparse PA raw data more suitable for the neural network, concurrently speeding up image reconstruction.
Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification
Besides, empirical study shows that the reasoning process of learned networks is in conformity with physicians' diagnosis.
Ranked #1 on
Neural Architecture Search
on LIDC-IDRI
Superposed Wave (s-Wave): Accelerating Photoacoustic Simulation
However, it is still in a developing stage, and a lot of experiments have to be performed in a simulation setting.
Medical Physics
A Jointed Feature Fusion Framework for Photoacoustic Reconstruction
The cross-domain features from limited-view position-wise data and the reconstructed image are fused by a backtracked supervision.
Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
In autonomous navigation of mobile robots, sensors suffer from massive occlusion in cluttered environments, leaving significant amount of space unknown during planning.
EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotors
Gradient-based planners are widely used for quadrotor local planning, in which a Euclidean Signed Distance Field (ESDF) is crucial for evaluating gradient magnitude and direction.
Robotics
Deep Learning Enables Robust and Precise Light Focusing on Treatment Needs
If light passes through the body tissues, focusing only on areas where treatment needs, such as tumors, will revolutionize many biomedical imaging and therapy technologies.
Deep learning for photoacoustic imaging: a survey
In this review, we performed an overview of some new developments and challenges in the application of machine learning to medical image analysis, with a special focus on deep learning in photoacoustic imaging.
CMPCC: Corridor-based Model Predictive Contouring Control for Aggressive Drone Flight
In this paper, we propose an efficient, receding horizon, local adaptive low-level planner as the middle layer between our original planner and controller.
Robotics
RAPTOR: Robust and Perception-aware Trajectory Replanning for Quadrotor Fast Flight
In this paper, we present RAPTOR, a robust and perception-aware replanning framework to support fast and safe flight.
Robotics
Making Robots Draw A Vivid Portrait In Two Minutes
The whole portrait drawing robotic system is named AiSketcher.
PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting
When predicting PM2. 5 concentrations, it is necessary to consider complex information sources since the concentrations are influenced by various factors within a long period.
Deep Learning Enabled Real-Time Photoacoustic Tomography System via Single Data Acquisition Channel
In this work, we develop a novel PACT system to provide real-time imaging, which is achieved by a 120-elements ultrasound array only using a single data acquisition (DAQ) channel.
Robust Real-time UAV Replanning Using Guided Gradient-based Optimization and Topological Paths
A path-guided optimization (PGO) approach is devised to tackle infeasible local minima, which improves the replanning success rate significantly.
Robotics
Bayesian machine learning for Boltzmann machine in quantum-enhanced feature spaces
Specifically, the training phase provides a physical quantity to measure the posterior distribution in quantum feature spaces, and this measure is utilized to design the quantum maximum a posterior (QMAP) algorithm and the quantum predictive distribution estimator (QPDE).
Normalization Helps Training of Quantized LSTM
The long-short-term memory (LSTM), though powerful, is memory and computa\x02tion expensive.
Neural Machine Translation with Soft Prototype
Neural machine translation models usually use the encoder-decoder framework and generate translation from left to right (or right to left) without fully utilizing the target-side global information.
Microsoft Research Asia's Systems for WMT19
We Microsoft Research Asia made submissions to 11 language directions in the WMT19 news translation tasks.
Machine Translation With Weakly Paired Documents
1) We provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised training signals.
Link Prediction via Graph Attention Network
Link prediction aims to infer missing links or predicting the future ones based on currently observed partial networks, it is a fundamental problem in network science with tremendous real-world applications.
Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs
Many problems in real life can be converted to combinatorial optimization problems (COPs) on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints.
Real-time Scalable Dense Surfel Mapping
First, superpixels extracted from both intensity and depth images are used to model surfels in the system.
Y-Net: A Hybrid Deep Learning Reconstruction Framework for Photoacoustic Imaging in vivo
Photoacoustic imaging (PAI) is an emerging non-invasive imaging modality combining the advantages of deep ultrasound penetration and high optical contrast.
Depth Growing for Neural Machine Translation
While very deep neural networks have shown effectiveness for computer vision and text classification applications, how to increase the network depth of neural machine translation (NMT) models for better translation quality remains a challenging problem.
Ranked #11 on
Machine Translation
on WMT2014 English-French
Soft Contextual Data Augmentation for Neural Machine Translation
While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited.
Understanding Urban Dynamics via Context-aware Tensor Factorization with Neighboring Regularization
In this paper, we propose a Neighbor-Regularized and context-aware Non-negative Tensor Factorization model (NR-cNTF) to discover interpretable urban dynamics from urban heterogeneous data.
Flying through a narrow gap using neural network: an end-to-end planning and control approach
To this end, we propose an end-to-end policy network, which imitates from the traditional pipeline and is fine-tuned using reinforcement learning.
Robotics
FIESTA: Fast Incremental Euclidean Distance Fields for Online Motion Planning of Aerial Robots
We integrate FIESTA into a completed quadrotor system and validate it by both simulation and onboard experiments.
Robotics
Efficient Sequence Learning with Group Recurrent Networks
Recurrent neural networks have achieved state-of-the-art results in many artificial intelligence tasks, such as language modeling, neural machine translation, speech recognition and so on.
A Parameter Estimation of Fractional Order Grey Model Based on Adaptive Dynamic Cat Swarm Algorithm
The parameters of Fractional Order Grey Model affect the prediction accuracy of the model.
SD-CNN: a Shallow-Deep CNN for Improved Breast Cancer Diagnosis
To evaluate the validity of our approach, we first develop a deep-CNN using 49 CEDM cases collected from Mayo Clinic to prove the contributions from recombined images for improved breast cancer diagnosis (0. 86 in accuracy using LE imaging vs. 0. 90 in accuracy using both LE and recombined imaging).
Towards Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs
Experimental results show that our method is capable of generating both visually comfortable and identity-preserving face sketches/photos over a wide range of challenging data.
Ranked #1 on
Face Sketch Synthesis
on CUFS
(FID metric)
FingerNet: An Unified Deep Network for Fingerprint Minutiae Extraction
In this paper, we propose a new way to design deep convolutional network combining domain knowledge and the representation ability of deep learning.
Efficient Inexact Proximal Gradient Algorithm for Nonconvex Problems
The proximal gradient algorithm has been popularly used for convex optimization.
Optimization and Control
Latent fingerprint minutia extraction using fully convolutional network
The CNN shares convolutional layers with the fully convolutional network to speed up.
A Novel Paradigm for Calculating Ramsey Number via Artificial Bee Colony Algorithm
This paper proposed a novel methodology for constructing Ramsey graphs about R(3, 10), which uses Artificial Bee Colony optimization(ABC) to raise the lower bound of Ramsey number R(3, 10).
LightLDA: Big Topic Models on Modest Compute Clusters
When building large-scale machine learning (ML) programs, such as big topic models or deep neural nets, one usually assumes such tasks can only be attempted with industrial-sized clusters with thousands of nodes, which are out of reach for most practitioners or academic researchers.
Total-Variation Minimization on Unstructured Volumetric Mesh: Biophysical Applications on Reconstruction of 3D Ischemic Myocardium
This paper describes the development and application of a new approach to total-variation (TV) minimization for reconstruction problems on geometrically-complex and unstructured volumetric mesh.
Learning to Rank for Blind Image Quality Assessment
The proposed BIQA method is one of learning to rank.
