Search Results for author:
Found 70 papers, 26 papers with code
A Language Model-based Generative Classifier for Sentence-level Discourse Parsing
Discourse segmentation and sentence-level discourse parsing play important roles for various NLP tasks to consider textual coherence.
Generic Mechanism for Reducing Repetitions in Encoder-Decoder Models
Encoder-decoder models have been commonly used for many tasks such as machine translation and response generation.
Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving
In this work, we propose a systematic study on simple Copy-Paste data augmentation for rare object detection in autonomous driving.
Probabilistic Models for Manufacturing Lead Times
In this study, we utilize Gaussian processes, probabilistic neural network, natural gradient boosting, and quantile regression augmented gradient boosting to model lead times of laser manufacturing processes.
Mix-up Self-Supervised Learning for Contrast-agnostic Applications
Contrastive self-supervised learning has attracted significant research attention recently.
Influence of the Endothelial Surface Layer on the Wall-induced Migration of Red Blood Cells
The endothelial lining of blood vessels presents a large surface area for exchanging materials between blood and tissues.
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records
We developed GatorTron models from scratch using the BERT architecture of different sizes including 345 million, 3. 9 billion, and 8. 9 billion parameters, compared GatorTron with three existing transformer models in the clinical and biomedical domain on 5 different clinical NLP tasks including clinical concept extraction, relation extraction, semantic textual similarity, natural language inference, and medical question answering, to examine how large transformer models could help clinical NLP at different linguistic levels.
Reinforcement Learning Based Query Vertex Ordering Model for Subgraph Matching
In recent years, many advanced techniques for query vertex ordering (i. e., matching order generation) have been proposed to reduce the unpromising intermediate results according to the preset heuristic rules.
Detailed Balance for Particle Models of Reversible Reactions in Bounded Domains
In bounded domains with no-flux boundary conditions, when choosing unbinding kernels consistent with several commonly used binding kernels, we show that preserving detailed balance of spatial reaction-fluxes at all points requires spatially varying unbinding rate functions near the domain boundary.
Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor
Segmentation and labeling of liver tumors and blood vessels in CT images can provide convenience for doctors in liver tumor diagnosis and surgical intervention.
Building an AI-ready RSE Workforce
Artificial Intelligence has been transforming industries and academic research across the globe, and research software development is no exception.
Decentralized Coordinated State Estimation in Integrated Transmission and Distribution Systems
Current transmission and distribution system states are mostly unobservable to each other, and state estimation is separately conducted in the two systems owing to the differences in network structures and analytical models.
SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation
The repeated cross-correlation and semi-FPN are designed based on this idea.
A Survey of Knowledge Enhanced Pre-trained Models
Pre-trained models learn contextualized word representations on large-scale text corpus through a self-supervised learning method, which has achieved promising performance after fine-tuning.
Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference
Sensors are the key to sensing the environment and imparting benefits to smart cities in many aspects, such as providing real-time air quality information throughout an urban area.
Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders
In order to overcome this problem, we propose a novel conditional variational autoencoder (VAE) that explicitly models one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code.
An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization
Medical named entity recognition (NER) and normalization (NEN) are fundamental for constructing knowledge graphs and building QA systems.
Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognition
In this paper, we tackle the problem by transferring knowledge from three aspects, i. e., domain, language and task, and strengthening connections among them.
Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function
We consider non-convex stochastic optimization problems where the objective functions have super-linearly growing and discontinuous stochastic gradients.
Animatable Neural Radiance Fields from Monocular RGB Videos
We present animatable neural radiance fields (animatable NeRF) for detailed human avatar creation from monocular videos.
Model-based 3D Hand Reconstruction via Self-Supervised Learning
For the first time, we demonstrate the feasibility of training an accurate 3D hand reconstruction network without relying on manual annotations.
Quantifying measurement-induced nonbilocal correlation
In the paper, we devote to defining an available measure to quantify the nonbilocal correlation in the entanglement-swapping experiment.
Quantum Physics
Adaptive Load Shedding for Grid Emergency Control via Deep Reinforcement Learning
Emergency control, typically such as under-voltage load shedding (UVLS), is broadly used to grapple with low voltage and voltage instability issues in practical power systems under contingencies.
Similarity Reasoning and Filtration for Image-Text Matching
Image-text matching plays a critical role in bridging the vision and language, and great progress has been made by exploiting the global alignment between image and sentence, or local alignments between regions and words.
Ranked #2 on
Image Retrieval
on Flickr30K 1K test
A Unified Spectral Sparsification Framework for Directed Graphs
For the first time, we prove the existence of linear-sized spectral sparsifiers for general directed graphs and introduce a practically-efficient and unified spectral graph sparsification approach that allows sparsifying real-world, large-scale directed and undirected graphs with guaranteed preservation of the original graph spectra.
Existence and uniqueness of local weak solution of d-dimensional tropical climate model without thermal diffusion in inhomogeneous Besov space
This paper studies the existence and uniqueness of local weak solutions to the d-dimensional tropical climate model without thermal diffusion.
Analysis of PDEs
Emotional Conversation Generation with Heterogeneous Graph Neural Network
Firstly, we design a Heterogeneous Graph-Based Encoder to represent the conversation content (i. e., the dialogue history, its emotion flow, facial expressions, audio, and speakers' personalities) with a heterogeneous graph neural network, and then predict suitable emotions for feedback.
SF-GRASS: Solver-Free Graph Spectral Sparsification
Recent spectral graph sparsification techniques have shown promising performance in accelerating many numerical and graph algorithms, such as iterative methods for solving large sparse matrices, spectral partitioning of undirected graphs, vectorless verification of power/thermal grids, representation learning of large graphs, etc.
Consensus-Aware Visual-Semantic Embedding for Image-Text Matching
In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching.
A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating
We are thus able to provide theoretical guarantees for the algorithm's convergence in (standard) Wasserstein distances for both convex and non-convex objective functions.
GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
We observe that existing works on structured entity interaction prediction cannot properly exploit the unique graph of graphs model.
Binarized Graph Neural Network
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches to binarize the model parameters and learn the compact embedding.
Machine learning on DNA-encoded libraries: A new paradigm for hit-finding
We demonstrate a new approach applying machine learning to DEL selection data by identifying active molecules from a large commercial collection and a virtual library of easily synthesizable compounds.
Nonasymptotic estimates for Stochastic Gradient Langevin Dynamics under local conditions in nonconvex optimization
Within the context of empirical risk minimization, see Raginsky, Rakhlin, and Telgarsky (2017), we are concerned with a non-asymptotic analysis of sampling algorithms used in optimization.
Retrieving Signals in the Frequency Domain with Deep Complex Extractors
Using the Wall Street Journal Dataset, we compare our phase-aware loss to several others that operate both in the time and frequency domains and demonstrate the effectiveness of our proposed signal extraction method and proposed loss.
Task-Oriented Conversation Generation Using Heterogeneous Memory Networks
How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans.
Retrieving Signals with Deep Complex Extractors
Building on recent advances, we propose a new deep complex-valued method for signal retrieval and extraction in the frequency domain.
Improving Captioning for Low-Resource Languages by Cycle Consistency
Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years.
E2GAN: End-to-End Generative Adversarial Network or Multivariate Time Series Imputation
The missing values, appear in most of multivariate time series, prevent advanced analysis of multivariate time series data.
A Survey and Experimental Analysis of Distributed Subgraph Matching
We conduct extensive experiments for both unlabelled matching and labelled matching to analyze the performance of distributed subgraph matching under various settings, which is finally summarized as a practical guide.
Databases
On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case
We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017).
RecovDB: accurate and efficient missing blocks recovery for large time series
In this paper, we also compare the efficiency and accuracy of RECOVDB against state-of-the-art recovery systems.
Voiceprint recognition of Parkinson patients based on deep learning
In this paper, a method based on Deep Neural Network (DNN) recognition and classification combined with Mini-Batch Gradient Descent (MBGD) is proposed to distinguish PD patients from healthy people using voiceprint features.
Multivariate Time Series Imputation with Generative Adversarial Networks
Multivariate time series usually contain a large number of missing values, which hinders the application of advanced analysis methods on multivariate time series data.
Deep Cross-Modal Projection Learning for Image-Text Matching
The key point of image-text matching is how to accurately measure the similarity between visual and textual inputs.
Ranked #10 on
Text based Person Retrieval
on CUHK-PEDES
Fashion-Gen: The Generative Fashion Dataset and Challenge
We introduce a new dataset of 293, 008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists.
Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
Quaternion numbers and quaternion neural networks have shown their efficiency to process multidimensional inputs as entities, to encode internal dependencies, and to solve many tasks with less learning parameters than real-valued models.
Ranked #19 on
Speech Recognition
on TIMIT
Medical Concept Embedding with Time-Aware Attention
Embeddings of medical concepts such as medication, procedure and diagnosis codes in Electronic Medical Records (EMRs) are central to healthcare analytics.
IDEL: In-Database Entity Linking with Neural Embeddings
We present a novel architecture, In-Database Entity Linking (IDEL), in which we integrate the analytics-optimized RDBMS MonetDB with neural text mining abilities.
Online Product Quantization
The experiments demonstrate that our online PQ model is both time-efficient and effective for ANN search in dynamic large scale databases compared with baseline methods and the idea of partial PQ codebook update further reduces the update cost.
FashionBrain Project: A Vision for Understanding Europe's Fashion Data Universe
A core business in the fashion industry is the understanding and prediction of customer needs and trends.
Device-to-Device Load Balancing for Cellular Networks
The idea is to shift traffic from a congested cell to its adjacent under-utilized cells by leveraging inter-cell D2D communication, so that the traffic can be served without using extra spectrum, effectively improving the spectrum temporal efficiency.
Networking and Internet Architecture
Deep Mutual Learning
Model distillation is an effective and widely used technique to transfer knowledge from a teacher to a student network.
Deep Complex Networks
Despite their attractive properties and potential for opening up entirely new neural architectures, complex-valued deep neural networks have been marginalized due to the absence of the building blocks required to design such models.
Ranked #3 on
Music Transcription
on MusicNet
Fully Distributed and Asynchronized Stochastic Gradient Descent for Networked Systems
This paper considers a general data-fitting problem over a networked system, in which many computing nodes are connected by an undirected graph.
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Meanwhile, Connectionist Temporal Classification (CTC) with Recurrent Neural Networks (RNNs), which is proposed for labeling unsegmented sequences, makes it feasible to train an end-to-end speech recognition system instead of hybrid settings.
End-to-End Data Visualization by Metric Learning and Coordinate Transformation
This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset.
Recurrent Neural Networks With Limited Numerical Precision
Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high.
Professor Forcing: A New Algorithm for Training Recurrent Networks
We introduce the Professor Forcing algorithm, which uses adversarial domain adaptation to encourage the dynamics of the recurrent network to be the same when training the network and when sampling from the network over multiple time steps.
Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)
Approximate Nearest neighbor search (ANNS) is fundamental and essential operation in applications from many domains, such as databases, machine learning, multimedia, and computer vision.
Databases
Recurrent Neural Networks With Limited Numerical Precision
We present results from the use of different stochastic and deterministic reduced precision training methods applied to three major RNN types which are then tested on several datasets.
On Multiplicative Integration with Recurrent Neural Networks
We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs).
Sample-Specific SVM Learning for Person Re-Identification
Person re-identification addresses the problem of matching people across disjoint camera views and extensive efforts have been made to seek either the robust feature representation or the discriminative matching metrics.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Batch Normalized Recurrent Neural Networks
Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies.
Subspace Clustering by Mixture of Gaussian Regression
Therefore, we propose Mixture of Gaussian Regression (MoG Regression) for subspace clustering by modeling noise as a Mixture of Gaussians (MoG).
