Search Results for author:
Found 69 papers, 18 papers with code
2nd Place Solution for Waymo Open Dataset Challenge - Real-time 2D Object Detection
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
Ranked #1 on
Object Detection
on Waymo Open Dataset
2nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object Detection
In an autonomous driving system, it is essential to recognize vehicles, pedestrians and cyclists from images.
DELTA: A DEep learning based Language Technology plAtform
In this paper we present DELTA, a deep learning based language technology platform.
Ranked #3 on
Text Classification
on Yahoo! Answers
Implementation of an Automated Learning System for Non-experts
This paper detailed the engineering system implementation of an automated machine learning system called YMIR, which completely relies on graphical interface to interact with users.
Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
Depth sensing is crucial for 3D reconstruction and scene understanding.
Is ChatGPT a Good Recommender? A Preliminary Study
We conduct human evaluations on two explainability-oriented tasks to more accurately evaluate the quality of contents generated by different models.
LLMRec: Benchmarking Large Language Models on Recommendation Task
The benchmark results indicate that LLMs displayed only moderate proficiency in accuracy-based tasks such as sequential and direct recommendation.
Learned Video Compression with Residual Prediction and Loop Filter
To reduce the complexity, a light ResNet structure is used as the backbone for both RP-Net and LF-Net.
SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models
However, diffusion models require careful tuning of inference hyperparameters on a validation set and are still sensitive to distribution shifts during testing.
BCE-Net: Reliable Building Footprints Change Extraction based on Historical Map and Up-to-Date Images using Contrastive Learning
This contrastive learning strategy allowed us to inject the semantics of buildings into a pipeline for the detection of changes, which is achieved by increasing the distinguishability of features of buildings from those of non-buildings.
SARNet: Semantic Augmented Registration of Large-Scale Urban Point Clouds
Registering urban point clouds is a quite challenging task due to the large-scale, noise and data incompleteness of LiDAR scanning data.
Deriving the stellar labels of LAMOST spectra with Stellar LAbel Machine (SLAM)
To illustrate this capability, we test the performance of SLAM on stars ranging from Teff$\sim$4000 to $\sim$8000 K trained on LAMOST spectra and stellar labels.
Solar and Stellar Astrophysics Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
TranSHER: Translating Knowledge Graph Embedding with Hyper-Ellipsoidal Restriction
However, such a method strictly restricts entities on the hyper-ellipsoid surfaces which limits the optimization of entity distribution, leading to suboptimal performance of knowledge graph completion.
Reverse-engineering Bar Charts Using Neural Networks
Reverse-engineering bar charts extracts textual and numeric information from the visual representations of bar charts to support application scenarios that require the underlying information.
DeepBranchTracer: A Generally-Applicable Approach to Curvilinear Structure Reconstruction Using Multi-Feature Learning
Curvilinear structures, which include line-like continuous objects, are fundamental geometrical elements in image-based applications.
Motion Prediction for Beating Heart Surgery with GRU
This work aims to predict the 3D coordinates of the point of interest (POI) on the surface of beating heart in dynamic minimally invasive surgery, which can improve the manoeuvrability of cardiac surgical robots and expand their functions.
Root-cause Analysis for Time-series Anomalies via Spatiotemporal Graphical Modeling in Distributed Complex Systems
Performance monitoring, anomaly detection, and root-cause analysis in complex cyber-physical systems (CPSs) are often highly intractable due to widely diverse operational modes, disparate data types, and complex fault propagation mechanisms.
Data-driven root-cause analysis for distributed system anomalies
Modern distributed cyber-physical systems encounter a large variety of anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems.
Predicting County Level Corn Yields Using Deep Long Short Term Memory Models
Corn yield prediction is beneficial as it provides valuable information about production and prices prior the harvest.
Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application
In recent years, an increasing popularity of deep learning model for intelligent condition monitoring and diagnosis as well as prognostics used for mechanical systems and structures has been observed.
Energy Prediction using Spatiotemporal Pattern Networks
This paper presents a novel data-driven technique based on the spatiotemporal pattern network (STPN) for energy/power prediction for complex dynamical systems.
An unsupervised spatiotemporal graphical modeling approach to anomaly detection in distributed CPS
Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems.
Learning Discriminative Illumination and Filters for Raw Material Classification with Optimal Projections of Bidirectional Texture Functions
We built an LED-based multispectral dome, with which we have acquired a BTF database of a variety of materials and demonstrated the effectiveness of the proposed approach for material classification.
Real-Time Visual Analysis of Microvascular Blood Flow for Critical Care
Our method is able to extract microcirculatory measurements that are consistent with clinical intuition and it has a potential to become a useful tool in critical care medicine.
Matting and Depth Recovery of Thin Structures Using a Focal Stack
For macro-scale, we evaluate our method on scenes with complex 3D thin structures such as tree branches and grass.
Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera
Depth sensing is crucial for 3D reconstruction and scene understanding.
Salient Instance Segmentation via Subitizing and Clustering
The experimental results on both salient region detection and salient instance segmentation datasets demonstrate the satisfactory performance of our framework.
MIOpen: An Open Source Library For Deep Learning Primitives
Deep Learning has established itself to be a common occurrence in the business lexicon.
Automatic Lumbar Spinal CT Image Segmentation with a Dual Densely Connected U-Net
The clinical treatment of degenerative and developmental lumbar spinal stenosis (LSS) is different.
A Multi-Task Learning Framework for Extracting Bacteria Biotope Information
This paper presents a novel transfer multi-task learning method for Bacteria Biotope rel+ner task at BioNLP-OST 2019.
Dual Learning-based Video Coding with Inception Dense Blocks
This method is mainly composed of two parts: intra prediction and reconstruction filtering.
Interpretable Machine Learning Model for Early Prediction of Mortality in Elderly Patients with Multiple Organ Dysfunction Syndrome (MODS): a Multicenter Retrospective Study and Cross Validation
This study aims to develop an interpretable and generalizable model for early mortality prediction in elderly patients with MODS.
CodeMatcher: Searching Code Based on Sequential Semantics of Important Query Words
CodeMatcher first collects metadata for query words to identify irrelevant/noisy ones, then iteratively performs fuzzy search with important query words on the codebase that is indexed by the Elasticsearch tool, and finally reranks a set of returned candidate code according to how the tokens in the candidate code snippet sequentially matched the important words in a query.
On the Replicability and Reproducibility of Deep Learning in Software Engineering
Experimental results show the importance of replicability and reproducibility, where the reported performance of a DL model could not be replicated for an unstable optimization process.
Future stability of the FLRW spacetime for a large class of perfect fluids
Several previous results as specific examples can be covered in the results of this article.
General Relativity and Quantum Cosmology Analysis of PDEs Primary 35A01, Secondary 35Q31, 35Q76, 83C05, 83F05
Newtonian Limits of Isolated Cosmological Systems on Long Time Scales
We establish the existence of $1$-parameter families of $\epsilon$-dependent solutions to the Einstein-Euler equations with a positive cosmological constant $\Lambda >0$ and a linear equation of state $p=\epsilon^2 K \rho$, $0<K\leq 1/3$, for the parameter values $0<\epsilon < \epsilon_0$.
General Relativity and Quantum Cosmology Cosmology and Nongalactic Astrophysics Analysis of PDEs
Cosmological Newtonian limits on large spacetime scales
We establish the existence of $1$-parameter families of $\epsilon$-dependent solutions to the Einstein-Euler equations with a positive cosmological constant $\Lambda >0$ and a linear equation of state $p=\epsilon^2 K \rho$, $0<K\leq 1/3$, for the parameter values $0<\epsilon < \epsilon_0$.
General Relativity and Quantum Cosmology Analysis of PDEs
A QP-adaptive Mechanism for CNN-based Filter in Video Coding
Convolutional neural network (CNN)-based filters have achieved great success in video coding.
LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks
Due to the lack of real-world datasets, they usually perform poorly when generalized in practice in terms of loss of image edge and color information.
UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement
To address this problem, we propose a real-time unsupervised generative adversarial network (GAN) containing multiple discriminators, i. e. a multi-scale discriminator, a texture discriminator, and a color discriminator.
Possible evidence of hydrogen emission in the first-overtone and multi-mode RR Lyrae variables
The nature of shock waves in non-fundamental mode RR Lyrae stars remains a mystery because of limited spectroscopic observations.
Solar and Stellar Astrophysics
Exploring the Galactic Anticenter substructure with LAMOST & Gaia DR2
Their location in [$\alpha$/M] vs. [M/H] space is more metal poor than typical thin disk stars, with [$\alpha$/M] \textbf{lower} than the thick disk.
Astrophysics of Galaxies
The Flare and Warp of the Young Stellar Disk traced with LAMOST DR5 OB-type stars
We present analysis of the spatial density structure for the outer disk from 8$-$14 \, kpc with the LAMOST DR5 13534 OB-type stars and observe similar flaring on north and south sides of the disk implying that the flaring structure is symmetrical about the Galactic plane, for which the scale height at different Galactocentric distance is from 0. 14 to 0. 5 \, kpc.
Astrophysics of Galaxies
Planets Across Space and Time (PAST). I. Characterizing the Memberships of Galactic Components and Stellar Ages: Revisiting the Kinematic Methods and Applying to Planet Host Stars
The revised kinematic method and AVR as well as the stellar catalog of kinematic properties and ages lay foundation for future studies on exoplanets from two dimensions of space and time in the Galactic context.
Earth and Planetary Astrophysics Astrophysics of Galaxies Solar and Stellar Astrophysics
BLOCKEYE: Hunting For DeFi Attacks on Blockchain
We applied BLOCKEYE in several popular DeFi projects and managed to discover potential security attacks that are unreported before.
Cryptography and Security Computers and Society
Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models
In this work, we introduce a general method for 3D self-supervised representation learning that 1) remains agnostic to the underlying neural network architecture, and 2) specifically leverages the geometric nature of 3D point cloud data.
Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
In addition, Byzantine faults including software, hardware, network issues occur in distributed systems which also lead to a negative impact on the prediction outcome.
Learned Image Compression with Separate Hyperprior Decoders
Learned image compression techniques have achieved considerable development in recent years.
Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification
To improve functionality, we propose a new transparent network called Graph Decipher to investigate the message-passing mechanism by prioritizing in two main components: the graph structure and node attributes, at the graph, feature, and global levels on a graph under the node classification task.
Sparse-Dyn: Sparse Dynamic Graph Multi-representation Learning via Event-based Sparse Temporal Attention Network
Dynamic graph neural networks have been widely used in modeling and representation learning of graph structure data.
Recursive Least Squares Policy Control with Echo State Network
However, limited by the strong correlation among sequential samples of the agent, ESN-based policy control algorithms are difficult to use the recursive least squares (RLS) algorithm to update the ESN's parameters.
Precognition in Task-oriented Dialogue Understanding: Posterior Regularization by Future Context
And only historical information is used for inference.
MixNN: A design for protecting deep learning models
In this paper, we propose a novel design, called MixNN, for protecting deep learning model structure and parameters.
S4OD: Semi-Supervised learning for Single-Stage Object Detection
In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity.
Immunofluorescence Capillary Imaging Segmentation: Cases Study
Our work offers a benchmark dataset for training deep learning models for capillary image segmentation and provides a potential tool for future capillary research.
Asynchronous Training Schemes in Distributed Learning with Time Delay
In the context of distributed deep learning, the issue of stale weights or gradients could result in poor algorithmic performance.
CAIBC: Capturing All-round Information Beyond Color for Text-based Person Retrieval
Indeed, color information is an important decision-making accordance for retrieval, but the over-reliance on color would distract the model from other key clues (e. g. texture information, structural information, etc.
Look Before You Leap: Improving Text-based Person Retrieval by Learning A Consistent Cross-modal Common Manifold
We evaluate our proposed method on two text-based person retrieval datasets CUHK-PEDES and RSTPReid.
LEGO-ABSA: A Prompt-based Task Assemblable Unified Generative Framework for Multi-task Aspect-based Sentiment Analysis
This paper proposes a unified generative multi-task framework that can solve multiple ABSA tasks by controlling the type of task prompts consisting of multiple element prompts.
Ranked #5 on
Aspect-Based Sentiment Analysis (ABSA)
on TASD
(using extra training data)
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Towards Cooperative Flight Control Using Visual-Attention
We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system.
Corner Detection Based on Multi-directional Gabor Filters with Multi-scales
In this work, the capability of the Gabor function to discriminate the intensity changes of step edges, L-shaped corners, Y-shaped or T-shaped corners, X-shaped corners, and star-shaped corners are investigated.
Real-Time Radiance Fields for Single-Image Portrait View Synthesis
We present a one-shot method to infer and render a photorealistic 3D representation from a single unposed image (e. g., face portrait) in real-time.
FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flow
Given the extracted flow, the flow-guided feature augmentation is designed to augment the object detection feature based on its optical flow, which improves the detection of small objects.
Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection
We present a learning-based system to reduce these artifacts without resorting to complex acquisition mechanisms like alternating exposures or costly processing that are typical of high dynamic range (HDR) imaging.
Soft Merging: A Flexible and Robust Soft Model Merging Approach for Enhanced Neural Network Performance
This merging process not only enhances the model performance by converging to a better local optimum, but also minimizes computational costs, offering an efficient and explicit learning process integrated with stochastic gradient descent.
Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them
Through our comprehensive review and analysis, this paper seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.
