Search Results for author:
Found 97 papers, 35 papers with code
Decoupled Local Aggregation for Point Cloud Learning
In this work, we propose to decouple the explicit modelling of spatial relations from local aggregation.
Ranked #2 on
Semantic Segmentation
on S3DIS Area5
Teeth And Root Canals Segmentation Using ZXYFormer With Uncertainty Guidance And Weight Transfer
In addition, there are weak edges at the tooth, between tooth and root canal, which makes it very difficult to segment such weak edges.
A Hybrid CNN-Transformer Architecture with Frequency Domain Contrastive Learning for Image Deraining
Image deraining is a challenging task that involves restoring degraded images affected by rain streaks.
Evaluation of STT-MRAM as a Scratchpad for Training in ML Accelerators
We devised a cross-layer simulation framework to evaluate the effectiveness of STT-MRAM as a scratchpad replacing SRAM in a systolic-array-based DNN accelerator.
Calibration in Deep Learning: A Survey of the State-of-the-Art
In this survey, we review the state-of-the-art calibration methods and provide an understanding of their principles for performing model calibration.
FLGo: A Fully Customizable Federated Learning Platform
Federated learning (FL) has found numerous applications in healthcare, finance, and IoT scenarios.
Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI
Magnetic resonance imaging (MRI) using hyperpolarized noble gases provides a way to visualize the structure and function of human lung, but the long imaging time limits its broad research and clinical applications.
SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth
By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.
Ranked #1 on
Multi-Object Tracking
on MOT20
(using extra training data)
Resilient-Economic Coordinated Robust Operation of Integrated Electric-Gas Systems
Interactions between power and gas systems, which are both large and complex, have been gradually intensified during the last decades, predominantly due to the propagation of large fleet natural gas-fired power units (GPUs) and the technological developments of power-to-gas (P2G) facilities.
Optimizing Energy Efficiency in Metro Systems Under Uncertainty Disturbances Using Reinforcement Learning
In the realm of urban transportation, metro systems serve as crucial and sustainable means of public transit.
DSMNet: Deep High-precision 3D Surface Modeling from Sparse Point Cloud Frames
Second, we propose an modeling evaluation method based on HPMB for object-level modeling to overcome this limitation.
Point Cloud Registration
Simultaneous Localization and Mapping
CIMI4D: A Large Multimodal Climbing Motion Dataset under Human-scene Interactions
The core of this dataset is a blending optimization process, which corrects for the pose as it drifts and is affected by the magnetic conditions.
OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation
Fortunately, we have identified two observations that help us achieve the best of both worlds: 1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and 2) learning localization cues is sufficient for open world instance segmentation.
Meta-Calibration Regularized Neural Networks
Our experiments show that (a) learning sample-wise gamma at continuous space can effectively perform calibration; (b) SECE smoothly optimise gamma-net towards better robustness to binning schemes; (c) the combination of gamma-net and SECE achieve the best calibration performance across various calibration metrics and retain very competitive predictive performance as compared to multiple recently proposed methods on three datasets.
SLOPER4D: A Scene-Aware Dataset for Global 4D Human Pose Estimation in Urban Environments
We present SLOPER4D, a novel scene-aware dataset collected in large urban environments to facilitate the research of global human pose estimation (GHPE) with human-scene interaction in the wild.
Ins-ATP: Deep Estimation of ATP for Organoid Based on High Throughput Microscopic Images
Performing ATP bioluminescence causes cell lysis of organoids, so it is impossible to observe organoids' long-term viability changes after medication continually.
Interpreting Hidden Semantics in the Intermediate Layers of 3D Point Cloud Classification Neural Network
It delivers the class Relevance to the activated neurons in the intermediate layers in a back-propagation manner, and associates the activation of neurons with the input points to visualize the hidden semantics of each layer.
Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Reality
Adversarial examples are beneficial to improve the robustness of the 3D neural network model and enhance the stability of the AR system.
Virtual Sparse Convolution for Multimodal 3D Object Detection
Finally, we develop a semi-supervised pipeline VirConv-S based on a pseudo-label framework.
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
We present CEMA: Causal Explanations in Multi-Agent systems; a general framework to create causal explanations for an agent's decisions in sequential multi-agent systems.
INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
It aims to infer knowledge for (the things at) unobserved locations using the data from (the things at) observed locations during a given time period of interest.
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization
In this work, we propose a novel LiDAR localization framework, SGLoc, which decouples the pose estimation to point cloud correspondence regression and pose estimation via this correspondence.
State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
Few-Shot Specific Emitter Identification via Hybrid Data Augmentation and Deep Metric Learning
Specific emitter identification (SEI) is a potential physical layer authentication technology, which is one of the most critical complements of upper layer authentication.
FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
Second, constrained by the far-distance in data distribution of the sampled clients, we further minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias.
Transformation-Equivariant 3D Object Detection for Autonomous Driving
However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed.
Statistical Inference for Coadded Astronomical Images
Coadded astronomical images are created by stacking multiple single-exposure images.
Exposing Surveillance Detection Routes via Reinforcement Learning, Attack Graphs, and Cyber Terrain
Reinforcement learning (RL) operating on attack graphs leveraging cyber terrain principles are used to develop reward and state associated with determination of surveillance detection routes (SDR).
Deploying a Retrieval based Response Model for Task Oriented Dialogues
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints.
HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces
To address these issues, we introduce hyper surface fitting to implicitly learn hyper surfaces, which are represented by multi-layer perceptron (MLP) layers that take point features as input and output surface patterns in a high dimensional feature space.
Ranked #2 on
Surface Normals Estimation
on PCPNet
KG-MTT-BERT: Knowledge Graph Enhanced BERT for Multi-Type Medical Text Classification
Herein, we develop a new model called KG-MTT-BERT (Knowledge Graph Enhanced Multi-Type Text BERT) by extending the BERT model for long and multi-type text with the integration of the medical knowledge graph.
Deep Reinforcement Learning for Multi-Agent Interaction
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning.
Verifiable Goal Recognition for Autonomous Driving with Occlusions
Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour.
Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation
Relevant recommendation is a special recommendation scenario which provides relevant items when users express interests on one target item (e. g., click, like and purchase).
A Co-design view of Compute in-Memory with Non-Volatile Elements for Neural Networks
In the second part, we review what is knows about the different new non-volatile memory materials and devices suited for compute in-memory, and discuss the outlook and challenges.
LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds
Quantitative and qualitative experiments show that our method outperforms the techniques based only on RGB images.
HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments.
Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks
Despite the usefulness of this service, we consider that recommending courses to users directly may neglect their varying degrees of expertise.
Multi-Graph Fusion Networks for Urban Region Embedding
Human mobility data contains rich but abundant information, which yields to the comprehensive region embeddings for cross domain tasks.
A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Set
The granular-ball rough set can simultaneously represent Pawlak rough sets, and the neighborhood rough set, so as to realize the unified representation of the two.
C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System
To implement this framework, we design both coarse-grained and fine-grained procedures for modeling user preference, where the former focuses on more general, coarse-grained semantic fusion and the latter focuses on more specific, fine-grained semantic fusion.
Ranked #1 on
Recommendation Systems
on ReDial
Transformer Uncertainty Estimation with Hierarchical Stochastic Attention
In this work, we propose a novel way to enable transformers to have the capability of uncertainty estimation and, meanwhile, retain the original predictive performance.
Linear Discriminant Analysis with High-dimensional Mixed Variables
Datasets containing both categorical and continuous variables are frequently encountered in many areas, and with the rapid development of modern measurement technologies, the dimensions of these variables can be very high.
Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
However, this approach failed to explicitly reflect the correlations between different nodes at different time steps, thus limiting the learning capability of graph neural networks.
Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images
By integrating the spatial features from each cardiac frame of the gated MPS and the temporal features from the sequential cardiac frames of the gated MPS, we developed a Spatial-Temporal V-Net (ST-VNet) for automatic extraction of RV endocardial and epicardial contours.
ConTIG: Continuous Representation Learning on Temporal Interaction Graphs
Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems.
Oscillatory Fourier Neural Network: A Compact and Efficient Architecture for Sequential Processing
To address these challenges, we propose a novel neuron model that has cosine activation with a time varying component for sequential processing.
Storage and Transmission Capacity Requirements of a Remote Solar Power Generation System
Large solar power stations usually locate in remote areas and connect to the main grid via a long transmission line.
Detecting Mitosis against Domain Shift using a Fused Detector and Deep Ensemble Classification Model for MIDOG Challenge
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients' prognosis.
Stationary Multi-source AI-powered Real-time Tomography (SMART)
The reconstructed volumetric images convincingly demonstrate the merits of the SMART system using the AI-empowered interior tomography approach, enabling cardiac micro-CT with the unprecedented temporal resolution of 30ms, which is an order of magnitude higher than the state of the art.
Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
Due to the lack of insight in industrial application, existing methods on open datasets neglect the camera pose information, which inevitably results in the detector being susceptible to camera extrinsic parameters.
Ranked #6 on
Monocular 3D Object Detection
on KITTI Cars Moderate
(using extra training data)
Learning Slice-Aware Representations with Mixture of Attentions
Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score.
DLA-Net: Learning Dual Local Attention Features for Semantic Segmentation of Large-Scale Building Facade Point Clouds
As there is a lack of 3D point clouds datasets related to the fine-grained building facade, we construct the first large-scale building facade point clouds benchmark dataset for semantic segmentation.
Federated Learning with Fair Averaging
Fairness has emerged as a critical problem in federated learning (FL).
Handling Long-Tail Queries with Slice-Aware Conversational Systems
We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives.
A Detector-oblivious Multi-arm Network for Keypoint Matching
This paper presents a matching network to establish point correspondence between images.
Neighbor Embedding Variational Autoencoder
Being one of the most popular generative framework, variational autoencoders(VAE) are known to suffer from a phenomenon termed posterior collapse, i. e. the latent variational distributions collapse to the prior, especially when a strong decoder network is used.
FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
In this paper, we propose a novel benchmark dataset with more than 1 million instances and more than 15, 000 images for Fine-grAined object recognItion in high-Resolution remote sensing imagery which is named as FAIR1M.
Random matrix description of dynamically backscattered coherent waves propagating in a wide-field-illuminated random medium
We find that the dynamic speckle patterns can be utilized to decouple the singly and multiply backscattered components.
Optics Applied Physics
Efficient erbium-doped thin-film lithium niobate waveguide amplifiers
Lithium niobate on insulator (LNOI) is an emerging photonic platform with great promises for future optical communications, nonlinear optics and microwave photonics.
Optics Applied Physics
Structure-preserving, energy stable numerical schemes for a liquid thin film coarsening model
In the second order numerical scheme, the BDF temporal stencil is applied, and an alternate convex-concave decomposition is derived, so that the concave part corresponds to a quadratic energy.
Numerical Analysis Numerical Analysis 35A15 (Primary) 12-XX, 12-08 (Secondary) F.2.2; G.2
Rotational dynamics of bottom-heavy rods in turbulence from experiments and numerical simulations
We successfully perform the three-dimensional tracking in a turbulent fluid flow of small asymmetrical particles that are neutrally-buoyant and bottom-heavy, i. e., they have a non-homogeneous mass distribution along their symmetry axis.
Fluid Dynamics
Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
Uncertainty quantification is crucial for building reliable and trustable machine learning systems.
VPC-Net: Completion of 3D Vehicles from MLS Point Clouds
Moreover, a new refiner module is also presented to preserve the vehicle details from inputs and refine the complete outputs with fine-grained information.
TCTS: A Task-Consistent Two-Stage Framework for Person Search
In the re-ID stage, we predict identity labels of detected bounding boxes, and use these examples to construct a more practical mixed train set for the DRA model.
DNN-aided Read-voltage Threshold Optimization for MLC Flash Memory with Finite Block Length
The error correcting performance of multi-level-cell (MLC) NAND flash memory is closely related to the block length of error correcting codes (ECCs) and log-likelihood-ratios (LLRs) of the read-voltage thresholds.
Review: deep learning on 3D point clouds
Deep learning is now the most powerful tool for data processing in computer vision, becoming the most preferred technique for tasks such as classification, segmentation, and detection.
Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling
Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features.
GMAN: A Graph Multi-Attention Network for Traffic Prediction
Between the encoder and the decoder, a transform attention layer is applied to convert the encoded traffic features to generate the sequence representations of future time steps as the input of the decoder.
Ranked #2 on
Image Dehazing
on KITTI
Toward better boundary preserved supervoxel segmentation for 3D point clouds
In this paper, we present a simple but effective supervoxel segmentation method for point clouds, which formalizes supervoxel segmentation as a subset selection problem.
Accelerating Mini-batch SARAH by Step Size Rules
Motivated by this gap, we proposed a variant of the Barzilai-Borwein (BB) method, referred to as the Random Barzilai-Borwein (RBB) method, to calculate step size for SARAH in the mini-batch setting, thereby leading to a new SARAH method: MB-SARAH-RBB.
PointNLM: Point Nonlocal-Means for vegetation segmentation based on middle echo point clouds
Second, to accurately extract trees from all point clouds, we propose a 3D deep learning network, PointNLM, to semantically segment tree crowns.
RF-Net: An End-to-End Image Matching Network based on Receptive Field
This paper proposes a new end-to-end trainable matching network based on receptive field, RF-Net, to compute sparse correspondence between images.
Fast Regularity-Constrained Plane Reconstruction
Man-made environments typically comprise planar structures that exhibit numerous geometric relationships, such as parallelism, coplanarity, and orthogonality.
LO-Net: Deep Real-time Lidar Odometry
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation.
RecSys-DAN: Discriminative Adversarial Networks for Cross-Domain Recommender Systems
Although various transfer learning methods have shown promising performance in this context, our proposed novel method RecSys-DAN focuses on alleviating the cross-domain and within-domain data sparsity and data imbalance and learns transferable latent representations for users, items and their interactions.
State-Regularized Recurrent Neural Networks
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
A Fast Iterative Algorithm for High-dimensional Differential Network
Differential network is an important tool to capture the changes of conditional correlations under two sample cases.
Computation
Penalized Interaction Estimation for Ultrahigh Dimensional Quadratic Regression
In this article we introduce a novel method which allows us to estimate the main effects and interactions separately.
Methodology
Integrating and querying similar tables from PDF documents using deep learning
Tabular data extraction from reports and other published data in PDF format is of interest for various data consolidation purposes such as analysing and aggregating financial reports of a company.
Towards Personalized Management of Type B Aortic Dissection Using STENT: a STandard cta database with annotation of the ENtire aorta and True-false lumen
The database contains 274 CT angiography (CTA) scans from 274 unique TBAD patients and is split into a training set(254 cases including 210 preoperative and 44 postoperative scans ) and a test set(20 cases). Based on STENT, we develop a series of methods including automated TBAD segmentation and automated measurement of TBAD parameters that facilitate personalized and precise management of the disease.
NeuroTreeNet: A New Method to Explore Horizontal Expansion Network
It is widely recognized that the deeper networks or networks with more feature maps have better performance.
An efficient ADMM algorithm for high dimensional precision matrix estimation via penalized quadratic loss
The estimation of high dimensional precision matrices has been a central topic in statistical learning.
Computation Methodology
State-Regularized Recurrent Networks
We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications.
Layerwise Recurrent Autoencoder for General Real-world Traffic Flow Forecasting
To forecast the traffic flow across a wide area and overcome the mentioned challenges, we design and propose a promising forecasting model called Layerwise Recurrent Autoencoder (LRA), in which a three-layer stacked autoencoder (SAE) architecture is used to obtain temporal traffic correlations and a recurrent neural networks (RNNs) model for prediction.
Geometric Multi-Model Fitting by Deep Reinforcement Learning
This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e. g., laser scanned point clouds).
RealPoint3D: Point Cloud Generation from a Single Image with Complex Background
Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud.
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
LRMM: Learning to Recommend with Missing Modalities
More importantly, LRMM is more robust to previous methods in alleviating data-sparsity and the cold-start problem.
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #15 on
Unsupervised Domain Adaptation
on Market to Duke
LiDAR-Video Driving Dataset: Learning Driving Policies Effectively
Learning autonomous-driving policies is one of the most challenging but promising tasks for computer vision.
Traffic Sign Timely Visual Recognizability Evaluation Based on 3D Measurable Point Clouds
Then, based on the VEM, we proposed the concept of the Visual Recognizability Field (VRF) to reflect the visual recognizability distribution in 3D space and established a Visual Recognizability Evaluation Model (VREM) to measure a traffic sign visual recognizability for a given viewpoint.
RRA: Recurrent Residual Attention for Sequence Learning
In this paper, we propose a recurrent neural network (RNN) with residual attention (RRA) to learn long-range dependencies from sequential data.
Partial Procedural Geometric Model Fitting for Point Clouds
However, most geometric model fitting methods are unable to fit an arbitrary geometric model (e. g. a surface with holes) to incomplete data, due to that the similarity metrics used in these methods are unable to measure the rigid partial similarity between arbitrary models.
Punctuation Prediction for Unsegmented Transcript Based on Word Vector
In this paper we propose an approach to predict punctuation marks for unsegmented speech transcript.
Image Captioning with Deep Bidirectional LSTMs
This work presents an end-to-end trainable deep bidirectional LSTM (Long-Short Term Memory) model for image captioning.
