Search Results for author:
Found 183 papers, 73 papers with code
How to leverage the multimodal EHR data for better medical prediction?
Therefore, in this paper, we first extract the accompanying clinical notes from EHR and propose a method to integrate these data, we also comprehensively study the different models and the data leverage methods for better medical task prediction performance.
Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences
This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G systems.
CE-U: Cross Entropy Unlearning
Large language models (LLMs) inadvertently memorize sensitive data from their massive pretraining corpora \cite{jang2022knowledge}.
Incomplete Graph Learning: A Comprehensive Survey
Subsequently, we classify incomplete graph learning methods according to the types of incompleteness: (1) attribute-incomplete graph learning methods, (2) attribute-missing graph learning methods, and (3) hybrid-absent graph learning methods.
Convolution-Based Converter : A Weak-Prior Approach For Modeling Stochastic Processes Based On Conditional Density Estimation
In this paper, a Convolution-Based Converter (CBC) is proposed to develop a methodology for removing the strong or fixed priors in estimating the probability distribution of targets based on observations in the stochastic process.
EFKAN: A KAN-Integrated Neural Operator For Efficient Magnetotelluric Forward Modeling
Neural operators (NOs) have been effectively used for rapid MT forward modeling, demonstrating their promising performance in solving the MT forward modeling-related partial differential equations (PDEs).
Large Language Models as Theory of Mind Aware Generative Agents with Counterfactual Reflection
Recent studies have increasingly demonstrated that large language models (LLMs) possess significant theory of mind (ToM) capabilities, showing the potential for simulating the tracking of mental states in generative agents.
MiniMax-01: Scaling Foundation Models with Lightning Attention
This approach enables us to conduct efficient training and inference on models with hundreds of billions of parameters across contexts spanning millions of tokens.
Towards Lightweight Time Series Forecasting: a Patch-wise Transformer with Weak Data Enriching
To contend with the two limitations, we propose LiPFormer, a novel Lightweight Patch-wise Transformer with weak data enriching.
Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
We propose the Multiple Monotonic Diversified Integrated Gradients (MuMoDIG) attack, which can generate highly transferable adversarial examples on different CNN and ViT models and defenses.
Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach
Multifaceted user modeling aims to uncover fine-grained patterns and learn representations from user data, revealing their diverse interests and characteristics, such as profile, preference, and personality.
A Tutorial of Personalized Federated Recommender Systems: Recent Advances and Future Directions
This tutorial seeks to provide an introduction to PFedRecSys, encompassing (1) an overview of existing studies on PFedRecSys, (2) a comprehensive taxonomy of PFedRecSys spanning four pivotal research directions-client-side adaptation, server-side aggregation, communication efficiency, privacy and protection, and (3) exploration of open challenges and promising future directions in PFedRecSys.
GDSG: Graph Diffusion-based Solution Generator for Optimization Problems in MEC Networks
We build GDSG as a multi-task diffusion model utilizing a Graph Neural Network (GNN) to acquire the distribution of high-quality solutions.
BATseg: Boundary-aware Multiclass Spinal Cord Tumor Segmentation on 3D MRI Scans
Extensive experiments on our dataset and another public kidney tumor segmentation dataset show that our proposed method achieves superior performance for multiclass tumor segmentation.
Hierarchical Learning for IRS-Assisted MEC Systems with Rate-Splitting Multiple Access
Intelligent reflecting surface (IRS)-assisted mobile edge computing (MEC) systems have shown notable improvements in efficiency, such as reduced latency, higher data rates, and better energy efficiency.
Multi-layer matrix factorization for cancer subtyping using full and partial multi-omics dataset
Cancer, with its inherent heterogeneity, is commonly categorized into distinct subtypes based on unique traits, cellular origins, and molecular markers specific to each type.
Learning Interpretable Network Dynamics via Universal Neural Symbolic Regression
Discovering governing equations of complex network dynamics is a fundamental challenge in contemporary science with rich data, which can uncover the mysterious patterns and mechanisms of the formation and evolution of complex phenomena in various fields and assist in decision-making.
UTMath: Math Evaluation with Unit Test via Reasoning-to-Coding Thoughts
The evaluation of mathematical reasoning capabilities is essential for advancing Artificial General Intelligence (AGI).
Diffusion Models as Network Optimizers: Explorations and Analysis
Next, we provide a concise theoretical proof and intuitive demonstration of the advantages of generative models over discriminative models in network optimization.
Optimal Hardening Strategy for Electricity-Hydrogen Networks with Hydrogen Leakage Risk Control against Extreme Weather
However, for electricity-hydrogen distribution networks (EHDNs), the leakage risk of hydrogen should be controlled to avoid severe incidents such as explosions.
Enhancing SNN-based Spatio-Temporal Learning: A Benchmark Dataset and Cross-Modality Attention Model
In this work, we present a neuromorphic dataset called DVS-SLR that can better exploit the inherent spatio-temporal properties of SNNs.
Conditional Prediction ROC Bands for Graph Classification
To address this need, we introduce Conditional Prediction ROC (CP-ROC) bands, offering uncertainty quantification for ROC curves and robustness to distributional shifts in test data.
Conditional Uncertainty Quantification for Tensorized Topological Neural Networks
Graph Neural Networks (GNNs) have become the de facto standard for analyzing graph-structured data, leveraging message-passing techniques to capture both structural and node feature information.
GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing
We verified the proposed model on both 2D and 3D meshes.
Modeling, Prediction and Risk Management of Distribution System Voltages with Non-Gaussian Probability Distributions
The deviation of voltage risks obtained by the proposed method is only 15% of that by the methods based on probabilistic prediction of nodal power injections.
Flexible Operation of Electricity-HCNG Networks with Variable Hydrogen Fraction: A Distributionally Robust Joint Chance-Constrained Approach
Hydrogen-enriched compressed natural gas (HCNG) is a promising way to utilize surplus renewable energy through hydrogen electrolysis and blending it into natural gas.
Optimal Control in Both Steady State and Transient Process with Unknown Disturbances
The scheme of online optimization as a feedback controller is widely used to steer the states of a physical system to the optimal solution of a predefined optimization problem.
CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought
We propose CoT-ST, a speech translation model that utilizes multimodal CoT to decompose speech translation into sequential steps of speech recognition and translation.
Energy-Efficient Multi-UAV-Enabled MEC Systems with Space-Air-Ground Integrated Networks
With the development of artificial intelligence integrated next-generation communication networks, mobile users (MUs) are increasingly demanding the efficient processing of computation-intensive and latency-sensitive tasks.
UAV-Enabled Data Collection for IoT Networks via Rainbow Learning
This letter considers a scenario where a multi-antenna UAV is dispatched to simultaneously collect data from multiple ground IoT nodes (GNs) within a time interval.
O-Mamba: O-shape State-Space Model for Underwater Image Enhancement
This branch includes MS-MoE for fusing multi-scale information within branches, Mutual Promotion module for interaction between spatial and channel information across branches, and Cyclic Multi-scale optimization strategy to maximize the use of multi-scale information.
Angle of Arrival Estimation with Transformer: A Sparse and Gridless Method with Zero-Shot Capability
To fully leverage the advantages of MIMO radars, it is crucial to develop an Angle of Arrival (AOA) algorithm that delivers high performance with reasonable computational workload.
DiffSG: A Generative Solver for Network Optimization with Diffusion Model
In summary, we demonstrate the potential of generative diffusion models in tackling complex network optimization problems and outline a promising path for their broader application in the communication community.
OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
It has long been challenging to recover the underlying dynamic 3D scene representations from a monocular RGB video.
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement
Notably, ASR models trained on GigaSpeech 2 can reduce the word error rate for Thai, Indonesian, and Vietnamese on our challenging and realistic YouTube test set by 25% to 40% compared to the Whisper large-v3 model, with merely 10% model parameters.
Survey for Landing Generative AI in Social and E-commerce Recsys -- the Industry Perspectives
Recently, generative AI (GAI), with their emerging capabilities, have presented unique opportunities for augmenting and revolutionizing industrial recommender systems (Recsys).
Joint Association, Beamforming, and Resource Allocation for Multi-IRS Enabled MU-MISO Systems With RSMA
Intelligent reflecting surface (IRS) and rate-splitting multiple access (RSMA) technologies are at the forefront of enhancing spectrum and energy efficiency in the next generation multi-antenna communication systems.
In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought
Recent works demonstrated that in-context RL could emerge with self-improvement in a trial-and-error manner when treating RL tasks as an across-episodic sequential prediction problem.
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles.
Federated Adaptation for Foundation Model-based Recommendations
It becomes a new open challenge to enable the foundation model to capture user preference changes in a timely manner with reasonable communication and computation costs while preserving privacy.
UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science.
Adversarial Example Soups: Improving Transferability and Stealthiness for Free
Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge.
Scalable Volt-VAR Optimization using RLlib-IMPALA Framework: A Reinforcement Learning Approach
To address this challenge, our research presents a novel framework that harnesses the potential of Deep Reinforcement Learning (DRL), specifically utilizing the Importance Weighted Actor-Learner Architecture (IMPALA) algorithm, executed on the RAY platform.
Computation Offloading for Multi-server Multi-access Edge Vehicular Networks: A DDQN-based Method
In this paper, we investigate a multi-user offloading problem in the overlapping domain of a multi-server mobile edge computing system.
Troublemaker Learning for Low-Light Image Enhancement
Second, the predicting model (PM) enhances the brightness of pseudo low-light images.
Zero-shot sketch-based remote sensing image retrieval based on multi-level and attention-guided tokenization
To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update.
Seismic Traveltime Tomography with Label-free Learning
To avoid generating and/or collecting labeled samples, we propose a novel method by integrating deep learning and dictionary learning to enhance the VMs with low resolution by using the traditional tomography-least square method (LSQR).
ADA-GNN: Atom-Distance-Angle Graph Neural Network for Crystal Material Property Prediction
However, most of the existing works only consider bond distances and overlook bond angles.
Fine-Grained Prototypes Distillation for Few-Shot Object Detection
However, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance. New methods are required to capture the distinctive local context for more robust novel object detection.
Joint Trading and Scheduling among Coupled Carbon-Electricity-Heat-Gas Industrial Clusters
This paper presents a carbon-energy coupling management framework for an industrial park, where the carbon flow model accompanying multi-energy flows is adopted to track and suppress carbon emissions on the user side.
SLP-Net:An efficient lightweight network for segmentation of skin lesions
Prompt treatment for melanoma is crucial.
Multi-stages attention Breast cancer classification based on nonlinear spiking neural P neurons with autapses
Downsampling in deep networks may lead to loss of information, so for compensating the detail and edge information and allowing convolutional neural networks to pay more attention to seek the lesion region, we propose a multi-stages attention architecture based on NSNP neurons with autapses.
NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos
In this paper, we aim to model 3D scene dynamics from multi-view videos.
Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images
We first introduce seven complexity factors to quantitatively measure the distributions of background and foreground object biases in appearance and geometry for datasets with human annotations.
A multi-layer refined network model for the identification of essential proteins
In order to improve the accuracy of the identification of essential proteins, researchers attempted to obtain a refined PIN by combining multiple biological information to filter out some unreliable interactions in the PIN.
Exploring Adversarial Robustness of LiDAR-Camera Fusion Model in Autonomous Driving
Our study assesses the adversarial robustness of LiDAR-camera fusion models in 3D object detection.
PerCNet: Periodic Complete Representation for Crystal Graphs
To solve this many-to-one issue, we consider the global information by further considering dihedral angles, which can guarantee that the proposed representation corresponds one-to-one with the crystal material.
RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency
In this paper, we study the problem of continuous 3D shape representations.
Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes
Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains.
Learning Generalizable Agents via Saliency-Guided Features Decorrelation
Our experimental results demonstrate that SGFD can generalize well on a wide range of test environments and significantly outperforms state-of-the-art methods in handling both task-irrelevant variations and task-relevant variations.
Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4
Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information.
Analysis and Experimental Validation of the WPT Efficiency of the Both-Sides Retrodirective System
The retrodirective antenna array is considered as a mechanism to enable target tracking of a power receiver for long range wireless power transfer (WPT) due to its simplicity in implementation using only analog circuits.
A Novel Neural-symbolic System under Statistical Relational Learning
A key objective in field of artificial intelligence is to develop cognitive models that can exhibit human-like intellectual capabilities.
A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading
To improve the MEC performance, it is required to design an optimal offloading strategy that includes offloading decision (i. e., whether offloading or not) and computational resource allocation of MEC.
Hydrogen Supply Infrastructure Network Planning Approach towards Chicken-egg Conundrum
However, there is a strong causality between HFCVs and hydrogen refueling stations (HRSs): the planning decisions of HRSs could affect the hydrogen refueling demand of HFCVs, and the growth of demand would in turn stimulate the further investment in HRSs, which is also known as the ``chicken and egg'' conundrum.
Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition
Graph convolutional networks have been widely applied in skeleton-based gait recognition.
EFLNet: Enhancing Feature Learning for Infrared Small Target Detection
To address this problem, we propose a new adaptive threshold focal loss (ATFL) function that decouples the target and the background, and utilizes the adaptive mechanism to adjust the loss weight to force the model to allocate more attention to target features.
Monadic Deep Learning
These dynamically typed deep learning frameworks treat neural networks as differentiable expressions that contain many trainable variable, and perform automatic differentiation on those expressions when training them.
EfficientSRFace: An Efficient Network with Super-Resolution Enhancement for Accurate Face Detection
In face detection, low-resolution faces, such as numerous small faces of a human group in a crowded scene, are common in dense face prediction tasks.
GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds
Our method consists of three major components, 1) the feature extractor to learn per-point features from input point clouds, 2) the superpoint constructor to progressively grow the sizes of superpoints, and 3) the semantic primitive clustering module to group superpoints into semantic elements for the final semantic segmentation.
When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions
However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings.
Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?
As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks.
GPFedRec: Graph-guided Personalization for Federated Recommendation
The federated recommendation system is an emerging AI service architecture that provides recommendation services in a privacy-preserving manner.
Integrating spoken instructions into flight trajectory prediction to optimize automation in air traffic control
The booming air transportation industry inevitably burdens air traffic controllers' workload, causing unexpected human factor-related incidents.
NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering
Multi-view shape reconstruction has achieved impressive progresses thanks to the latest advances in neural implicit surface rendering.
Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?
The use of pretrained embeddings has become widespread in modern e-commerce machine learning (ML) systems.
ADCNet: Learning from Raw Radar Data via Distillation
As autonomous vehicles and advanced driving assistance systems have entered wider deployment, there is an increased interest in building robust perception systems using radars.
NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-view Images
In particular, NeAT represents the 3D surface as a level set of a signed distance function (SDF) with a validity branch for estimating the surface existence probability at the query positions.
Decoupling Skill Learning from Robotic Control for Generalizable Object Manipulation
Our experiments on manipulating complex articulated objects show that the proposed approach is more generalizable to unseen objects with large intra-class variations, outperforming previous approaches.
Dual Personalization on Federated Recommendation
Moreover, we provide visualizations and in-depth analysis of the personalization techniques in item embedding, which shed novel insights on the design of recommender systems in federated settings.
How to Share: Balancing Layer and Chain Sharing in Industrial Microservice Deployment
However, due to the limited resources of edge servers, it is difficult to meet the optimization goals of the two methods at the same time.
Text2Struct: A Machine Learning Pipeline for Mining Structured Data from Text
However, an annotation scheme and a training dataset have not been available for training machine learning models to mine structured data from text without special templates and patterns.
Distributionally Robust Day-ahead Scheduling for Power-traffic Network under a Potential Game Framework
In order to ensure the individual optimality of the two networks in a unified framework in day-ahead power scheduling, a two-stage distributionally robust centralized optimization model is established to carry out the equilibrium of power-transportation coupled network.
OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds
In this paper, we study the problem of 3D object segmentation from raw point clouds.
Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images
We firstly introduce four complexity factors to quantitatively measure the distributions of object- and scene-level biases in appearance and geometry for datasets with human annotations.
DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views.
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.
Reconfigurable Intelligent Computational Surfaces: When Wave Propagation Control Meets Computing
The envisioned sixth-generation (6G) of wireless networks will involve an intelligent integration of communications and computing, thereby meeting the urgent demands of diverse applications.
Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach
The learning problem is framed as a subset selection task in which a subset of all possible rules needs to be selected to form an accurate and interpretable rule set.
Driving in Real Life with Inverse Reinforcement Learning
In this paper, we introduce the first learning-based planner to drive a car in dense, urban traffic using Inverse Reinforcement Learning (IRL).
3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies
The key to our method is the introduction of a new sign, the NULL sign, in addition to the conventional in and out labels.
GR-GAN: Gradual Refinement Text-to-image Generation
We also introduce a new metric Cross-Model Distance (CMD) for simultaneously evaluating image quality and image-text consistency.
RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
Stochastic Gradient-based Fast Distributed Multi-Energy Management for an Industrial Park with Temporally-Coupled Constraints
Contemporary industrial parks are challenged by the growing concerns about high cost and low efficiency of energy supply.
Multi-scale Context-aware Network with Transformer for Gait Recognition
Although gait recognition has drawn increasing research attention recently, since the silhouette differences are quite subtle in spatial domain, temporal feature representation is crucial for gait recognition.
Ranked #3 on
Gait Recognition
on OUMVLP
3D microstructural generation from 2D images of cement paste using generative adversarial networks
Establishing a realistic three-dimensional (3D) microstructure is a crucial step for studying microstructure development of hardened cement pastes.
Stack operation of tensor networks
The tensor network, as a facterization of tensors, aims at performing the operations that are common for normal tensors, such as addition, contraction and stacking.
On the Advances and Challenges of Adaptive Online Testing
In recent years, the interest in developing adaptive solutions for online testing has grown significantly in the industry.
Asynchronous Decentralized Federated Learning for Collaborative Fault Diagnosis of PV Stations
Therefore, federated learning can be exploited to train a collaborative fault diagnosis model.
Towards Robust Off-policy Learning for Runtime Uncertainty
Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment.
Energy Management Based on Multi-Agent Deep Reinforcement Learning for A Multi-Energy Industrial Park
Owing to large industrial energy consumption, industrial production has brought a huge burden to the grid in terms of renewable energy access and power supply.
Sentiment-Aware Automatic Speech Recognition pre-training for enhanced Speech Emotion Recognition
We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more ``emotion aware''.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds
Each point in the dataset has been labelled with fine-grained semantic annotations, resulting in a dataset that is three times the size of the previous existing largest photogrammetric point cloud dataset.
A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection
In particular, BPGR can also provide easy-to-understand insights for reasoning results to show interpretability.
CDRec: Cayley-Dickson Recommender
In this paper, we propose a recommendation framework named Cayley-Dickson Recommender.
Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
Based on that, we also designed a neural network that depends on the graph attention mechanism. Specifically, we introduced the syntactic structural of the basic block, i. e., its corresponding AST, in source code model to provide sufficient information and fill the gap.
A Survey on Neural-symbolic Learning Systems
In recent years, neural systems have demonstrated highly effective learning ability and superior perception intelligence.
Speech recognition for air traffic control via feature learning and end-to-end training
In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Comparative Study of Speaker Role Identification in Air Traffic Communication Using Deep Learning Approaches
Most importantly, a multi-modal speaker role identification network (MMSRINet) is designed to achieve the SRI task by considering both the speech and textual modality features.
OctField: Hierarchical Implicit Functions for 3D Modeling
We achieve this goal by introducing a hierarchical octree structure to adaptively subdivide the 3D space according to the surface occupancy and the richness of part geometry.
How to Leverage Multimodal EHR Data for Better Medical Predictions?
Therefore, in this paper, we first extract the accompanying clinical notes from EHR and propose a method to integrate these data, we also comprehensively study the different models and the data leverage methods for better medical task prediction.
Fast Distributed Stochastic Scheduling for A Multi-Energy Industrial Park
To solve the issue, the energy management problem is constructed as a stochastic optimization problem.
A Robust and Efficient Multi-Scale Seasonal-Trend Decomposition
Many real-world time series exhibit multiple seasonality with different lengths.
Spectrum Learning-Aided Reconfigurable Intelligent Surfaces for 'Green' 6G Networks
In the sixth-generation (6G) era, emerging large-scale computing based applications (for example processing enormous amounts of images in real-time in autonomous driving) tend to lead to excessive energy consumption for the end users, whose devices are usually energy-constrained.
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
We study the problem of efficient semantic segmentation of large-scale 3D point clouds.
Distributed Urban Freeway Traffic Optimization Considering Congestion Propagation
Most exiting works develop traffic optimization strategies depending on the local traffic states of congested road segments, where the congestion propagation is neglected.
Effect of Adaptive and Fixed Shared Steering Control on Distracted Driver Behavior
Evaluation results indicated that, for both attentive and distracted drivers, haptic guidance with adaptive authority yielded lower driver workload and reduced lane departure risk than manual driving and fixed authority.
A Joint Energy and Latency Framework for Transfer Learning over 5G Industrial Edge Networks
In this paper, we propose a transfer learning (TL)-enabled edge-CNN framework for 5G industrial edge networks with privacy-preserving characteristic.
NeuSE: A Neural Snapshot Ensemble Method for Collaborative Filtering
In collaborative filtering (CF) algorithms, the optimal models are usually learned by globally minimizing the empirical risks averaged over all the observed data.
Hyperbolic Neural Collaborative Recommender
In the second phase, we develop a deep framework based on hyperbolic geometry to integrate constructed neighbor sets into recommendation.
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Labelling point clouds fully is highly time-consuming and costly.
Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks
Besides the integration of top-down and bottom-up networks, unlike existing pose discriminators that are designed solely for single person, and consequently cannot assess natural inter-person interactions, we propose a two-person pose discriminator that enforces natural two-person interactions.
3D Multi-Person Pose Estimation (absolute)
3D Multi-Person Pose Estimation (root-relative)
+2
RadarLoc: Learning to Relocalize in FMCW Radar
There is considerable work in the field of deep camera relocalization, which directly estimates poses from raw images.
Intelligent Spectrum Learning for Wireless Networks with Reconfigurable Intelligent Surfaces
Reconfigurable intelligent surface (RIS) has become a promising technology for enhancing the reliability of wireless communications, which is capable of reflecting the desired signals through appropriate phase shifts.
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems
Finally, by integrating the SRL with ASR, an end-to-end multilingual ASR framework is formulated in a supervised manner, which is able to translate the raw wave into text in one model, i. e., wave-to-text.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Improving speech recognition models with small samples for air traffic control systems
By virtue of the common terminology used in the ATC domain, the transfer learning task can be regarded as a sub-domain adaption task, in which the transferred model is optimized using a joint corpus consisting of baseline samples and new transcribed samples from the target dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
D2A: A Dataset Built for AI-Based Vulnerability Detection Methods Using Differential Analysis
However, existing datasets to train models for vulnerability identification suffer from multiple limitations such as limited bug context, limited size, and synthetic and unrealistic source code.
HSR: Hyperbolic Social Recommender
With the prevalence of online social media, users' social connections have been widely studied and utilized to enhance the performance of recommender systems.
Contrastive Unsupervised Learning for Speech Emotion Recognition
Speech emotion recognition (SER) is a key technology to enable more natural human-machine communication.
Ranked #4 on
Speech Emotion Recognition
on MSP-Podcast (Dominance)
(using extra training data)
DEFT: Distilling Entangled Factors by Preventing Information Diffusion
Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning.
STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?
Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography.
Adversarial example generation with AdaBelief Optimizer and Crop Invariance
ABI-FGM and CIM can be readily integrated to build a strong gradient-based attack to further boost the success rates of adversarial examples for black-box attacks.
OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details.
Testing Scalable Bell Inequalities for Quantum Graph States on IBM Quantum Devices
We are able to show violations of the inequalities on various graph states by constructing low-depth quantum circuits producing them, and by applying the readout error mitigation technique.
Quantum Physics
Random Transformation of Image Brightness for Adversarial Attack
Before deep neural networks are deployed, adversarial attacks can thus be an important method to evaluate and select robust models in safety-critical applications.
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos
To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters.
Ranked #1 on
Root Joint Localization
on Human3.6M
3D Absolute Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+5
Finding Second-Order Stationary Points Efficiently in Smooth Nonconvex Linearly Constrained Optimization Problems
To the best of our knowledge, this is the first time that first-order algorithms with polynomial per-iteration complexity and global sublinear rate are designed to find SOSPs of the important class of non-convex problems with linear constraints (almost surely).
Curvature Regularization to Prevent Distortion in Graph Embedding
Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space.
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction.
Ranked #2 on
Point Cloud Registration
on ETH (trained on 3DMatch)
Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System
By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle.
Learning Personalized Discretionary Lane-Change Initiation for Fully Autonomous Driving Based on Reinforcement Learning
In this article, the authors present a novel method to learn the personalized tactic of discretionary lane-change initiation for fully autonomous vehicles through human-computer interactions.
Optimising Stochastic Routing for Taxi Fleets with Model Enhanced Reinforcement Learning
The future of mobility-as-a-Service (Maas)should embrace an integrated system of ride-hailing, street-hailing and ride-sharing with optimised intelligent vehicle routing in response to a real-time, stochastic demand pattern.
Towards Scalable Distributed Training of Deep Learning on Public Cloud Clusters
Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters.
Learning to Reconstruct and Segment 3D Objects
To endow machines with the ability to perceive the real-world in a three dimensional representation as we do as humans is a fundamental and long-standing topic in Artificial Intelligence.
Multi-Scale Networks for 3D Human Pose Estimation with Inference Stage Optimization
Addressing these problems, we introduce a spatio-temporal network for robust 3D human pose estimation.
GRF: Learning a General Radiance Field for 3D Representation and Rendering
We present a simple yet powerful neural network that implicitly represents and renders 3D objects and scenes only from 2D observations.
GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering
The function models 3D scenes as a general radiance field, which takes a set of 2D images with camera poses and intrinsics as input, constructs an internal representation for each 3D point of the scene, and renders the corresponding appearance and geometry of any 3D point viewing from an arbitrary angle.
Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges
An essential prerequisite for unleashing the potential of supervised deep learning algorithms in the area of 3D scene understanding is the availability of large-scale and richly annotated datasets.
Offloading Optimization in Edge Computing for Deep Learning Enabled Target Tracking by Internet-of-UAVs
This motivates us to consider offloading this type of deep learning (DL) tasks to a mobile edge computing (MEC) server due to limited computational resource and energy budget of the UAV, and further improve the inference accuracy.
Computation Offloading in Multi-Access Edge Computing Networks: A Multi-Task Learning Approach
Multi-access edge computing (MEC) has already shown the potential in enabling mobile devices to bear the computation-intensive applications by offloading some tasks to a nearby access point (AP) integrated with a MEC server (MES).
Lessons Learned from Accident of Autonomous Vehicle Testing: An Edge Learning-aided Offloading Framework
This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint.
Joint Optimization of the Deployment and Resource Allocation of UAVs in Vehicular Edge Computing and Networks
With the development of smart vehicles, computing-intensive tasks are widely and rapidly generated.
A Novel Graphic Bending Transformation on Benchmark
Classical benchmark problems utilize multiple transformation techniques to increase optimization difficulty, e. g., shift for anti centering effect and rotation for anti dimension sensitivity.
3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years.
Ranked #3 on
3D Human Pose Estimation
on HumanEva-I
GRATE: Granular Recovery of Aggregated Tensor Data by Example
In this paper, we address the challenge of recovering an accurate breakdown of aggregated tensor data using disaggregation examples.
PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization
In this paper, we present a novel end-to-end learning-based LiDAR relocalization framework, termed PointLoc, which infers 6-DoF poses directly using only a single point cloud as input, without requiring a pre-built map.
Robotics
Geom-GCN: Geometric Graph Convolutional Networks
From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses.
Node Classification on Non-Homophilic (Heterophilic) Graphs
Representation Learning
+1
A Block-based Generative Model for Attributed Networks Embedding
To preserve the attribute information, we assume that each node has a hidden embedding related to its assigned block.
ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment
To our best knowledge, this is the first work that aims at building a real and multilingual ASR corpus for the air traffic related research.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
We study the problem of efficient semantic segmentation for large-scale 3D point clouds.
Ranked #2 on
3D Semantic Segmentation
on Toronto-3D
DeepPCO: End-to-End Point Cloud Odometry through Deep Parallel Neural Network
There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images.
SNAP: Finding Approximate Second-Order Stationary Solutions Efficiently for Non-convex Linearly Constrained Problems
This paper proposes low-complexity algorithms for finding approximate second-order stationary points (SOSPs) of problems with smooth non-convex objective and linear constraints.
Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
The framework directly regresses 3D bounding boxes for all instances in a point cloud, while simultaneously predicting a point-level mask for each instance.
Ranked #14 on
3D Instance Segmentation
on S3DIS
(mPrec metric)
Deep Bayesian Optimization on Attributed Graphs
Attributed graphs, which contain rich contextual features beyond just network structure, are ubiquitous and have been observed to benefit various network analytics applications.
Deep Neural Architecture Search with Deep Graph Bayesian Optimization
Based on the new surrogate, we then develop a graph Bayesian optimization framework to address the challenging task of deep neural architecture search.
Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
Although we can benefit a lot from DA, designing appropriate DA policies requires a lot of expert experience and time consumption, and the evaluation of searching the optimal policies is costly.
Energy Storage Management via Deep Q-Networks
Energy storage devices represent environmentally friendly candidates to cope with volatile renewable energy generation.
Learning Nonlinear Mixtures: Identifiability and Algorithm
Linear mixture models have proven very useful in a plethora of applications, e. g., topic modeling, clustering, and source separation.
Enhanced Network Embedding with Text Information
TENE learns the representations of nodes under the guidance of both proximity matrix which captures the network structure and text cluster membership matrix derived from clustering for text information.
Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network
Traffic prediction is a fundamental and vital task in Intelligence Transportation System (ITS), but it is very challenging to get high accuracy while containing low computational complexity due to the spatiotemporal characteristics of traffic flow, especially under the metropolitan circumstances.
Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction
However, GRU based approaches are unable to consistently estimate 3D shapes given different permutations of the same set of input images as the recurrent unit is permutation variant.
Ranked #1 on
3D Reconstruction
on Data3D−R2N2
A Pseudo Label based Dataless Naive Bayes Algorithm for Text Classification with Seed Words
We empirically show that PL-DNB outperforms traditional dataless text classification algorithms with seed words.
Graph Bayesian Optimization: Algorithms, Evaluations and Applications
Network structure optimization is a fundamental task in complex network analysis.
3D-PhysNet: Learning the Intuitive Physics of Non-Rigid Object Deformations
This is further confounded by the fact that shape information about encountered objects in the real world is often impaired by occlusions, noise and missing regions e. g. a robot manipulating an object will only be able to observe a partial view of the entire solid.
Defo-Net: Learning Body Deformation using Generative Adversarial Networks
Modelling the physical properties of everyday objects is a fundamental prerequisite for autonomous robots.
Robotics
Dense 3D Object Reconstruction from a Single Depth View
Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the object as input, and is able to generate the complete 3D occupancy grid with a high resolution of 256^3 by recovering the occluded/missing regions.
Group Sparse Bayesian Learning for Active Surveillance on Epidemic Dynamics
To address the challenge, we study the problem of active surveillance, i. e., how to identify a small portion of system components as sentinels to effect monitoring, such that the epidemic dynamics of an entire system can be readily predicted from the partial data collected by such sentinels.
3D Object Reconstruction from a Single Depth View with Adversarial Learning
In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.
Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
To recover the `clustering-friendly' latent representations and to better cluster the data, we propose a joint DR and K-means clustering approach in which DR is accomplished via learning a deep neural network (DNN).
Robust Volume Minimization-Based Matrix Factorization for Remote Sensing and Document Clustering
This paper considers \emph{volume minimization} (VolMin)-based structured matrix factorization (SMF).
Learning From Hidden Traits: Joint Factor Analysis and Latent Clustering
Dimensionality reduction is usually performed in a preprocessing stage that is separate from subsequent data analysis, such as clustering or classification.
