Search Results for author:
Found 258 papers, 84 papers with code
L-Eval: Instituting Standardized Evaluation for Long Context Language Models
Recently, there has been growing interest in extending the context length of large language models (LLMs), aiming to effectively process long inputs of one turn or conversations with more extensive histories.
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Despite the simplicity of our method, an IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fully fine-tuned image prompt model.
Ranked #3 on
Diffusion Personalization Tuning Free
on AgeDB
Dynamic SLAM: The Need For Speed
In this paper, we propose a new feature-based, model-free, object-aware dynamic SLAM algorithm that exploits semantic segmentation to allow estimation of motion of rigid objects in a scene without the need to estimate the object poses or have any prior knowledge of their 3D models.
Robotics
VDO-SLAM: A Visual Dynamic Object-aware SLAM System
Combining Simultaneous Localisation and Mapping (SLAM) estimation and dynamic scene modelling can highly benefit robot autonomy in dynamic environments.
Robotics
Robust Ego and Object 6-DoF Motion Estimation and Tracking
The problem of tracking self-motion as well as motion of objects in the scene using information from a camera is known as multi-body visual odometry and is a challenging task.
BMInf: An Efficient Toolkit for Big Model Inference and Tuning
In recent years, large-scale pre-trained language models (PLMs) containing billions of parameters have achieved promising results on various NLP tasks.
Generalized Predictive Model for Autonomous Driving
In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline.
Sparse Mixture-of-Experts are Domain Generalizable Learners
It is motivated by an empirical finding that transformer-based models trained with empirical risk minimization (ERM) outperform CNN-based models employing state-of-the-art (SOTA) DG algorithms on multiple DG datasets.
Ranked #11 on
Domain Generalization
on DomainNet
(using extra training data)
Hybrid Beamforming for Millimeter Wave Systems Using the MMSE Criterion
A particular innovation in our proposed alternating minimization algorithms is a carefully designed initialization method, which leads to faster convergence.
Information Theory Information Theory
Training-Free Long-Context Scaling of Large Language Models
The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length.
PARAGEN : A Parallel Generation Toolkit
PARAGEN is a PyTorch-based NLP toolkit for further development on parallel generation.
IDRLnet: A Physics-Informed Neural Network Library
Physics Informed Neural Network (PINN) is a scientific computing framework used to solve both forward and inverse problems modeled by Partial Differential Equations (PDEs).
Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach
To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based methods utilize a feature encoder to transform the image and then implement the SR image generation in a compact latent space.
NTU4DRadLM: 4D Radar-centric Multi-Modal Dataset for Localization and Mapping
5) Considered both middle- and large- scale outdoor environments, i. e., the 6 trajectories range from 246m to 6. 95km.
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance.
Client-Edge-Cloud Hierarchical Federated Learning
To combine their advantages, we propose a client-edge-cloud hierarchical Federated Learning system, supported with a HierFAVG algorithm that allows multiple edge servers to perform partial model aggregation.
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
This approach is characterized by a two-stage process: drafting and verification.
A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning
With the development of convolutional neural networks, hundreds of deep learning based dehazing methods have been proposed.
Graph Neural Networks for Wireless Communications: From Theory to Practice
For design guidelines, we propose a unified framework that is applicable to general design problems in wireless networks, which includes graph modeling, neural architecture design, and theory-guided performance enhancement.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Machine Learning Based Cyber Attacks Targeting on Controlled Information: A Survey
Stealing attack against controlled information, along with the increasing number of information leakage incidents, has become an emerging cyber security threat in recent years.
Generalized Relation Modeling for Transformer Tracking
Compared with previous two-stream trackers, the recent one-stream tracking pipeline, which allows earlier interaction between the template and search region, has achieved a remarkable performance gain.
Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
Secondly, a BERT with locality-constrained attention is proposed to obtain representations of descriptions at different scales.
Ranked #15 on
Text based Person Retrieval
on CUHK-PEDES
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.
Ranked #4 on
Person Re-Identification
on PRCC
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.
Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
In this paper, we propose to apply graph neural networks (GNNs) to solve large-scale radio resource management problems, supported by effective neural network architecture design and theoretical analysis.
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration
Deformable image registration is a fundamental task in medical image analysis, aiming to establish a dense and non-linear correspondence between a pair of images.
Group-Buying Recommendation for Social E-Commerce
Group-buying recommendation for social e-commerce, which recommends an item list when users want to launch a group, plays an important role in the group success ratio and sales.
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
Extensive experiments evidence that the proposed task-oriented communication system achieves a better rate-distortion tradeoff than baseline methods and significantly reduces the feature transmission latency in dynamic channel conditions.
BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems
By exploiting the strong sparsity and the fault-tolerant property of the intermediate feature in a deep neural network (DNN), BottleNet++ achieves a much higher compression ratio than existing methods.
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
How Powerful is Graph Convolution for Recommendation?
In this paper, we endeavor to obtain a better understanding of GCN-based CF methods via the lens of graph signal processing.
Ranked #5 on
Collaborative Filtering
on Gowalla
Hybrid Far- and Near-Field Channel Estimation for THz Ultra-Massive MIMO via Fixed Point Networks
We draw inspirations from fixed point theory to develop an efficient deep learning based channel estimator with adaptive complexity and linear convergence guarantee.
An Adaptive and Robust Deep Learning Framework for THz Ultra-Massive MIMO Channel Estimation
For practical usage, the proposed framework is further extended to wideband THz UM-MIMO systems with beam squint effect.
Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression
We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation.
DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep Learning
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field.
Low-complexity Deep Video Compression with A Distributed Coding Architecture
This has inspired a distributed coding architecture aiming at reducing the encoding complexity.
How many infections of COVID-19 there will be in the "Diamond Princess"-Predicted by a virus transmission model based on the simulation of crowd flow
Objectives: Simulate the transmission process of COVID-19 in a cruise ship, and then to judge how many infections there will be in the 3711 people in the "Diamond Princess" and analyze measures that could have prevented mass transmission.
Physics and Society Computers and Society
Deep Denoising Neural Network Assisted Compressive Channel Estimation for mmWave Intelligent Reflecting Surfaces
Integrating large intelligent reflecting surfaces (IRS) into millimeter-wave (mmWave) massive multi-input-multi-ouput (MIMO) has been a promising approach for improved coverage and throughput.
CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling
In this paper, we propose Comprehensive Attention Benchmark (CAB) under a fine-grained attention taxonomy with four distinguishable attention patterns, namely, noncausal self, causal self, noncausal cross, and causal cross attentions.
A Graph Neural Network Approach for Scalable Wireless Power Control
Specifically, a $K$-user interference channel is first modeled as a complete graph, where the quantitative information of wireless channels is incorporated as the features of the graph.
LDMIC: Learning-based Distributed Multi-view Image Coding
Multi-view image compression plays a critical role in 3D-related applications.
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.
Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction
Data-driven predictive methods which can efficiently and accurately transform protein sequences into biologically active structures are highly valuable for scientific research and medical development.
Stargazer: A transformer-based driver action detection system for intelligent transportation
Distracted driver actions can be dangerous and cause severe accidents.
Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification
In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution.
Light Field Saliency Detection with Deep Convolutional Networks
Light field imaging presents an attractive alternative to RGB imaging because of the recording of the direction of the incoming light.
Branchy-GNN: a Device-Edge Co-Inference Framework for Efficient Point Cloud Processing
The recent advancements of three-dimensional (3D) data acquisition devices have spurred a new breed of applications that rely on point cloud data processing.
Distributed, Parallel, and Cluster Computing
Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query
However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.
Hyperspectral Image Super Resolution with Real Unaligned RGB Guidance
The features of RGB reference images are then processed by a multi-stage alignment module to explicitly align the features of RGB reference with the LR HSI.
Communication-Computation Trade-Off in Resource-Constrained Edge Inference
The recent breakthrough in artificial intelligence (AI), especially deep neural networks (DNNs), has affected every branch of science and technology.
Task-Oriented Communication for Multi-Device Cooperative Edge Inference
To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i. e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server.
Multi-dataset Training of Transformers for Robust Action Recognition
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition.
Task-Oriented Communication for Edge Video Analytics
With the development of artificial intelligence (AI) techniques and the increasing popularity of camera-equipped devices, many edge video analytics applications are emerging, calling for the deployment of computation-intensive AI models at the network edge.
GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering
To train the GATCluster in a completely unsupervised manner, we design four self-learning tasks with the constraints of transformation invariance, separability maximization, entropy analysis, and attention mapping.
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage.
EPI-based Oriented Relation Networks for Light Field Depth Estimation
Based on the observation that an oriented line and its neighboring pixels in an EPI share a similar linear structure, we propose an end-to-end fully convolutional network (FCN) to estimate the depth value of the intersection point on the horizontal and vertical EPIs.
Accelerating Physics-Informed Neural Network Training with Prior Dictionaries
Physics-Informed Neural Networks (PINNs) can be regarded as general-purpose PDE solvers, but it might be slow to train PINNs on particular problems, and there is no theoretical guarantee of corresponding error bounds.
Context-aware Communication for Multi-agent Reinforcement Learning
Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers.
Boosting Neural Representations for Videos with a Conditional Decoder
Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks.
Complete Dictionary Learning via $\ell_p$-norm Maximization
Dictionary learning is a classic representation learning method that has been widely applied in signal processing and data analytics.
Selective Knowledge Sharing for Privacy-Preserving Federated Distillation without A Good Teacher
While federated learning is promising for privacy-preserving collaborative learning without revealing local data, it remains vulnerable to white-box attacks and struggles to adapt to heterogeneous clients.
Urban Generative Intelligence (UGI): A Foundational Platform for Agents in Embodied City Environment
Urban environments, characterized by their complex, multi-layered networks encompassing physical, social, economic, and environmental dimensions, face significant challenges in the face of rapid urbanization.
Evaluation of a Canonical Image Representation for Sidescan Sonar
In this paper, a canonical transformation method consisting of intensity correction and slant range correction is proposed to decrease the above distortion.
FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data
This enables client models to be updated in a shared feature space with consistent classifiers during local training.
Message Passing Meets Graph Neural Networks: A New Paradigm for Massive MIMO Systems
As one of the core technologies for 5G systems, massive multiple-input multiple-output (MIMO) introduces dramatic capacity improvements along with very high beamforming and spatial multiplexing gains.
A Deep Neural Network Surrogate Modeling Benchmark for Temperature Field Prediction of Heat Source Layout
Thermal issue is of great importance during layout design of heat source components in systems engineering, especially for high functional-density products.
Efficient reinforcement learning control for continuum robots based on Inexplicit Prior Knowledge
Moreover, recent reinforcement learning methods are data-inefficient and can not be directly deployed to the robot without simulation.
MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates
Federated learning (FL) is a promising framework for privacy-preserving collaborative learning, where model training tasks are distributed to clients and only the model updates need to be collected at a server.
DeepIlluminance: Contextual Illuminance Estimation via Deep Neural Networks
First, the contextual net with a center-surround architecture extracts local contextual features from image patches, and generates initial illuminant estimates and the corresponding color corrected patches.
Decentralized Statistical Inference with Unrolled Graph Neural Networks
In this paper, we investigate the decentralized statistical inference problem, where a network of agents cooperatively recover a (structured) vector from private noisy samples without centralized coordination.
Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction
To solve this problem, this work develops a novel physics-informed deep reversible regression models for temperature field reconstruction of heat-source systems (TFR-HSS), which can better reconstruct the temperature field with limited monitoring points unsupervisedly.
Deep Adaptive Arbitrary Polynomial Chaos Expansion: A Mini-data-driven Semi-supervised Method for Uncertainty Quantification
Based on the adaptive aPC, a semi-supervised deep adaptive arbitrary polynomial chaos expansion (Deep aPCE) method is proposed to reduce the training data cost and improve the surrogate model accuracy.
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals
Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation.
$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection
For a task with $k$ training labels, $k$Folden induces $k$ sub-models, each of which is trained on a subset with $k-1$ categories with the left category masked unknown to the sub-model.
Task-Oriented Communication with Out-of-Distribution Detection: An Information Bottleneck Framework
Task-oriented communication is an emerging paradigm for next-generation communication networks, which extracts and transmits task-relevant information, instead of raw data, for downstream applications.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
We achieve a biomedical multilingual corpus by incorporating three granularity knowledge alignments (entity, fact, and passage levels) into monolingual corpora.
A Self-adaptive Neuroevolution Approach to Constructing Deep Neural Network Architectures Across Different Types
One of the key settings in SANE is the search space defined by cells and organs self-adapted to different DNN types.
Sluggish and Chemically-Biased Interstitial Diffusion in Concentrated Solid Solution Alloys: Mechanisms and Methods
Interstitial diffusion is a pivotal process that governs the phase stability and irradiation response of materials in non-equilibrium conditions.
iEnhancer-ELM: improve enhancer identification by extracting position-related multiscale contextual information based on enhancer language models
Although many feature extraction methods have been proposed to improve the performance of enhancer identification, they cannot learn position-related multiscale contextual information from raw DNA sequences.
Attentive Multi-Layer Perceptron for Non-autoregressive Generation
Furthermore, we marry AMLP with popular NAR models, deriving a highly efficient NAR-AMLP architecture with linear time and space complexity.
Deep Nearest Class Mean Model for Incremental Odor Classification
That is, the odor datasets are dynamically growing while both training samples and number of classes are increasing over time.
Deep Learning for identifying radiogenomic associations in breast cancer
Results: The best AUC performance for distinguishing molecular subtypes was 0. 65 (95% CI:[0. 57, 0. 71]) and was achieved by the off-the-shelf deep features approach.
Deep learning analysis of breast MRIs for prediction of occult invasive disease in ductal carcinoma in situ
In the first approach, we adopted the transfer learning strategy, in which a network pre-trained on a large dataset of natural images is fine-tuned with our DCIS images.
When Point Process Meets RNNs: Predicting Fine-Grained User Interests with Mutual Behavioral Infectivity
Inspired by point process in modeling temporal point process, in this paper we present a deep prediction method based on two recurrent neural networks (RNNs) to jointly model each user's continuous browsing history and asynchronous event sequences in the context of inter-user behavioral mutual infectivity.
High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
After the ResNet was trained, it was applied to reconstruct the T2 mapping from simulation and in vivo human brain data.
Forest understory trees can be segmented accurately within sufficiently dense airborne laser scanning point clouds
Existing segmentation procedures typically detect more than 90% of overstory trees, yet they barely detect 60% of understory trees because of the occlusion effect of higher canopy layers.
Vertical stratification of forest canopy for segmentation of under-story trees within small-footprint airborne LiDAR point clouds
This paper presents a tree segmentation approach for multi-story stands that stratifies the point cloud to canopy layers and segments individual tree crowns within each layer using a digital surface model based tree segmentation method.
Power Data Classification: A Hybrid of a Novel Local Time Warping and LSTM
Finally, using the power consumption data from a real data center, we show that the proposed LTW can improve the classification accuracy of DTW from about 84% to 90%.
Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model
The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding.
Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time.
Deep LSTM for Large Vocabulary Continuous Speech Recognition
It is a competitive framework that LSTM models of more than 7 layers are successfully trained on Shenma voice search data in Mandarin and they outperform the deep LSTM models trained by conventional approach.
Exponential Moving Average Model in Parallel Speech Recognition Training
As training data rapid growth, large-scale parallel training with multi-GPUs cluster is widely applied in the neural network model learning currently. We present a new approach that applies exponential moving average method in large-scale parallel training of neural network model.
A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data
This paper presents a non-parametric approach for segmenting trees from airborne LiDAR data in deciduous forests.
Agglomerative clustering and collectiveness measure via exponent generating function
A novel agglomerative clustering method is proposed by utilizing the path integral to define the affinity measure.
Implementation of Training Convolutional Neural Networks
Deep learning refers to the shining branch of machine learning that is based on learning levels of representations.
Performance Analysis on Evolutionary Algorithms for the Minimum Label Spanning Tree Problem
We also show that GSEMO achieves a $(2ln(n))$-approximation ratio for the MLST problem in expected polynomial time of $n$ and $k$.
Real-Time Traffic Signal Control for Modern Roundabouts by Using Particle Swarm Optimization-Based Fuzzy Controller
This mechanism helps to instantly respond to the current traffic condition of the roundabout so as to improve real-timeness.
Automatic deep learning-based normalization of breast dynamic contrast-enhanced magnetic resonance images
Then, based on the segmentation results, a subject-specific piecewise linear mapping function was applied between the anchor points to normalize the same type of tissue in different patients into the same intensity ranges.
Dynamic Computation Offloading for Mobile-Edge Computing with Energy Harvesting Devices
Sample simulation results shall be presented to verify the theoretical analysis as well as validate the effectiveness of the proposed algorithm.
Information Theory Information Theory
Towards an Intelligent Edge: Wireless Communication Meets Machine Learning
Accordingly, a new research area, called edge learning, emerges, which crosses and revolutionizes two disciplines: wireless communication and machine learning.
Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission
To solve the problem, a new retransmission protocol called data-importance aware automatic-repeat-request (importance ARQ) is proposed.
LORM: Learning to Optimize for Resource Management in Wireless Networks with Few Training Samples
To further address the task mismatch problem, we develop a transfer learning method via self-imitation in LORM, named LORM-TL, which can quickly adapt a pre-trained machine learning model to the new task with only a few additional unlabeled training samples.
Session-level Language Modeling for Conversational Speech
We propose to generalize language models for conversational speech recognition to allow them to operate across utterance boundaries and speaker changes, thereby capturing conversation-level phenomena such as adjacency pairs, lexical entrainment, and topical coherence.
On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of Constructions
We explore a generic definition of RKBS and the reproducing kernel for RKBS that is independent of construction.
Topological Persistence in Geometry and Analysis
The theory of persistence modules is an emerging field of algebraic topology which originated in topological data analysis.
Algebraic Topology Classical Analysis and ODEs Symplectic Geometry 55U99, 58Cxx, 53Dxx
The Roadmap to 6G -- AI Empowered Wireless Networks
The recent upsurge of diversified mobile applications, especially those supported by Artificial Intelligence (AI), is spurring heated discussions on the future evolution of wireless communications.
Transfer Learning for Mixed-Integer Resource Allocation Problems in Wireless Networks
A unique advantage of the proposed method is that it can tackle the task mismatch issue with a few additional unlabeled training samples, which is especially important when transferring to large-size problems.
Mobile Edge Intelligence and Computing for the Internet of Vehicles
The Internet of Vehicles (IoV) is an emerging paradigm, driven by recent advancements in vehicular communications and networking.
Networking and Internet Architecture Signal Processing
Learning Clustered Representation for Complex Free Energy Landscapes
In this paper we first analyzed the inductive bias underlying the data scattered across complex free energy landscapes (FEL), and exploited it to train deep neural networks which yield reduced and clustered representation for the FEL.
Restricted Linearized Augmented Lagrangian Method for Euler's Elastica Model
In this paper, a simple cutting-off strategy is introduced into the augmented Lagrangian based algorithms for minimizing the Euler's elastica energy, which leads to easy parameter tuning and fast convergence.
Non-imaging single-pixel sensing with optimized binary modulation
The conventional high-level sensing techniques require high-fidelity images as input to extract target features, which are produced by either complex imaging hardware or high-complexity reconstruction algorithms.
Multi-grained Attention Networks for Single Image Super-Resolution
In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts.
A Study of Data Pre-processing Techniques for Imbalanced Biomedical Data Classification
However, previous studies usually focused on different classifiers, and overlook the class imbalance problem in real-world biomedical datasets.
Advances in Online Audio-Visual Meeting Transcription
This increases marginally to 1. 6% when 50% of the attendees are unknown to the system.
Faster Activity and Data Detection in Massive Random Access: A Multi-armed Bandit Approach
In this paper, we develop multi-armed bandit approaches for more efficient detection via coordinate descent, which make a delicate trade-off between exploration and exploitation in coordinate selection.
Sparse Optimization for Green Edge AI Inference
By exploiting the inherent connections between the set of task selection and group sparsity structural transmit beamforming vector, we reformulate the optimization as a group sparse beamforming problem.
Communication-Efficient Edge AI: Algorithms and Systems
By pushing inference and training processes of AI models to edge nodes, edge AI has emerged as a promising alternative.
DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
Our diarization system includes multiple modules, namely voice activity detection (VAD), segmentation, speaker embedding extraction, similarity scoring, clustering, resegmentation and overlap detection.
Scene Text Recognition via Transformer
Different from previous transformer based models [56, 34], which just use the decoder of the transformer to decode the convolutional attention, the proposed method use a convolutional feature maps as word embedding input into transformer.
Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection
In contrast to existing works, the adversarial examples crafted by our method can also deceive recent machine learning based detectors that rely on semantic features such as control-flow-graph.
Cryptography and Security
A Perspective on Deep Learning for Molecular Modeling and Simulations
Deep learning is transforming many areas in science, and it has great potential in modeling molecular systems.
The Design and Construction of a Chinese Sarcasm Dataset
Thus, the detection and processing of sarcasm is important to social media analysis. However, most existing sarcasm dataset are in English and there is still a lack of authoritative Chinese sarcasm dataset.
Target-based Sentiment Annotation in Chinese Financial News
Based on high quality annotation guideline and effective quality control strategy, a corpus with 8, 314 target-level sentiment annotation is constructed on 6, 336 paragraphs from Chinese financial news text.
Zero-shot Text Classification via Reinforced Self-training
In this situation, transferring from seen classes to unseen classes is extremely hard.
TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems
We showed that the WGAN-based method was effective to preserve image texture.
Flow Field Reconstructions with GANs based on Radial Basis Functions
Motivated by the problems of existing approaches and inspired by the success of the generative adversarial networks (GANs) in the field of computer vision, we prove an optimal discriminator theorem that the optimal discriminator of a GAN is a radial basis function neural network (RBFNN) while dealing with nonlinear sparse FFD regression and generation.
Microscope Based HER2 Scoring System
Recently, artificial intelligence (AI) has been used in various disease diagnosis to improve diagnostic accuracy and reliability, but the interpretation of diagnosis results is still an open problem.
DeFuzz: Deep Learning Guided Directed Fuzzing
Fuzzing is one of the most effective technique to identify potential software vulnerabilities.
Deep Reinforcement Learning of Transition States
Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach (RL$^\ddag$) to automatically unravel chemical reaction mechanisms.
Improving RNN transducer with normalized jointer network
In this work, we analyze the cause of the huge gradient variance in RNN-T training and proposed a new \textit{normalized jointer network} to overcome it.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Dynamic latency speech recognition with asynchronous revision
In this work we propose an inference technique, asynchronous revision, to unify streaming and non-streaming speech recognition models.
Automated Big Traffic Analytics for Cyber Security
Network traffic analytics technology is a cornerstone for cyber security systems.
Cryptography and Security
Ultra-Fast Accurate AoA Estimation via Automotive Massive-MIMO Radar
Massive multiple-input multiple-output (MIMO) radar, enabled by millimeter-wave virtual MIMO techniques, provides great promises to the high-resolution automotive sensing and target detection in unmanned ground/aerial vehicles (UGA/UAV).
Blind Data Detection in Massive MIMO via $\ell_3$-norm Maximization over the Stiefel Manifold
Specifically, we propose a novel $\ell_3$-norm-based formulation to recover the data without channel estimation.
Efficient and fair trading algorithms in market design environments
We propose a new method to define trading algorithms in market design environments.
Cores in discrete exchange economies with complex endowments
The core is a traditional and useful solution concept in economic theory.
Hawking radiation from nonrotating singularity-free black holes in conformal gravity
Besides, we investigate the dependence of the greybody factor and the sparsity of Hawking radiation on the conformal parameters.
General Relativity and Quantum Cosmology
Exploiting Behavioral Consistence for Universal User Representation
In this work, we focus on developing universal user representation model.
Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales
Deep learning is changing many areas in molecular physics, and it has shown great potential to deliver new solutions to challenging molecular modeling problems.
Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design
Hierarchical FL, with a client-edge-cloud aggregation hierarchy, can effectively leverage both the cloud server's access to many clients' data and the edge servers' closeness to the clients to achieve a high communication efficiency.
Single-photon imaging over 200 km
Long-range active imaging has widespread applications in remote sensing and target recognition.
Constrained Pseudo-market Equilibrium
We propose a pseudo-market solution to resource allocation problems subject to constraints.
Large-scale phase retrieval
In computational phase imaging, phase retrieval (PR) is required to reconstruct both amplitude and phase in complex space from intensity-only measurements.
Affine-modeled video extraction from a single motion blurred image
Recovering these sharp video frames from a single blurred image is nontrivial, due to not only its strong ill-posedness, but also various types of complex motion in reality such as rotation and motion in depth.
Supporting More Active Users for Massive Access via Data-assisted Activity Detection
Massive machine-type communication (mMTC) has been regarded as one of the most important use scenarios in the fifth generation (5G) and beyond wireless networks, which demands scalable access for a large number of devices.
HMM-Free Encoder Pre-Training for Streaming RNN Transducer
This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model.
Semi-Decentralized Federated Edge Learning for Fast Convergence on Non-IID Data
Federated edge learning (FEEL) has emerged as an effective approach to reduce the large communication latency in Cloud-based machine learning solutions, while preserving data privacy.
Communication-Efficient Federated Learning with Dual-Side Low-Rank Compression
Federated learning (FL) is a promising and powerful approach for training deep learning models without sharing the raw data of clients.
Joint Activity Detection and Data Decoding in Massive Random Access via a Turbo Receiver
In this paper, we propose a turbo receiver for joint activity detection and data decoding in grant-free massive random access, which iterates between a detector and a belief propagation (BP)-based channel decoder.
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services.
Complex-domain super-resolution imaging with distributed optimization
Complex-domain imaging has emerged as a valuable technique for investigating weak-scattered samples.
Agile wide-field imaging with selective high resolution
In this work, we report an agile wide-field imaging framework with selective high resolution that requires only two detectors.
Invariant Information Bottleneck for Domain Generalization
IIB significantly outperforms IRM on synthetic datasets, where the pseudo-invariant features and geometric skews occur, showing the effectiveness of proposed formulation in overcoming failure modes of IRM.
Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
Recently, deep convolutional neural network methods have achieved an excellent performance in image superresolution (SR), but they can not be easily applied to embedded devices due to large memory cost.
Feedback Pyramid Attention Networks for Single Image Super-Resolution
Recently, convolutional neural network (CNN) based image super-resolution (SR) methods have achieved significant performance improvement.
Joint Activity Detection, Channel Estimation, and Data Decoding for Grant-free Massive Random Access
In particular, the common sparsity pattern in the received pilot and data signal has been ignored in most existing studies, and auxiliary information of channel decoding has not been utilized for user activity detection.
RBUE: A ReLU-Based Uncertainty Estimation Method of Deep Neural Networks
Deep Ensemble is widely considered the state-of-the-art method which can estimate the uncertainty with higher quality, but it is very expensive to train and test.
Primary-Auxiliary Model Scheduling Based Estimation of the Vertical Wheel Force in a Full Vehicle System
A real-world application to the estimation of the vertical wheel force in a full vehicle system are, respectively, conducted to demonstrate the effectiveness of the proposed method.
Neural Calibration for Scalable Beamforming in FDD Massive MIMO with Implicit Channel Estimation
Channel estimation and beamforming play critical roles in frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems.
Semantic Reinforced Attention Learning for Visual Place Recognition
(2) By exploiting the interpretability of the local weighting scheme, a semantic constrained initialization is proposed so that the local attention can be reinforced by semantic priors.
Image-free single-pixel segmentation
We envision that this image-free segmentation technique can be widely applied in various resource-limited platforms such as UAV and unmanned vehicle that require real-time sensing.
Communication-Computation Efficient Device-Edge Co-Inference via AutoML
Device-edge co-inference, which partitions a deep neural network between a resource-constrained mobile device and an edge server, recently emerges as a promising paradigm to support intelligent mobile applications.
Sk-Unet Model with Fourier Domain for Mitosis Detection
Mitotic count is the most important morphological feature of breast cancer grading.
Learn to Communicate with Neural Calibration: Scalability and Generalization
Furthermore, such networks will vary dynamically in a significant way, which makes it intractable to develop comprehensive analytical models.
Attentional Pyramid Pooling of Salient Visual Residuals for Place Recognition
The core of visual place recognition (VPR) lies in how to identify task-relevant visual cues and embed them into discriminative representations.
kFolden: k-Fold Ensemble for Out-Of-Distribution Detection
Out-of-Distribution (OOD) detection is an important problem in natural language processing (NLP).
From em-Projections to Variational Auto-Encoder
This paper reviews the em-projections in information geometry and the recent understanding of variational auto-encoder, and explains that they share a common formulation as joint minimization of the Kullback-Leibler divergence between two manifolds of probability distributions, and the joint minimization can be implemented by alternating projections or alternating gradient descent.
Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients
Federated edge learning (FEEL) has drawn much attention as a privacy-preserving distributed learning framework for mobile edge networks.
Semi-Decentralized Federated Edge Learning with Data and Device Heterogeneity
By exploiting the low-latency communication among edge servers for efficient model sharing, SD-FEEL can incorporate more training data, while enjoying much lower latency compared with conventional federated learning.
Weighted Encoding Optimization for Dynamic Single-pixel Imaging and Sensing
While the network is training at a high sampling rate, the modulation patterns and corresponding weights are updated iteratively, which produces optimal ranked encoding series when converged.
A Critical Analysis of Image-based Camera Pose Estimation Techniques
Camera, and associated with its objects within the field of view, localization could benefit many computer vision fields, such as autonomous driving, robot navigation, and augmented reality (AR).
Data-Driven Deep Learning Based Hybrid Beamforming for Aerial Massive MIMO-OFDM Systems with Implicit CSI
To this end, by modeling the key transmission modules as an end-to-end (E2E) neural network, this paper proposes a data-driven deep learning (DL)-based unified hybrid beamforming framework for both the time division duplex (TDD) and frequency division duplex (FDD) systems with implicit channel state information (CSI).
Stochastic Coded Federated Learning with Convergence and Privacy Guarantees
Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework, where many clients collaboratively train a machine learning model by exchanging model updates with a parameter server instead of sharing their raw data.
The Volcspeech system for the ICASSP 2022 multi-channel multi-party meeting transcription challenge
For Track 1, we propose several approaches to empower the clustering-based speaker diarization system to handle overlapped speech.
The Gene of Scientific Success
Under this consideration, our paper presents and analyzes the causal factors that are crucial for scholars' academic success.
AugHover-Net: Augmenting Hover-net for Nucleus Segmentation and Classification
Connective nuclei may look very different from each other while some of them share a similar shape with the epithelial ones.
Communication-Efficient Federated Distillation with Active Data Sampling
Federated Distillation (FD) is a recently proposed alternative to enable communication-efficient and robust FL, which achieves orders of magnitude reduction of the communication overhead compared with FedAvg and is flexible to handle heterogeneous models at the clients.
Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack
To evaluate the attack efficacy, we crafted heterogeneous security scenarios where the detectors were embedded with different levels of defense and the attackers' background knowledge of data varies.
Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images
In this paper, we propose a self-supervised learning framework for light field depth estimation.
Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting
Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models.
Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types
MC-TMB algorithm also exhibited good generalization on the external validation cohort with an AUC of 0. 732 (0. 683-0. 761), and better performance when compared to other methods.
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining
Large-scale vision-language pre-training has achieved promising results on downstream tasks.
Evolution as a Service: A Privacy-Preserving Genetic Algorithm for Combinatorial Optimization
Specifically, PEGA enables users outsourcing COPs to the cloud server holding a competitive GA and approximating the optimal solution in a privacy-preserving manner.
Federated Learning with GAN-based Data Synthesis for Non-IID Clients
A combination of the local private dataset and synthetic dataset with confident pseudo labels leads to nearly identical data distributions among clients, which improves the consistency among local models and benefits the global aggregation.
Resource-Constrained Edge AI with Early Exit Prediction
In this paper, we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.
A Manifold-based Airfoil Geometric-feature Extraction and Discrepant Data Fusion Learning Method
Geometrical shape of airfoils, together with the corresponding flight conditions, are crucial factors for aerodynamic performances prediction.
Hiding Your Signals: A Security Analysis of PPG-based Biometric Authentication
It reduces the success rate of rPPG spoofing attacks in user authentication to 0. 05.
PrivBayes： Private Data release via Bayesian networks
Given a dataset D, PRIVBAYES first constructs a Bayesian network N , which (i) provides a succinct model of the correlations among the attributes in D and (ii) allows us to approximate the distribution of data in D using a set P of lowdimensional marginals of D. After that, PRIVBAYES injects noise into each marginal in P to ensure differential privacy, and then uses the noisy marginals and the Bayesian network to construct an approximation of the data distribution in D. Finally, PRIVBAYES samples tuples from the approximate distribution to construct a synthetic dataset, and then releases the synthetic data.
Augmented Deep Unfolding for Downlink Beamforming in Multi-cell Massive MIMO With Limited Feedback
In limited feedback multi-user multiple-input multiple-output (MU-MIMO) cellular networks, users send quantized information about the channel conditions to the associated base station (BS) for downlink beamforming.
Text-Adaptive Multiple Visual Prototype Matching for Video-Text Retrieval
To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features.
DReS-FL: Dropout-Resilient Secure Federated Learning for Non-IID Clients via Secret Data Sharing
Federated learning (FL) strives to enable collaborative training of machine learning models without centrally collecting clients' private data.
Deep Latent Mixture Model for Recommendation
Recent advances in neural networks have been successfully applied to many tasks in online recommendation applications.
Stochastic Coded Federated Learning: Theoretical Analysis and Incentive Mechanism Design
During training, the server computes gradients on the global coded dataset to compensate for the missing model updates of the straggling devices.
Blind Performance Prediction for Deep Learning Based Ultra-Massive MIMO Channel Estimation
Reliability is of paramount importance for the physical layer of wireless systems due to its decisive impact on end-to-end performance.
Lightweight and Flexible Deep Equilibrium Learning for CSI Feedback in FDD Massive MIMO
In this paper, we propose a lightweight and flexible deep learning-based CSI feedback approach by capitalizing on deep equilibrium models.
Large-scale single-photon imaging
Benefiting from its single-photon sensitivity, single-photon avalanche diode (SPAD) array has been widely applied in various fields such as fluorescence lifetime imaging and quantum computing.
Machine Learning for Large-Scale Optimization in 6G Wireless Networks
The sixth generation (6G) wireless systems are envisioned to enable the paradigm shift from "connected things" to "connected intelligence", featured by ultra high density, large-scale, dynamic heterogeneity, diversified functional requirements and machine learning capabilities, which leads to a growing need for highly efficient intelligent algorithms.
