Search Results for author:
Found 101 papers, 36 papers with code
Building Sentiment Lexicons for Mainland Scandinavian Languages Using Machine Translation and Sentence Embeddings
This method benefits from the English Sentiwordnet and a thesaurus in one of the target languages.
LoopAnimate: Loopable Salient Object Animation
The proposed LoopAnimate, which for the first time extends the single-pass generation length of UNet-based video generation models to 35 frames while maintaining high-quality video generation.
Factor risk measures
In this paper, we introduce a double-argument mapping as a risk measure to assess the risk relative to a vector of factors, called factor risk measure.
AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement
Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool.
Hidden You Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Logic Chain Injection
This paper proposes a new type of jailbreak attacks which can deceive both the LLMs and human (i. e., security analyst).
Understanding Language Modeling Paradigm Adaptations in Recommender Systems: Lessons Learned and Open Challenges
The emergence of Large Language Models (LLMs) has achieved tremendous success in the field of Natural Language Processing owing to diverse training paradigms that empower LLMs to effectively capture intricate linguistic patterns and semantic representations.
Antinetwork among China A-shares
The correlation-based financial networks, constructed with the correlation relationships among the time series of fluctuations of daily logarithmic prices of stocks, are intensively studied.
Real-time Transformer-based Open-Vocabulary Detection with Efficient Fusion Head
End-to-end transformer-based detectors (DETRs) have shown exceptional performance in both closed-set and open-vocabulary object detection (OVD) tasks through the integration of language modalities.
RFWave: Multi-band Rectified Flow for Audio Waveform Reconstruction
Recent advancements in generative modeling have led to significant progress in audio waveform reconstruction from diverse representations.
DeepCRE: Transforming Drug R&D via AI-Driven Cross-drug Response Evaluation
The fields of therapeutic application and drug research and development (R&D) both face substantial challenges, i. e., the therapeutic domain calls for more treatment alternatives, while numerous promising pre-clinical drugs have failed in clinical trials.
Auxiliary Reward Generation with Transition Distance Representation Learning
To achieve automatic auxiliary reward generation, we propose a novel representation learning approach that can measure the ``transition distance'' between states.
An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion
A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients.
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
To address these two challenges, we propose a diffusion-based refinement framework called DRPose, which refines the output of deterministic models by reverse diffusion and achieves more suitable multi-hypothesis prediction for the current pose benchmark by multi-step refinement with multiple noises.
Lightweight high-resolution Subject Matting in the Real World
To alleviate these issues, we propose to construct a saliency object matting dataset HRSOM and a lightweight network PSUNet.
NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian
To bridge these gaps, we introduce NLEBench, a comprehensive benchmark tailored for evaluating natural language generation capabilities in Norwegian, a low-resource language.
Robust Visual Imitation Learning with Inverse Dynamics Representations
Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems.
Exploring Small Language Models with Prompt-Learning Paradigm for Efficient Domain-Specific Text Classification
Our evaluations show that, in few-shot settings when prompt-based model fine-tuning is possible, T5-base, a typical SLM with 220M parameters, achieve approximately 75% accuracy with limited labeled data (up to 15% of full data), which shows great potentials of SLMs with prompt-learning.
A duality between utility transforms and probability distortions
In this paper, we establish a mathematical duality between utility transforms and probability distortions.
How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection
Extensive experimental results show that existing top OVD models all fail on the new tasks except for simple object types, demonstrating the value of the proposed dataset in pinpointing the weakness of current OVD models and guiding future research.
Ranked #1 on
Negation
on OVDEval
IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse
Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task.
Double-chain Constraints for 3D Human Pose Estimation in Images and Videos
Notably, our model achieves state-of-the-art performance on all action categories in the Human3. 6M dataset using detected 2D poses from CPN, and our code is available at: https://github. com/KHB1698/DC-GCT.
Ranked #44 on
3D Human Pose Estimation
on Human3.6M
The Effectiveness of Large Language Models (ChatGPT and CodeBERT) for Security-Oriented Code Analysis
However, we observed that the strengths and limitations of adopting these LLMs to the code analysis have not been investigated.
Ranked #2 on
Code Generation
on MBPP
SoK: Comparing Different Membership Inference Attacks with a Comprehensive Benchmark
We have identified three principles for the proposed "comparing different MI attacks" methodology, and we have designed and implemented the MIBench benchmark with 84 evaluation scenarios for each dataset.
FedDCT: A Dynamic Cross-Tier Federated Learning Scheme in Wireless Communication Networks
FL enables the training of a global model among clients without exposing local data.
C$^3$PS: Context-aware Conditional Cross Pseudo Supervision for Semi-supervised Medical Image Segmentation
In this paper, we introduce a novel Context-aware Conditional Cross Pseudo Supervision method (referred as C$^3$PS) for semi-supervised medical image segmentation.
Behavior Contrastive Learning for Unsupervised Skill Discovery
Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective.
Non-rigid Point Cloud Registration for Middle Ear Diagnostics with Endoscopic Optical Coherence Tomography
To overcome the lack of labeled training data, a fast and effective generation pipeline in Blender3D is designed to simulate middle ear shapes and extract in-vivo noisy and partial point clouds.
Indeterminate Probability Neural Network
Besides, for our proposed neural network framework, the output of neural network is defined as probability events, and based on the statistical analysis of these events, the inference model for classification task is deduced.
In-Situ Calibration of Antenna Arrays for Positioning With 5G Networks
Owing to the ubiquity of cellular communication signals, positioning with the fifth generation (5G) signal has emerged as a promising solution in global navigation satellite system-denied areas.
Pre-train, Prompt and Recommendation: A Comprehensive Survey of Language Modelling Paradigm Adaptations in Recommender Systems
The emergence of Pre-trained Language Models (PLMs) has achieved tremendous success in the field of Natural Language Processing (NLP) by learning universal representations on large corpora in a self-supervised manner.
Which Features are Learned by CodeBert: An Empirical Study of the BERT-based Source Code Representation Learning
The Bidirectional Encoder Representations from Transformers (BERT) were proposed in the natural language process (NLP) and shows promising results.
Link-level simulator for 5G localization
Channel-state-information-based localization in 5G networks has been a promising way to obtain highly accurate positions compared to previous communication networks.
Recommending on graphs: a comprehensive review from a data perspective
Recent advances in graph-based learning approaches have demonstrated their effectiveness in modelling users' preferences and items' characteristics for Recommender Systems (RSS).
Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learning
In this work, we develop a novel identity detection reinforcement learning (IDRL) framework that allows an agent to dynamically infer the identities of nearby agents and select an appropriate policy to accomplish the task.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples
In this paper, we propose an AutoEncoder-based Adversarial Examples (AEAE) detector, that can guard DNN models by detecting adversarial examples with low computation in an unsupervised manner.
Precision measurement of the return distribution property of the Chinese stock market index
(2) The central part of return distribution is well described by the symmetrical L\'{e}vy $\alpha$-stable process with a stability parameter comparable with the value of about 1. 4 extracted in the U. S. stock market.
OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network
The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision.
Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning
Model-Agnostic Meta-Learning (MAML) is one of the most successful meta-learning techniques for few-shot learning.
KiPA22 Report: U-Net with Contour Regularization for Renal Structures Segmentation
Three-dimensional (3D) integrated renal structures (IRS) segmentation is important in clinical practice.
Learning-based Autonomous Channel Access in the Presence of Hidden Terminals
We consider the problem of autonomous channel access (AutoCA), where a group of terminals tries to discover a communication strategy with an access point (AP) via a common wireless channel in a distributed fashion.
Efficient Joint DOA and TOA Estimation for Indoor Positioning with 5G Picocell Base Stations
Secondly, based on the deployment reality that 5G picocell gNBs only have a small-scale antenna array but have a large signal bandwidth, the proposed scheme decouples the estimation of time-of-arrival (TOA) and direction-of-arrival (DOA) to reduce the huge complexity induced by two-dimensional joint processing.
Phased Progressive Learning with Coupling-Regulation-Imbalance Loss for Imbalanced Data Classification
This loss is effective in addressing quantity imbalances and outliers, while regulating the focus of attention on samples with varying classification difficulties.
Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters
We took natural language processing (NLP) as an example to show how Nebula-I works in different training phases that include: a) pre-training a multilingual language model using two remote clusters; and b) fine-tuning a machine translation model using knowledge distilled from pre-trained models, which run through the most popular paradigm of recent deep learning.
Cross-Lingual Natural Language Inference
Distributed Computing
+2
Balancing Multi-Domain Corpora Learning for Open-Domain Response Generation
Furthermore, we propose Domain-specific Frequency (DF), a novel word-level importance weight that measures the relative importance of a word for a specific corpus compared to other corpora.
Temporal and spatial evolution of the distribution related to the number of COVID-19 pandemic
(1) The distributions of the numbers for cumulative confirmed cases and deaths obey power-law in early stages of COVID-19 and stretched exponential function in subsequent course.
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning
We show that such OOD sampling and pessimistic bootstrapping yields provable uncertainty quantifier in linear MDPs, thus providing the theoretical underpinning for PBRL.
Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection
Experimental results show that the contribution of image transformations to adversarial detection is significantly different, the combination of them can significantly improve the generic detection ability against state-of-the-art adversarial attacks.
Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
It is necessary to force the student network to learn the modality relationship information of the teacher network.
Dynamic Bottleneck for Robust Self-Supervised Exploration
Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards.
MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildings
Head detection in the indoor video is an essential component of building occupancy detection.
CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentation
The proposed training strategy and novel unsupervised domain adaptation framework, called Collaborative Adversarial Domain Adaptation (CADA), can effectively overcome the challenge.
Towards Better Data Augmentation using Wasserstein Distance in Variational Auto-encoder
VAE, or variational auto-encoder, compresses data into latent attributes, and generates new data of different varieties.
Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain
In addition to algorithmic analysis, we provide a comprehensive and unified empirical comparison of different exploration methods for DRL on a set of commonly used benchmarks.
Circuit design and integration feasibility of a high-resolution broadband on-chip spectral monitor
Full tuning of the comb of resonances over a free spectral range is achieved with a high-resolution bandwidth of 1. 30 GHz.
An explainable two-dimensional single model deep learning approach for Alzheimer's disease diagnosis and brain atrophy localization
In this research, we propose a novel end-to-end deep learning approach for automated diagnosis of AD and localization of important brain regions related to the disease from sMRI data.
Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features
In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image.
Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
In this way, an obvious gap can be produced between the distributions of normal and abnormal data in the target domain, therefore enabling the anomaly detection in the domain.
Principled Exploration via Optimistic Bootstrapping and Backward Induction
In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I).
Ion-beam-assisted characterization of quinoline-insoluble particles in nuclear graphite
A much higher concentration of QI particles in NBG-18 than IG-110 was characterized and is suggested to be responsible for the smaller maximum dimensional shrinkage of NBG-18 than IG-110 during irradiation.
Applied Physics
VARA-TTS: Non-Autoregressive Text-to-Speech Synthesis based on Very Deep VAE with Residual Attention
This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely.
Security and Privacy for Artificial Intelligence: Opportunities and Challenges
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies.
Single Model Deep Learning on Imbalanced Small Datasets for Skin Lesion Classification
This paper proposes a novel single-model based strategy for classification of skin lesions on small and imbalanced datasets.
Sojourn times of Gaussian related random fields
In the literature, based on the pioneering research of S. Berman the sojourn times have been utilised to derive the tail asymptotics of supremum of Gaussian processes.
Gaussian Processes
Probability
Primary 60G15, secondary 60G70
A Survey on Active Deep Learning: From Model-driven to Data-driven
Which samples should be labelled in a large data set is one of the most important problems for trainingof deep learning.
Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification
At the network search stage, the DCNNs are fine-tuned with the full training set in order to select the model with the highest BACC.
Optimistic Exploration with Backward Bootstrapped Bonus for Deep Reinforcement Learning
However, such an approach is challenging in developing practical exploration algorithms for Deep Reinforcement Learning (DRL).
Recomposition vs. Prediction: A Novel Anomaly Detection for Discrete Events Based On Autoencoder
One of the most challenging problems in the field of intrusion detection is anomaly detection for discrete event logs.
Generating Comprehensive Data with Protocol Fuzzing for Applying Deep Learning to Detect Network Attacks
Network attacks have become a major security concern for organizations worldwide and have also drawn attention in the academics.
Cryptography and Security
Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement Learning
Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded.
GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack
Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs).
Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detection
As an increasing number of deep-learning-based malware scanners have been proposed, the existing evasion techniques, including code obfuscation and polymorphic malware, are found to be less effective.
Regularised Text Logistic Regression: Key Word Detection and Sentiment Classification for Online Reviews
Moreover, RTL identifies a small set of word features, corresponding to 3% for Restaurant and 20% for Hotel, which boosts working efficiency by allowing managers to drill down into a much smaller set of important customer reviews.
Ordering and Inequalities for Mixtures on Risk Aggregation
Aggregation sets, which represent model uncertainty due to unknown dependence, are an important object in the study of robust risk aggregation.
Speaker Independent and Multilingual/Mixlingual Speech-Driven Talking Head Generation Using Phonetic Posteriorgrams
Recent approaches mainly have following limitations: 1) most speaker-independent methods need handcrafted features that are time-consuming to design or unreliable; 2) there is no convincing method to support multilingual or mixlingual speech as input.
Towards classification parity across cohorts
In this research work, we aim to achieve classification parity across explicit as well as implicit sensitive features.
Email Threat Detection Using Distinct Neural Network Approaches
This paper describes different approaches to detect malicious content in email interactions through a combination of machine learning and natural language processing tools.
Unsupervised Image-generation Enhanced Adaptation for Object Detection in Thermal images
To reduce the gap between visible domain and thermal domain, the proposed method manages to generate simulated fake thermal images that are similar to the target images, and preserves the annotation information of the visible source domain.
Regression and Learning with Pixel-wise Attention for Retinal Fundus Glaucoma Segmentation and Detection
In addition, we develop several attention strategies to guide the networks to learn the important features that have a major impact on prediction accuracy.
Using Deep Learning to Solve Computer Security Challenges: A Survey
Although using machine learning techniques to solve computer security challenges is not a new idea, the rapidly emerging Deep Learning technology has recently triggered a substantial amount of interests in the computer security community.
Cryptography and Security
KRNET: Image Denoising with Kernel Regulation Network
In this paper, we optimize CNN regularization capability by developing a kernel regulation module.
Image Restoration Using Deep Regulated Convolutional Networks
While the depth of convolutional neural networks has attracted substantial attention in the deep learning research, the width of these networks has recently received greater interest.
Ranked #1 on
Grayscale Image Denoising
on BSD200 sigma70
SDCNet: Smoothed Dense-Convolution Network for Restoring Low-Dose Cerebral CT Perfusion
With substantial public concerns on potential cancer risks and health hazards caused by the accumulated radiation exposure in medical imaging, reducing radiation dose in X-ray based medical imaging such as Computed Tomography Perfusion (CTP) has raised significant research interests.
CFEA: Collaborative Feature Ensembling Adaptation for Domain Adaptation in Unsupervised Optic Disc and Cup Segmentation
Our proposed CFEA is an interactive paradigm which presents an exquisite of collaborative adaptation through both adversarial learning and ensembling weights.
REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
As part of REFUGE, we have publicly released a data set of 1200 fundus images with ground truth segmentations and clinical glaucoma labels, currently the largest existing one.
DurIAN: Duration Informed Attention Network For Multimodal Synthesis
In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously.
Maximizing Mutual Information for Tacotron
End-to-end speech synthesis methods already achieve close-to-human quality performance.
Learning Privately over Distributed Features: An ADMM Sharing Approach
Distributed machine learning has been widely studied in order to handle exploding amount of data.
YNU-HPCC at SemEval-2019 Task 8: Using A LSTM-Attention Model for Fact-Checking in Community Forums
The LSTM-Attention model uses two LSTM to extract the features of the question and answer pair.
SvTPM: A Secure and Efficient vTPM in the Cloud
In this paper, we present SvTPM, a secure and efficient software-based vTPM implementation based on hardware-rooted Trusted Execution Environment (TEE), providing a whole life cycle protection of vTPMs in the cloud.
Cryptography and Security
Accelerated Labeling of Discrete Abstractions for Autonomous Driving Subject to LTL Specifications
Linear temporal logic and automaton-based run-time verification provide a powerful framework for designing task and motion planning algorithms for autonomous agents.
ServeNet: A Deep Neural Network for Web Services Classification
Automated service classification plays a crucial role in service discovery, selection, and composition.
Learning Pixel-Distribution Prior with Wider Convolution for Image Denoising
In this work, we explore an innovative strategy for image denoising by using convolutional neural networks (CNN) to learn pixel-distribution from noisy data.
Wide Inference Network for Image Denoising via Learning Pixel-distribution Prior
We explore an innovative strategy for image denoising by using convolutional neural networks (CNN) to learn similar pixel-distribution features from noisy images.
Hey, you, keep away from my device: remotely implanting a virus expeller to defeat Mirai on IoT devices
In particular, at a negotiated time slot, a customer is required to reboot the compromised device, then a "white" Mirai operated by the manufacturer breaks into the clean-state IoT devices immediately.
Cryptography and Security
Active Deep Learning for Classification of Hyperspectral Images
It is shown that the proposed algorithm is efficient and effective in classifying hyperspectral images.
GaDei: On Scale-up Training As A Service For Deep Learning
By evaluating the NLC workloads, we show that only the conservative hyper-parameter setup (e. g., small mini-batch size and small learning rate) can guarantee acceptable model accuracy for a wide range of customers.
Context-aware System Service Call-oriented Symbolic Execution of Android Framework with Application to Exploit Generation
We present novel ideas and techniques to resolve the challenges, and have built the first system for symbolic execution of Android Framework.
Cryptography and Security Software Engineering
Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks
Deep neural networks have proven to be quite effective in a wide variety of machine learning tasks, ranging from improved speech recognition systems to advancing the development of autonomous vehicles.
High-speed real-time single-pixel microscopy based on Fourier sampling
However, according to CS theory, image reconstruction is an iterative process that consumes enormous amounts of computational time and cannot be performed in real time.
Multimodal Spontaneous Emotion Corpus for Human Behavior Analysis
The corpus further includes derived features from 3D, 2D, and IR (infrared) sensors and baseline results for facial expression and action unit detection.
