Search Results for author:
Found 49 papers, 13 papers with code
Towards Controllable Speech Synthesis in the Era of Large Language Models: A Survey
In this paper, we conduct a comprehensive survey of controllable TTS, covering approaches ranging from basic control techniques to methods utilizing natural language prompts, aiming to provide a clear understanding of the current state of research.
Behavior Backdoor for Deep Learning Models
Specifically, to adapt the optimization goal of behavior backdoor, we introduce the behavior-driven backdoor object optimizing method by a bi-target behavior backdoor training loss, thus we could guide the poisoned model optimization direction.
KinMo: Kinematic-aware Human Motion Understanding and Generation
Controlling human motion based on text presents an important challenge in computer vision.
Start from Video-Music Retrieval: An Inter-Intra Modal Loss for Cross Modal Retrieval
In reality, a video can use different music as background music, and a music can be used as background music for different videos.
ISWSST: Index-space-wave State Superposition Transformers for Multispectral Remotely Sensed Imagery Semantic Segmentation
Currently the semantic segmentation task of multispectral remotely sensed imagery (MSRSI) faces the following problems: 1) Usually, only single domain feature (i. e., space domain or frequency domain) is considered; 2) downsampling operation in encoder generally leads to the accuracy loss of edge extraction; 3) multichannel features of MSRSI are not fully considered; and 4) prior knowledge of remote sensing is not fully utilized.
Probing many-body Bell correlation depth with superconducting qubits
As an illustrating example, we variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations.
UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation
Besides the aforementioned spectrum noises in semantic segmentation, MUDM is also a self-supervised learning strategy to effectively reduce the edge false change detection from the generated imagery with geometric registration error.
Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases
In this study, we introduce Rene, a pioneering large-scale model tailored for respiratory sound recognition.
Collaborative Edge AI Inference over Cloud-RAN
To realize efficient uplink feature aggregation, we allow each RRH receives local feature vectors from all devices over the same resource blocks simultaneously by leveraging an over-the-air computation (AirComp) technique.
RCoCo: Contrastive Collective Link Prediction across Multiplex Network in Riemannian Space
Annotating anchor users is laborious and expensive, and thus it is impractical to work with quantities of anchor users.
Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients
We compare the proposed CHA with GPT4.
Fine-Grained Bipartite Concept Factorization for Clustering
In this paper we propose a novel concept factorization method that seeks factor matrices using a cross-order positive semi-definite neighbor graph which provides comprehensive and complementary neighbor information of the data.
Active Learning Framework for Cost-Effective TCR-Epitope Binding Affinity Prediction
To reduce annotation cost, we present ActiveTCR, a framework that incorporates active learning and TCR-epitope binding affinity prediction models.
Zero-Shot Learning by Harnessing Adversarial Samples
To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS).
Reduce Computational Complexity for Convolutional Layers by Skipping Zeros
Convolutional neural networks necessitate good algorithms to reduce complexity, and sufficient utilization of parallel processors for acceleration.
Dragon-Alpha&cu32: A Java-based Tensor Computing Framework With its High-Performance CUDA Library
Java is very powerful, but in Deep Learning field, its capabilities probably has not been sufficiently exploited.
Background Invariance Testing According to Semantic Proximity
This ontology enables (i) efficient and meaningful search for background scenes of different semantic distances to a target image, (ii) quantitative control of the distribution and sparsity of the sampled background scenes, and (iii) quality assurance using visual representations of invariance testing results (referred to as variance matrices).
MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue
Firstly, we build an evaluation metric composed of 5 groups of parallel sub-metrics called Multi-Metric Evaluation (MME) to evaluate the quality of dialogue comprehensively.
Adaptive Prompt Learning-based Few-Shot Sentiment Analysis
In the field of natural language processing, sentiment analysis via deep learning has a excellent performance by using large labeled datasets.
Experimental quantum adversarial learning with programmable superconducting qubits
Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.
CLMB: deep contrastive learning for robust metagenomic binning
Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data.
Wireless Federated Learning over MIMO Networks: Joint Device Scheduling and Beamforming Design
Specifically, we theoretically establish the convergence analysis of the FL process, and then apply the proposed device scheduling policy to maximize the number of weighted devices under the FL system latency and sum power constraints.
ML4ML: Automated Invariance Testing for Machine Learning Models
In this paper, we show that testing the invariance qualities of ML models may result in complex visual patterns that cannot be classified using simple formulas.
Face.evoLVe: A High-Performance Face Recognition Library
In this paper, we develop face. evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition.
Uncovering the molecular mechanism for dual effect of ATP on phase separation in FUS solution
Recent studies reported that adenosine triphosphate (ATP) could inhibit as well as enhance the phase separation in prion-like proteins.
Soft Condensed Matter Biological Physics
Colorectal Polyp Detection in Real-world Scenario: Design and Experiment Study
All these factors pose a significant challenge to effective polyp detection in a colonoscopy.
A Sequential Modelling Approach for Indoor Temperature Prediction and Heating Control in Smart Buildings
The rising availability of large volume data, along with increasing computing power, has enabled a wide application of statistical Machine Learning (ML) algorithms in the domains of Cyber-Physical Systems (CPS), Internet of Things (IoT) and Smart Building Networks (SBN).
Tunneling through an Eternal Traversable Wormhole
Comparing to the high-temperature black hole phase where the bulk geometry is disconnected, we find both the tunneling probability and the differential conductance in the low-temperature wormhole phase show non-trivial oscillation, which directly provides an unambiguous signature of the underlying $SL(2)$ symmetry of the bulk geometry.
Strongly Correlated Electrons Disordered Systems and Neural Networks High Energy Physics - Theory
Searching for Quasi-Periodic Modulations in $γ$-ray Active Galactic Nuclei
We perform a systematic search of quasi-periodic variabilities in $\gamma$-ray active galactic nuclei (AGNs) in the third \emph{Fermi} Large Area Telescope source catalog (3FGL).
High Energy Astrophysical Phenomena
Colorectal Polyp Segmentation by U-Net with Dilation Convolution
The model we design consists of an encoder to extract multi-scale semantic features and a decoder to expand the feature maps to a polyp segmentation map.
Information Scrambling in Quantum Neural Networks
In this Letter, we show that this process can also be viewed from the opposite direction: the quantum information in the output qubits is scrambled into the input.
AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy
Though challenging, with the great advances in object detection techniques, automated polyp detection still demonstrates a great potential in reducing the false negative rate while maintaining a high precision.
EleAtt-RNN: Adding Attentiveness to Neurons in Recurrent Neural Networks
For an RNN block, an EleAttG is used for adaptively modulating the input by assigning different levels of importance, i. e., attention, to each element/dimension of the input.
Ranked #3 on
Skeleton Based Action Recognition
on SYSU 3D
3D Anchor-Free Lesion Detector on Computed Tomography Scans
The anchor mechanism is removed and lesions are formalized as single keypoints.
Multi-Stream Single Shot Spatial-Temporal Action Detection
We present a 3D Convolutional Neural Networks (CNNs) based single shot detector for spatial-temporal action detection tasks.
Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition
Skeleton-based human action recognition has attracted great interest thanks to the easy accessibility of the human skeleton data.
Ranked #1 on
Skeleton Based Action Recognition
on SYSU 3D
SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
In order to address this issue, we propose a data-driven state refinement module for LSTM network (SR-LSTM), which activates the utilization of the current intention of neighbors, and jointly and iteratively refines the current states of all participants in the crowd through a message passing mechanism.
Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach
Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features.
Bayesian deep neural networks for low-cost neurophysiological markers of Alzheimer's disease severity
As societies around the world are ageing, the number of Alzheimer's disease (AD) patients is rapidly increasing.
Attention Boosted Sequential Inference Model
Attention mechanism has been proven effective on natural language processing.
Ranked #1 on
Natural Language Inference
on Quora Question Pairs
Adding Attentiveness to the Neurons in Recurrent Neural Networks
We propose adding a simple yet effective Element-wiseAttention Gate (EleAttG) to an RNN block (e. g., all RNN neurons in a network layer) that empowers the RNN neurons to have the attentiveness capability.
Ranked #110 on
Skeleton Based Action Recognition
on NTU RGB+D
Deep Learning Topological Invariants of Band Insulators
Despite the complexity of the neural network, we find that the output of certain intermediate hidden layers resembles either the winding angle for models in AIII class or the solid angle (Berry curvature) for models in A class, indicating that neural networks essentially capture the mathematical formula of topological invariants.
View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognition
In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints in a learning based data driven manner.
Ranked #1 on
Skeleton Based Action Recognition
on UWA3D
Visualizing Neural Network Developing Perturbation Theory
In this letter, motivated by the question that whether the empirical fitting of data by neural network can yield the same structure of physical laws, we apply the neural network to a simple quantum mechanical two-body scattering problem with short-range potentials, which by itself also plays an important role in many branches of physics.
Riemannian tangent space mapping and elastic net regularization for cost-effective EEG markers of brain atrophy in Alzheimer's disease
The diagnosis of Alzheimer's disease (AD) in routine clinical practice is most commonly based on subjective clinical interpretations.
Sensor Selection and Random Field Reconstruction for Robust and Cost-effective Heterogeneous Weather Sensor Networks for the Developing World
Next, building on the S-BLUE, we address the second problem, and develop an efficient algorithm for query based sensor set selection with performance guarantee.
Machine Learning Topological Invariants with Neural Networks
In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators.
View Adaptive Recurrent Neural Networks for High Performance Human Action Recognition from Skeleton Data
Rather than re-positioning the skeletons based on a human defined prior criterion, we design a view adaptive recurrent neural network (RNN) with LSTM architecture, which enables the network itself to adapt to the most suitable observation viewpoints from end to end.
Ranked #6 on
Skeleton Based Action Recognition
on SYSU 3D
