Search Results for author:
Found 94 papers, 24 papers with code
基于多层次预训练策略和多任务学习的端到端蒙汉语音翻译(End-to-end Mongolian-Chinese Speech Translation Based on Multi-level Pre-training Strategies and Multi-task Learning)
“端到端语音翻译将源语言语音直接翻译为目标语言文本, 它需要“源语言语音-目标语言文本”作为训练数据, 然而这类数据极其稀缺, 本文提出了一种多层次预训练策略和多任务学习相结合的训练方法, 首先分别对语音识别和机器翻译模型的各个模块进行多层次预训练, 接着将语音识别和机器翻译模型连接起来构成语音翻译模型, 然后使用迁移学习对预训练好的模型进行多步骤微调, 在此过程中又运用多任务学习的方法, 将语音识别作为语音翻译的一个辅助任务来组织训练, 充分利用了已经存在的各种不同形式的数据来训练端到端模型, 首次将端到端技术应用于资源受限条件下的蒙汉语音翻译, 构建了首个翻译质量较高、实际可用的端到端蒙汉语音翻译系统。”
The X-LANCE Technical Report for Interspeech 2024 Speech Processing Using Discrete Speech Unit Challenge
Discrete speech tokens have been more and more popular in multiple speech processing fields, including automatic speech recognition (ASR), text-to-speech (TTS) and singing voice synthesis (SVS).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
GraspXL: Generating Grasping Motions for Diverse Objects at Scale
Moreover, we show that our framework can be deployed to different dexterous hands and work with reconstructed or generated objects.
HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction
Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e. g. point position and element shape, into the HIQuery.
VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt.
Privacy-preserving transactive energy systems: Key topics and open research challenges
This manuscript aims to formalize and conclude the discussions initiated during the PriTEM workshop 22-23 March 2023.
Double-Flow GAN model for the reconstruction of perceived faces from brain activities
Face plays an important role in human's visual perception, and reconstructing perceived faces from brain activities is challenging because of its difficulty in extracting high-level features and maintaining consistency of multiple face attributes, such as expression, identity, gender, etc.
VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models
Our model can edit and translate the desired results within seconds based on user instructions.
AdaDiff: Adaptive Step Selection for Fast Diffusion
Diffusion models, as a type of generative models, have achieved impressive results in generating images and videos conditioned on textual conditions.
Joint Design of ISAC Waveform under PAPR Constraints
In this paper, we formulate the precoding problem of integrated sensing and communication (ISAC) waveform as a non-convex quadratically constrainted quadratic program (QCQP), in which the weighted sum of communication multi-user interference (MUI) and the gap between dual-use waveform and ideal radar waveform is minimized with peak-to-average power ratio (PAPR) constraints.
Predicting urban tree cover from incomplete point labels and limited background information
This paper studies how to combine accurate point labels of urban trees along streets with crowd-sourced annotations from an open geographic database to delineate city trees in remote sensing images, a task which is challenging even for humans.
AdapterShadow: Adapting Segment Anything Model for Shadow Detection
To adapt SAM for shadow images, trainable adapters are inserted into the frozen image encoder of SAM, since the training of the full SAM model is both time and memory consuming.
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework
In this work, we propose a distributed resilient consensus framework, consisting of a pre-designed consensus protocol and distributed model predictive control (DMPC) optimization, which can help significantly reduce the requirement on the network robustness and effectively handle the general linear constrained MAS under adversarial attacks.
Addressing preferred orientation in single-particle cryo-EM through AI-generated auxiliary particles
The single-particle cryo-EM field faces the persistent challenge of preferred orientation, lacking general computational solutions.
ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose.
S$^3$-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detection
These methods typically use visual and depth representations to generate query points on objects, whose quality plays a decisive role in the detection accuracy.
Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation
In this way, the categorization of each point is conditioned on its local semantic pattern.
Efficient option pricing with unary-based photonic computing chip and generative adversarial learning
In the modern financial industry system, the structure of products has become more and more complex, and the bottleneck constraint of classical computing power has already restricted the development of the financial industry.
Rician likelihood loss for quantitative MRI using self-supervised deep learning
Results: Networks trained with NLR loss show higher estimation accuracy than MSE for the ADC and IVIM diffusion coefficients as SNR decreases, with minimal loss of precision or total error.
DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis
To address this, we develop a generalist model that shares architecture and parameters across centers to utilize the shared knowledge.
Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling
In order to craft natural-looking adversarial clothes that can evade person detectors at multiple viewing angles, we propose adversarial camouflage textures (AdvCaT) that resemble one kind of the typical textures of daily clothes, camouflage textures.
Patch-CNN: Training data-efficient deep learning for high-fidelity diffusion tensor estimation from minimal diffusion protocols
To overcome these limitations, we propose Patch-CNN, a neural network with a minimal (non-voxel-wise) convolutional kernel (3$\times$3$\times$3).
SSC3OD: Sparsely Supervised Collaborative 3D Object Detection from LiDAR Point Clouds
Extensive experiments on three large-scale datasets reveal that our proposed SSC3OD can effectively improve the performance of sparsely supervised collaborative 3D object detectors.
Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning
It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain.
When SAM Meets Shadow Detection
As a promptable generic object segmentation model, segment anything model (SAM) has recently attracted significant attention, and also demonstrates its powerful performance.
Quadratic Graph Attention Network (Q-GAT) for Robust Construction of Gene Regulatory Networks
The former informs that nonlinear aggregation of quadratic neurons can amplify useful signals and suppress unwanted noise, thereby facilitating robustness, while the latter reveals that Q-GAT can leverage more features in prediction thanks to the dual attention mechanism, which endows Q-GAT with the ability to confront adversarial perturbation.
Focused and Collaborative Feedback Integration for Interactive Image Segmentation
Interactive image segmentation aims at obtaining a segmentation mask for an image using simple user annotations.
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency.
Ranked #1 on
Anomaly Detection
on VisA
Resolving quantitative MRI model degeneracy with machine learning via training data distribution design
Our results illustrate the importance of training set design which has the potential to allow accurate estimation of tissue properties with ML.
Collaborative Perception in Autonomous Driving: Methods, Datasets and Challenges
The former focuses on collaboration modules and efficiency, and the latter is devoted to addressing the problems in actual application.
Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On
In this paper, a novel virtual try-on algorithm, dubbed SAL-VTON, is proposed, which links the garment with the person via semantically associated landmarks to alleviate misalignment.
Prototypical Residual Networks for Anomaly Detection and Localization
Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness.
Ranked #2 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
Self-Regularized Prototypical Network for Few-Shot Semantic Segmentation
A direct yet effective prototype regularization on support set is proposed in SRPNet, in which the generated prototypes are evaluated and regularized on the support set itself.
Searching a High-Performance Feature Extractor for Text Recognition Network
We design a domain-specific search space by exploring principles for having good feature extractors.
Neural Architecture Search
Vocal Bursts Intensity Prediction
How can spherical CNNs benefit ML-based diffusion MRI parameter estimation?
A possible consequence of the lack of rotational equivariance is that the training dataset must contain a diverse range of microstucture orientations.
Enforcing continuous symmetries in physics-informed neural network for solving forward and inverse problems of partial differential equations
As a typical application of deep learning, physics-informed neural network (PINN) {has been} successfully used to find numerical solutions of partial differential equations (PDEs), but how to improve the limited accuracy is still a great challenge for PINN.
A Unified Understanding of Deep NLP Models for Text Classification
The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually.
0/1 Deep Neural Networks via Block Coordinate Descent
The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs).
Neural Network Decoders for Permutation Codes Correcting Different Errors
Permutation codes were extensively studied in order to correct different types of errors for the applications on power line communication and rank modulation for flash memory.
PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit
PaddleSpeech is an open-source all-in-one speech toolkit.
Automatic Speech Recognition (ASR)
Environmental Sound Classification
+9
3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
(2) We adopt a task-driven strategy that couples a segmentation task with a generative adversarial network (GAN) framework to improve the translation performance.
Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation
Self-supervised approaches, sometimes referred to as unsupervised, have been loosely based on auto-encoders, whereas supervised methods have, to date, been trained on groundtruth labels.
Thin-Plate Spline Motion Model for Image Animation
Firstly, we propose thin-plate spline motion estimation to produce a more flexible optical flow, which warps the feature maps of the source image to the feature domain of the driving image.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
A photonic chip-based machine learning approach for the prediction of molecular properties
Machine learning methods have revolutionized the discovery process of new molecules and materials.
Projected Sliced Wasserstein Autoencoder-based Hyperspectral Images Anomaly Detection
In this case, the Wasserstein distance can be calculated with the closed-form, even the prior distribution is not Gaussian.
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots.
Auto-Encoding Score Distribution Regression for Action Quality Assessment
Traditionally, AQA is treated as a regression problem to learn the underlying mappings between videos and action scores.
Ranked #1 on
Action Quality Assessment
on JIGSAWS
MAGORINO: Magnitude-only fat fraction and R2* estimation with Rician noise modelling
Purpose: Magnitude-based fitting of chemical shift-encoded data enables proton density fat fraction (PDFF) and R2* estimation where complex-based methods fail or when phase data is inaccessible or unreliable, such as in multi-centre studies.
Volume of hyperintense inflammation (VHI): a deep learning-enabled quantitative imaging biomarker of inflammation load in spondyloarthritis
Short inversion time inversion recovery (STIR) MRI is widely used in clinical practice to identify and quantify inflammation in axial spondyloarthritis.
Unveiling personnel movement in a larger indoor area with a non-overlapping multi-camera system
Surveillance cameras are widely applied for indoor occupancy measurement and human movement perception, which benefit for building energy management and social security.
Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud
There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object.
Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
Extensive experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures to obtain the better tradeoff between visual quality and computational complexity.
EventAnchor: Reducing Human Interactions in Event Annotation of Racket Sports Videos
The popularity of racket sports (e. g., tennis and table tennis) leads to high demands for data analysis, such as notational analysis, on player performance.
FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection
Most successful object detectors are anchor-based, which is difficult to adapt to the diversity of traffic objects.
TESS Delivers Five New Hot Giant Planets Orbiting Bright Stars from the Full Frame Images
TOI-640 b is one of only three known hot Jupiters to have a highly inflated radius (R$_{\rm P}$ > 1. 7R$_{\rm J}$, possibly a result of its host star's evolution) and resides on an orbit with a period longer than 5 days.
Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Multi-Model Least Squares-Based Recomputation Framework for Large Data Analysis
Most multilayer least squares (LS)-based neural networks are structured with two separate stages: unsupervised feature encoding and supervised pattern classification.
Prototypical Matching and Open Set Rejection for Zero-Shot Semantic Segmentation
In this work, we present zero-shot semantic segmentation, which aims to identify not only the seen classes contained in training but also the novel classes that have never been seen.
Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing
In this work, we treat each respective region in an image as a whole, and capture the structure topology as well as the affinity among different regions.
[Re] Reimplementation of FixMatch and Investigation on Noisy (Pseudo) Labels and Confirmation Errors of FixMatch
FixMatch is a semi-supervised learning method, which achieves comparable results with fully supervised learning by leveraging a limited number of labeled data (pseudo labelling technique) and taking a good use of the unlabeled data (consistency regularization ).
Combining Self-Supervised and Supervised Learning with Noisy Labels
Thus, inspired by the observation that classifier is more robust to noisy labels while representation is much more fragile, and by the recent advances of self-supervised representation learning (SSRL) technologies, we design a new method, i. e., CS$^3$NL, to obtain representation by SSRL without labels and train the classifier directly with noisy labels.
Robust Speaker Extraction Network Based on Iterative Refined Adaptation
dataset confirm the superior performance of the proposed method over the network without IRA in terms of SI-SDR and PESQ improvement.
UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition
This approach consists of a generator network and a discriminator network, which operate directly in the time domain.
TOI-954 b and EPIC 246193072 b: Short-Period Saturn-Mass Planets that Test Whether Irradiation Leads to Inflation
We report the discovery of two short-period Saturn-mass planets, one transiting the G subgiant TOI-954 (TIC 44792534, $ V = 10. 343 $, $ T = 9. 78 $) observed in TESS Sectors 4 & 5, and one transiting the G dwarf EPIC 246193072 ($ V = 12. 70 $, $ K = 10. 67 $) observed in K2 Campaigns 12 & 19.
Earth and Planetary Astrophysics
A marine radioisotope gamma-ray spectrum analysis method based on Monte Carlo simulation and MLP neural network
We apply multilayer perceptron (MLP) to analyze the 662 keV full energy peak of Cs-137 in the seawater spectrum.
Deep Monocular Visual Odometry for Ground Vehicle
To push the limit, we analyze the motion pattern of a ground vehicle and focus on learning two-degrees-of-freedom motions by proposed motion focusing and decoupling.
Explanation of Reinforcement Learning Model in Dynamic Multi-Agent System
The results show that verbal explanation generated by both models improve subjective satisfaction of users towards the interpretability of DRL systems.
Emotion Correlation Mining Through Deep Learning Models on Natural Language Text
That means, journalists may try to attract attention using fear and joy words but arouse the emotion love instead; After news release, netizens generate emotional comments to express their intense emotions, i. e., anger, sadness, and love.
A lateral semicircular canal segmentation based geometric calibration for human temporal bone CT Image
Computed Tomography (CT) of the temporal bone has become an important method for diagnosing ear diseases.
AutoSTR: Efficient Backbone Search for Scene Text Recognition
In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance.
Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks
We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks.
All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision.
A Generalized and Robust Method Towards Practical Gaze Estimation on Smart Phone
For the second issue, we define a new metric to measure the robustness of gaze estimator, and propose an adversarial training based Disturbance with Ordinal loss (DwO) method to improve it.
Learning Alignment for Multimodal Emotion Recognition from Speech
Further, emotion recognition will be beneficial from using audio-textual multimodal information, it is not trivial to build a system to learn from multimodality.
Multimodal Emotion Recognition
Speech Emotion Recognition
+2
User independent Emotion Recognition with Residual Signal-Image Network
To the best of author's knowledge, our method is the first attempt to classify large scale subject-independent emotion with 7962 pieces of EDA signals from 457 subjects.
DELTA: A DEep learning based Language Technology plAtform
In this paper we present DELTA, a deep learning based language technology platform.
Ranked #3 on
Text Classification
on Yahoo! Answers
DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter
The Long Short-Term Memory (LSTM) neural network based data association algorithm named as DeepDA for multi-target tracking in clutters is proposed to deal with the NP-hard combinatorial optimization problem in this paper.
A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting
To improve the robustness, a speech enhancement front-end is involved.
Training GANs with Centripetal Acceleration
Training generative adversarial networks (GANs) often suffers from cyclic behaviors of iterates.
Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models
By contrast, in objective news bodies and titles, it is easy to regard text as caused love (gd).
A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction
In this paper, we first utilize the word embedding that focuses on sub-word units to the Mongolian Phrase Break (PB) prediction task by using Long-Short-Term-Memory (LSTM) model.
Active Deep Learning for Classification of Hyperspectral Images
It is shown that the proposed algorithm is efficient and effective in classifying hyperspectral images.
Efficient 3D Room Shape Recovery From a Single Panorama
We propose a method to recover the shape of a 3D room from a full-view indoor panorama.
Homography Estimation From the Common Self-Polar Triangle of Separate Ellipses
In this paper, we address the problem of homography estimation from two separate ellipses.
The Common Self-Polar Triangle of Concentric Circles and Its Application to Camera Calibration
In this paper, we explore the properties of the common self-polar triangle, when the two conics happen to be concentric circles.
Feature Selection Based on Term Frequency and T-Test for Text Categorization
Much work has been done on feature selection.
Scale Selection of Adaptive Kernel Regression by Joint Saliency Map for Nonrigid Image Registration
JSM guides the local structure matching in nonrigid registration by emphasizing these JSSs' sparse deformation vectors in adaptive kernel regression of hierarchical sparse deformation vectors for iterative dense deformation reconstruction.
Local Structure Matching Driven by Joint-Saliency-Structure Adaptive Kernel Regression
For nonrigid image registration, matching the particular structures (or the outliers) that have missing correspondence and/or local large deformations, can be more difficult than matching the common structures with small deformations in the two images.
Inverse-Category-Frequency based supervised term weighting scheme for text categorization
Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs.
Ranked #1 on
Multi-class Classification
on Reuters-52
