Search Results for author:
Found 187 papers, 19 papers with code
An Augmented Benchmark Dataset for Geometric Question Answering through Dual Parallel Text Encoding
The lack of high-quality datasets and efficient neural geometric solvers impedes the development of automatic geometric problems solving.
System Description on Automatic Simultaneous Translation Workshop
This paper shows our submission on the second automatic simultaneous translation workshop at NAACL2021.
PINGAN Omini-Sinitic at SemEval-2022 Task 4: Multi-prompt Training for Patronizing and Condescending Language Detection
This paper describes the second-placed system for subtask 2 and the ninth-placed system for subtask 1 in SemEval 2022 Task 4: Patronizing and Condescending Language Detection.
SVVAD: Personal Voice Activity Detection for Speaker Verification
To address this, we propose a speaker verification-based voice activity detection (SVVAD) framework that can adapt the speech features according to which are most informative for SV.
P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV).
Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
Blind Omnidirectional Image Quality Assessment (BOIQA) aims to objectively assess the human perceptual quality of omnidirectional images (ODIs) without relying on pristine-quality image information.
Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization
To eliminate this concern, we propose a federated learning text summarization scheme, which allows users to share the global model in a cooperative learning manner without sharing raw data.
Two-stage Denoising Diffusion Model for Source Localization in Graph Inverse Problems
However, the inherent intricacy and uncertainty in information dissemination pose significant challenges, and the ill-posed nature of the source localization problem further exacerbates these challenges.
Detecting Out-of-distribution Examples via Class-conditional Impressions Reappearing
Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data.
SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning
In this paper, we propose a scalable value-decomposition exploration (SVDE) method, which includes a scalable training mechanism, intrinsic reward design, and explorative experience replay.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response Retrieval
Deep neural networks have achieved remarkable performance in retrieval-based dialogue systems, but they are shown to be ill calibrated.
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains challenging.
Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification
Data-Free Knowledge Distillation (DFKD) has recently attracted growing attention in the academic community, especially with major breakthroughs in computer vision.
QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis
Recent expressive text to speech (TTS) models focus on synthesizing emotional speech, but some fine-grained styles such as intonation are neglected.
Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autoregressive models.
Improving EEG-based Emotion Recognition by Fusing Time-frequency And Spatial Representations
Using deep learning methods to classify EEG signals can accurately identify people's emotions.
Lorentz Equivariant Model for Knowledge-Enhanced Hyperbolic Collaborative Filtering
Introducing prior auxiliary information from the knowledge graph (KG) to assist the user-item graph can improve the comprehensive performance of the recommender system.
HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation
To mitigate this issue, we propose Hierarchical Spatial-Temporal transFormers (HSTFormer) to capture multi-level joints' spatial-temporal correlations from local to global gradually for accurate 3D HPE.
A deep local attention network for pre-operative lymph node metastasis prediction in pancreatic cancer via multiphase CT imaging
Lymph node (LN) metastasis status is one of the most critical prognostic and cancer staging factors for patients with resectable pancreatic ductal adenocarcinoma (PDAC), or in general, for any types of solid malignant tumors.
Syntax-Guided Domain Adaptation for Aspect-based Sentiment Analysis
In this work, we propose a novel Syntax-guided Domain Adaptation Model, named SDAM, for more effective cross-domain ABSA.
Adapitch: Adaption Multi-Speaker Text-to-Speech Conditioned on Pitch Disentangling with Untranscribed Data
In this paper, we proposed Adapitch, a multi-speaker TTS method that makes adaptation of the supervised module with untranscribed data.
Improving Speech Representation Learning via Speech-level and Phoneme-level Masking Approach
In this work, we proposed two kinds of masking approaches: (1) speech-level masking, making the model to mask more speech segments than silence segments, (2) phoneme-level masking, forcing the model to mask the whole frames of the phoneme, instead of phoneme pieces.
MetaSpeech: Speech Effects Switch Along with Environment for Metaverse
Metaverse expands the physical world to a new dimension, and the physical environment and Metaverse environment can be directly connected and entered.
Improving Imbalanced Text Classification with Dynamic Curriculum Learning
Recent advances in pre-trained language models have improved the performance for text classification tasks.
Semi-Supervised Learning Based on Reference Model for Low-resource TTS
Most previous neural text-to-speech (TTS) methods are mainly based on supervised learning methods, which means they depend on a large training dataset and hard to achieve comparable performance under low-resource conditions.
Linguistic-Enhanced Transformer with CTC Embedding for Speech Recognition
We also find that in joint CTC-Attention ASR model, decoder is more sensitive to linguistic information than acoustic information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning
Estimating age from a single speech is a classic and challenging topic.
Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation
Unsupervised representation learning for speech audios attained impressive performances for speech recognition tasks, particularly when annotated speech is limited.
Pre-Avatar: An Automatic Presentation Generation Framework Leveraging Talking Avatar
Since the beginning of the COVID-19 pandemic, remote conferencing and school-teaching have become important tools.
Pose Guided Human Image Synthesis with Partially Decoupled GAN
Most existing methods encode the texture of the whole reference human image into a latent space, and then utilize a decoder to synthesize the image texture of the target pose.
RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery
The extraction of sequence patterns from a collection of functionally linked unlabeled DNA sequences is known as DNA motif discovery, and it is a key task in computational biology.
Machine Unlearning Method Based On Projection Residual
Even when data is removed from the dataset, the effects of these data persist in the model.
Blur the Linguistic Boundary: Interpreting Chinese Buddhist Sutra in English via Neural Machine Translation
Buddhism is an influential religion with a long-standing history and profound philosophy.
Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition
For multi-head attention in Transformer ASR, it is not easy to model monotonic alignments in different heads.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Boosting Star-GANs for Voice Conversion with Contrastive Discriminator
Nonparallel multi-domain voice conversion methods such as the StarGAN-VCs have been widely applied in many scenarios.
Accurate and Robust Lesion RECIST Diameter Prediction and Segmentation with Transformers
To the best of our knowledge, it is the first time to use keypoint regression for RECIST diameter prediction.
Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation
Deep neural networks can capture the intricate interaction history information between queries and documents, because of their many complicated nonlinear units, allowing them to provide correct search recommendations.
ODformer: Spatial-Temporal Transformers for Long Sequence Origin-Destination Matrix Forecasting Against Cross Application Scenario
Origin-Destination (OD) matrices record directional flow data between pairs of OD regions.
TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training
In this paper, a novel voice conversion framework, named $\boldsymbol T$ext $\boldsymbol G$uided $\boldsymbol A$utoVC(TGAVC), is proposed to more effectively separate content and timbre from speech, where an expected content embedding produced based on the text transcriptions is designed to guide the extraction of voice content.
Uncertainty Calibration for Deep Audio Classifiers
In this work, we investigate the uncertainty calibration for deep audio classifiers.
SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning
Speech emotion recognition (SER) has many challenges, but one of the main challenges is that each framework does not have a unified standard.
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion
Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme.
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval
To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage.
A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy
Currently, the federated graph neural network (GNN) has attracted a lot of attention due to its wide applications in reality without violating the privacy regulations.
Micro-Expression Recognition Based on Attribute Information Embedding and Cross-modal Contrastive Learning
Micro-expressions have the characteristics of short duration and low intensity, and it is difficult to train a high-performance classifier with the limited number of existing micro-expressions.
Speech Augmentation Based Unsupervised Learning for Keyword Spotting
In our experiments, with augmentation based unsupervised learning, our KWS model achieves better performance than other unsupervised methods, such as CPC, APC, and MPC.
Adaptive Activation Network For Low Resource Multilingual Speech Recognition
The existing models mostly established a bottleneck (BN) layer by pre-training on a large source language, and transferring to the low resource target language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Cali3F: Calibrated Fast Fair Federated Recommendation System
Specific to recommendation systems, many federated recommendation algorithms have been proposed to realize the privacy-preserving collaborative recommendation.
DT-SV: A Transformer-based Time-domain Approach for Speaker Verification
Therefore, we propose an approach to derive utterance-level speaker embeddings via a Transformer architecture that uses a novel loss function named diffluence loss to integrate the feature information of different Transformer layers.
A Fair Federated Learning Framework With Reinforcement Learning
More importantly, we apply the Gini coefficient and validation accuracy of clients in each communication round to construct a reward function for the reinforcement learning.
Federated Split BERT for Heterogeneous Text Classification
To address this issue, we propose a framework, FedSplitBERT, which handles heterogeneous data and decreases the communication cost by splitting the BERT encoder layers into local part and global part.
Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information
Non-negative matrix factorization (NMF) based topic modeling is widely used in natural language processing (NLP) to uncover hidden topics of short text documents.
Leveraging Causal Inference for Explainable Automatic Program Repair
The experiments on four programming languages (Java, C, Python, and JavaScript) show that CPR can generate causal graphs for reasonable interpretations and boost the performance of bug fixing in automatic program repair.
QSpeech: Low-Qubit Quantum Speech Application Toolkit
However, Quantum Neural Network (QNN) running on low-qubit quantum devices would be difficult since it is based on Variational Quantum Circuit (VQC), which requires many qubits.
Augmentation-induced Consistency Regularization for Classification
In this paper, we propose a consistency regularization framework based on data augmentation, called CR-Aug, which forces the output distributions of different sub models generated by data augmentation to be consistent with each other.
Adaptive Few-Shot Learning Algorithm for Rare Sound Event Detection
In this work, we propose a novel task-adaptive module which is easy to plant into any metric-based few-shot learning frameworks.
Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance
And the second is that the training of GAN is unstable and slow to converge, such as model collapse.
Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning
However, due to the slow sample collection and poor sample exploration, there are still some problems in multi-agent reinforcement learning, such as unstable model iteration and low training efficiency.
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction.
Localized Adversarial Domain Generalization
Adversarial domain generalization is a popular approach to DG, but conventional approaches (1) struggle to sufficiently align features so that local neighborhoods are mixed across domains; and (2) can suffer from feature space over collapse which can threaten generalization performance.
Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition
The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters.
A Study of Different Ways to Use The Conformer Model For Spoken Language Understanding
In this paper, we compare different ways to combine ASR and NLU, in particular using a single Conformer model with different ways to use its components, to better understand the strengths and weaknesses of each approach.
Self-Attention for Incomplete Utterance Rewriting
In this paper, we propose a novel method by directly extracting the coreference and omission relationship from the self-attention weight matrix of the transformer instead of word embeddings and edit the original text accordingly to generate the complete utterance.
Towards Speaker Age Estimation with Label Distribution Learning
To address this, we utilize the ambiguous information among the age labels, convert each age label into a discrete label distribution and leverage the label distribution learning (LDL) method to fit the data.
VU-BERT: A Unified framework for Visual Dialog
The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog history.
r-G2P: Evaluating and Enhancing Robustness of Grapheme to Phoneme Conversion by Controlled noise introducing and Contextual information incorporation
In this paper, we aim to evaluate and enhance the robustness of G2P models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Lumbar Bone Mineral Density Estimation from Chest X-ray Images: Anatomy-aware Attentive Multi-ROI Modeling
Osteoporosis is a common chronic metabolic bone disease often under-diagnosed and under-treated due to the limited access to bone mineral density (BMD) examinations, e. g. via Dual-energy X-ray Absorptiometry (DXA).
Coherence Learning using Keypoint-based Pooling Network for Accurately Assessing Radiographic Knee Osteoarthritis
In this work, we propose a computer-aided diagnosis approach to provide more accurate and consistent assessments of both composite and fine-grained OA grades simultaneously.
Comprehensive and Clinically Accurate Head and Neck Organs at Risk Delineation via Stratified Deep Learning: A Large-scale Multi-Institutional Study
Accurate organ at risk (OAR) segmentation is critical to reduce the radiotherapy post-treatment complications.
A deep learning pipeline for localization, differentiation, and uncertainty estimation of liver lesions using multi-phasic and multi-sequence MRI
Results: the proposed CAD solution achieves a mean F1 score of 0. 62, outperforming the abdominal radiologist (0. 47), matching the junior hepatology radiologist (0. 61), and underperforming the senior hepatology radiologist (0. 68).
Accurate and Generalizable Quantitative Scoring of Liver Steatosis from Ultrasound Images via Scalable Deep Learning
High diagnostic performance was observed across all viewpoints: area under the curves of the ROC to classify >=mild, >=moderate, =severe steatosis grades were 0. 85, 0. 90, and 0. 93, respectively.
Multi-institutional Validation of Two-Streamed Deep Learning Method for Automated Delineation of Esophageal Gross Tumor Volume using planning-CT and FDG-PETCT
252 institution-1 patients had a treatment planning-CT (pCT) and a pair of diagnostic FDG-PETCT; 354 patients from other 3 institutions had only pCT.
ClsVC: Learning Speech Representations with two different classification tasks.
Voice conversion(VC) aims to convert one speaker's voice to generate a new speech as it is said by another speaker.
SAME: Deformable Image Registration based on Self-supervised Anatomical Embeddings
In this work, we introduce a fast and accurate method for unsupervised 3D medical image registration.
DeepStationing: Thoracic Lymph Node Station Parsing in CT Scans using Anatomical Context Encoding and Key Organ Auto-Search
Lymph node station (LNS) delineation from computed tomography (CT) scans is an indispensable step in radiation oncology workflow.
A Flexible Three-Dimensional Hetero-phase Computed Tomography Hepatocellular Carcinoma (HCC) Detection Algorithm for Generalizable and Practical HCC Screening
We develop a flexible three-dimensional deep algorithm, called hetero-phase volumetric detection (HPVD), that can accept any combination of contrast-phase inputs and with adjustable sensitivity depending on the clinical purpose.
ICAF: Iterative Contrastive Alignment Framework for Multimodal Abstractive Summarization
Integrating multimodal knowledge for abstractive summarization task is a work-in-progress research area, with present techniques inheriting fusion-then-generation paradigm.
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check
Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters.
Ranked #1 on
Chinese Spell Checking
on SIGHAN 2015
A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization
Disease is one of the fundamental entities in biomedical research.
PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning
This paper describes the winning system for subtask 2 and the second-placed system for subtask 1 in SemEval 2021 Task 4: ReadingComprehension of Abstract Meaning.
Speech2Video: Cross-Modal Distillation for Speech to Video Generation
This paper investigates a novel task of talking face video generation solely from speeches.
Federated Learning with Dynamic Transformer for Text to Speech
Text to speech (TTS) is a crucial task for user interaction, but TTS model training relies on a sizable set of high-quality original datasets.
Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive.
Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
We evaluated the proposed methods on phoneme classification and speaker recognition tasks.
Leveraging Large-Scale Weakly Labeled Data for Semi-Supervised Mass Detection in Mammograms
Starting with a fully supervised model trained on the data with pixel-level masks, the proposed framework iteratively refines the model itself using the entire weakly labeled data (image-level soft label) in a self-training fashion.
An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition
For the analyses, we plot attention weight distributions in the decoders to visualize the relationships between token-level acoustic embeddings.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Multi-Grained Knowledge Distillation for Named Entity Recognition
To maximally assimilate knowledge into the student model, we propose a multi-grained distillation scheme, which integrates cross entropy involved in conditional random field (CRF) and fuzzy learning. To validate the effectiveness of our proposal, we conducted a comprehensive evaluation on five NER benchmarks, reporting cross-the-board performance gains relative to competing prior-arts.
Lesion Segmentation and RECIST Diameter Prediction via Click-driven Attention and Dual-path Connection
PDNet learns comprehensive and representative deep image features for our tasks and produces more accurate results on both lesion segmentation and RECIST diameter prediction.
Weakly-Supervised Universal Lesion Segmentation with Regional Level Set Loss
Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS).
Scalable Semi-supervised Landmark Localization for X-ray Images using Few-shot Deep Adaptive Graph
It first trains a DAG model on the labeled data and then fine-tunes the pre-trained model on the unlabeled data with a teacher-student SSL mechanism.
An Alignment-Agnostic Model for Chinese Text Error Correction
Most existing models based on detect-correct framework can correct mistaken characters errors, but they cannot deal with missing or redundant characters.
Learning from Subjective Ratings Using Auto-Decoded Deep Latent Embeddings
Importantly, ADDLE does not expect multiple raters per image in training, meaning it can readily learn from data mined from hospital archives.
Opportunistic Screening of Osteoporosis Using Plain Film Chest X-ray
In this paper, we propose a method to predict BMD from Chest X-ray (CXR), one of the most common, accessible, and low-cost medical image examinations.
Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data
Lesion detection serves a critical role in early diagnosis and has been well explored in recent years due to methodological advancesand increased data availability.
Semi-Supervised Learning for Bone Mineral Density Estimation in Hip X-ray Images
Specifically, we propose a new semi-supervised self-training algorithm to train the BMD regression model using images coupled with DEXA measured BMDs and unlabeled images with pseudo BMDs.
Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining
(2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification.
Efficient Client Contribution Evaluation for Horizontal Federated Learning
In this paper an efficient method is proposed to evaluate the contributions of federated participants.
A Quantitative Metric for Privacy Leakage in Federated Learning
In addition, using the proposed metric, we investigate the influential factors of risk level.
Enhancing Data-Free Adversarial Distillation with Activation Regularization and Virtual Interpolation
We add an activation regularizer and a virtual interpolation method to improve the data generation efficiency.
Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
We propose a novel network structure, called Memory-Self-Attention (MSA) Transducer.
Joint Intent Detection And Slot Filling Based on Continual Learning Model
Slot filling and intent detection have become a significant theme in the field of natural language understanding.
NVAE-GAN Based Approach for Unsupervised Time Series Anomaly Detection
In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).
Structure Controllable Text Generation
Controlling the presented forms (or structures) of generated text are as important as controlling the generated contents during neural text generation.
KETG: A Knowledge Enhanced Text Generation Framework
Embedding logical knowledge information into text generation is a challenging NLP task.
Knowledge Distillation with Adaptive Asymmetric Label Sharpening for Semi-supervised Fracture Detection in Chest X-rays
Exploiting available medical records to train high performance computer-aided diagnosis (CAD) models via the semi-supervised learning (SSL) setting is emerging to tackle the prohibitively high labor costs involved in large-scale medical image annotations.
Image Inpainting Guided by Coherence Priors of Semantics and Textures
In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner.
Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization
This paper proposes a robust and accurate method that effectively exploits the anatomical knowledge of the spine to facilitate vertebra localization and identification.
Fully-Automated Liver Tumor Localization and Characterization from Multi-Phase MR Volumes Using Key-Slice ROI Parsing: A Physician-Inspired Approach
Using radiological scans to identify liver tumors is crucial for proper patient treatment.
Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
In this work, we present deep lesion tracker (DLT), a deep learning approach that uses both appearance- and anatomical-based signals.
3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
We exploit the feasibility to distinguish pancreatic ductal adenocarcinoma (PDAC) from the nine other nonPDAC masses using multi-phase CT imaging.
A New Window Loss Function for Bone Fracture Detection and Localization in X-ray Images with Point-based Annotation
Object detection methods are widely adopted for computer-aided diagnosis using medical images.
SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
We introduce such an approach, called Self-supervised Anatomical eMbedding (SAM).
GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
Graph-to-sequence model is proposed and formed by a graph encoder and an attentional decoder.
MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution
In this paper, an efficient network, named location-variable convolution, is proposed to model the dependencies of waveforms.
Contour Transformer Network for One-shot Segmentation of Anatomical Structures
In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism.
Semantic SLAM with Autonomous Object-Level Data Association
It is often desirable to capture and map semantic information of an environment during simultaneous localization and mapping (SLAM).
Empirical Studies of Institutional Federated Learning For Natural Language Processing
It is also found that the FL models are sensitive to data load balancedness among client datasets.
CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition
The information are used to extract acoustic representation for each token in parallel, referred to as token-level acoustic embedding which substitutes the word embedding in autoregressive transformer (AT) to achieve parallel generation in decoder.
Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores
One of the challenges of the Optical Music Recognition task is to transcript the symbols of the camera-captured images into digital music notations.
Melody Classification based on Performance Event Vector and BRNN
We proposed a model for the Conference of Music and Technology (CSMT2020) data challenge of melody classification.
FedSmart: An Auto Updating Federated Learning Optimization Mechanism
Federated learning has made an important contribution to data privacy-preserving.
Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
In order to increase the width of network and enrich representation of features, the inception blocks with dilation are adopted.
User-Guided Domain Adaptation for Rapid Annotation from User Interactions: A Study on Pathological Liver Segmentation
Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models.
Learning from Multiple Datasets with Heterogeneous and Partial Labels for Universal Lesion Detection in CT
For example, DeepLesion is such a large-scale CT image dataset with lesions of various types, but it also has many unlabeled lesions (missing annotations).
Deep Volumetric Universal Lesion Detection using Light-Weight Pseudo 3D Convolution and Surface Point Regression
Identifying, measuring and reporting lesions accurately and comprehensively from patient CT scans are important yet time-consuming procedures for physicians.
Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network
Specifically, we first utilize a 3D convolutional neural network with ROI-pooling to extract the GTV$_{LN}$'s instance-wise appearance features.
Lymph Node Gross Tumor Volume Detection and Segmentation via Distance-based Gating using 3D CT/PET Imaging in Radiotherapy
Finding, identifying and segmenting suspicious cancer metastasized lymph nodes from 3D multi-modality imaging is a clinical task of paramount importance.
DeepPrognosis: Preoperative Prediction of Pancreatic Cancer Survival and Surgical Margin via Contrast-Enhanced CT Imaging
We present a multi-task CNN to accomplish both tasks of outcome and margin prediction where the network benefits from learning the tumor resection margin related features to improve survival prediction.
Robust Pancreatic Ductal Adenocarcinoma Segmentation with Multi-Institutional Multi-Phase Partially-Annotated CT Scans
A student model is trained on both manual and pseudo annotated multi-phase images.
A Real-time Robot-based Auxiliary System for Risk Evaluation of COVID-19 Infection
The structure of our model are maintained concise to be implemented for real-time applications.
Large-scale Transfer Learning for Low-resource Spoken Language Understanding
However, the increased complexity of a model can also introduce high risk of over-fitting, which is a major challenge in SLU tasks due to the limitation of available data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Prosody Learning Mechanism for Speech Synthesis System Without Text Length Limit
Recent neural speech synthesis systems have gradually focused on the control of prosody to improve the quality of synthesized speech, but they rarely consider the variability of prosody and the correlation between prosody and semantics together.
MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection
The MLNET leveraged multi-branches to extract multiple contextual speech information and investigated an effective attention block to weight the most crucial parts of the context for final classification.
Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification
We borrow the idea of neural architecture search(NAS) for the textindependent speaker verification task.
Neural Architecture Search
Text-Independent Speaker Verification
DREAM: A Dynamic Relational-Aware Model for Social Recommendation
In this paper, we propose a unified framework named Dynamic RElation Aware Model (DREAM) for social recommendation, which tries to model both users dynamic interests and their friends temporal influences.
Reliable Liver Fibrosis Assessment from Ultrasound using Global Hetero-Image Fusion and View-Specific Parameterization
Ultrasound (US) is a critical modality for diagnosing liver fibrosis.
UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
The problem of session-based recommendation aims to predict user next actions based on session histories.
A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users
Specifically, we first try to learn more effective user and item latent features in both source and target domains.
DCDIR: A Deep Cross-Domain Recommendation System for Cold Start Users in Insurance Domain
In this paper, we propose a Deep Cross Domain Insurance Recommendation System (DCDIR) for cold start users.
One Click Lesion RECIST Measurement and Segmentation on CT Scans
Based on the results of the first network, the second one refines the lesion segmentation and RECIST estimation.
E$^2$Net: An Edge Enhanced Network for Accurate Liver and Tumor Segmentation on CT Scans
We introduce an edge prediction module in E$^2$Net and design an edge distance map between liver and tumor boundaries, which is used as an extra supervision signal to train the edge enhanced network.
Learning to Segment Anatomical Structures Accurately from One Exemplar
Accurate segmentation of critical anatomical structures is at the core of medical image analysis.
Anatomy-Aware Siamese Network: Exploiting Semantic Asymmetry for Accurate Pelvic Fracture Detection in X-ray Images
A new contrastive feature learning component in our Siamese network is designed to optimize the deep image features being more salient corresponding to the underlying semantic asymmetries (caused by pelvic fracture occurrences).
Contextualized Emotion Recognition in Conversation as Sequence Tagging
Emotion recognition in conversation (ERC) is an important topic for developing empathetic machines in a variety of areas including social opinion mining, health-care and so on.
Ranked #2 on
Emotion Recognition in Conversation
on DailyDialog
Emotion Classification
Emotion Recognition in Conversation
+1
Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning
To this end, we propose a fully-automated and multi-stage liver tumor characterization framework designed for dynamic contrast computed tomography (CT).
Universal Lesion Detection by Learning from Multiple Heterogeneously Labeled Datasets
First, we learn a multi-head multi-task lesion detector using all datasets and generate lesion proposals on DeepLesion.
Ranked #5 on
Medical Object Detection
on DeepLesion
(using extra training data)
Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation
In medical imaging, organ/pathology segmentation models trained on current publicly available and fully-annotated datasets usually do not well-represent the heterogeneous modalities, phases, pathologies, and clinical scenarios encountered in real environments.
Detecting Scatteredly-Distributed, Small, andCritically Important Objects in 3D OncologyImaging via Decision Stratification
We focus on the detection and segmentation of oncology-significant (or suspicious cancer metastasized) lymph nodes (OSLNs), which has not been studied before as a computational task.
JSSR: A Joint Synthesis, Segmentation, and Registration System for 3D Multi-Modal Image Alignment of Large-scale Pathological CT Scans
We extensively evaluate our JSSR system on a large-scale medical image dataset containing 1, 485 patient CT imaging studies of four different phases (i. e., 5, 940 3D CT scans with pathological livers) on the registration, segmentation and synthesis tasks.
Organ at Risk Segmentation for Head and Neck Cancer using Stratified Learning and Neural Architecture Search
This is the goal of our work, where we introduce stratified organ at risk segmentation (SOARS), an approach that stratifies OARs into anchor, mid-level, and small & hard (S&H) categories.
Structured Landmark Detection via Topology-Adapting Deep Graph Learning
Image landmark detection aims to automatically identify the locations of predefined fiducial points.
Ranked #4 on
Face Alignment
on COFW-68
MDCNN-SID: Multi-scale Dilated Convolution Network for Singer Identification
Most singer identification methods are processed in the frequency domain, which potentially leads to information loss during the spectral transformation.
BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
One-Shot methods have evolved into one of the most popular methods in Neural Architecture Search (NAS) due to weight sharing and single training of a supernet.
Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge.
GraphTTS: graph-to-sequence modelling in neural text-to-speech
This paper leverages the graph-to-sequence method in neural text-to-speech (GraphTTS), which maps the graph embedding of the input sequence to spectrograms.
A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder
Recently, the speaker clustering model based on aggregation hierarchy cluster (AHC) is a common method to solve two main problems: no preset category number clustering and fix category number clustering.
AlignTTS: Efficient Feed-Forward Text-to-Speech System without Explicit Alignment
Targeting at both high efficiency and performance, we propose AlignTTS to predict the mel-spectrum in parallel.
Bone Suppression on Chest Radiographs With Adversarial Learning
Dual-energy (DE) chest radiography provides the capability of selectively imaging two clinically relevant materials, namely soft tissues, and osseous structures, to better characterize a wide variety of thoracic pathology and potentially improve diagnosis in posteroanterior (PA) chest radiographs.
Weakly Supervised Lesion Co-segmentation on CT Scans
In this work, we propose a weakly-supervised co-segmentation model that first generates pseudo-masks from the RECIST slices and uses these as training labels for an attention-based convolutional neural network capable of segmenting common lesions from a pair of CT scans.
Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation
Lesion segmentation on computed tomography (CT) scans is an important step for precisely monitoring changes in lesion/tumor growth.
Lesion Harvester: Iteratively Mining Unlabeled Lesions and Hard-Negative Examples at Scale
This is the goal of our work, where we develop a powerful system to harvest missing lesions from the DeepLesion dataset at high precision.
Nanoconfined, dynamic electrolyte gating and memory effects in multilayered graphene-based membranes
Multilayered graphene-based nanoporous membranes with electrolyte incorporated between individual sheets is a unique nano-heterostructure system in which nanoconfined electrons in graphene and ions confined in between sheets are intimately coupled throughout the entire membrane.
Mesoscale and Nanoscale Physics Materials Science Soft Condensed Matter Applied Physics Chemical Physics
An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation
In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation.
Domain Fingerprints for No-reference Image Quality Assessment
Human fingerprints are detailed and nearly unique markers of human identity.
MOD: A Deep Mixture Model with Online Knowledge Distillation for Large Scale Video Temporal Concept Localization
In this paper, we present and discuss a deep mixture model with online knowledge distillation (MOD) for large-scale video temporal concept localization, which is ranked 3rd in the 3rd YouTube-8M Video Understanding Challenge.
A Quality-Diversity Controllable GAN for Text Generation
Text generation is a critical and difficult natural language processing task.
CT Data Curation for Liver Patients: Phase Recognition in Dynamic Contrast-Enhanced CT
This is the focus of our work, where we present a principled data curation tool to extract multi-phase CT liver studies and identify each scan's phase from a real-world and heterogenous hospital PACS dataset.
Accurate Esophageal Gross Tumor Volume Segmentation in PET/CT using Two-Stream Chained 3D Deep Network Fusion
Gross tumor volume (GTV) segmentation is a critical step in esophageal cancer radiotherapy treatment planning.
Deep Esophageal Clinical Target Volume Delineation using Encoded 3D Spatial Context of Tumors, Lymph Nodes, and Organs At Risk
Clinical target volume (CTV) delineation from radiotherapy computed tomography (RTCT) images is used to define the treatment areas containing the gross tumor volume (GTV) and/or sub-clinical malignant disease for radiotherapy (RT).
Weakly Supervised Universal Fracture Detection in Pelvic X-rays
In this paper, we propose a two-stage hip and pelvic fracture detection method that executes localized fracture classification using weakly supervised ROI mining.
TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
In this work, we exploit the unsupervised domain adaptation problem for radiology image interpretation across domains.
A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics
This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody.