Search Results for author:
Found 42 papers, 15 papers with code
Mapping Urban Villages in China: Progress and Challenges
We also address the challenges and future directions for further research.
Bridging Domain Gaps between Pretrained Multimodal Models and Recommendations
With the explosive growth of multimodal content online, pre-trained visual-language models have shown great potential for multimodal recommendation.
Fusion of Millimeter-wave Radar and Pulse Oximeter Data for Low-burden Diagnosis of Obstructive Sleep Apnea-Hypopnea Syndrome
Objective: The aim of the study is to develop a novel method for improved diagnosis of obstructive sleep apnea-hypopnea syndrome (OSAHS) in clinical or home settings, with the focus on achieving diagnostic performance comparable to the gold-standard polysomnography (PSG) with significantly reduced monitoring burden.
Advancing Singlish Understanding: Bridging the Gap with Datasets and Multimodal Models
Singlish, a Creole language rooted in English, is a key focus in linguistic research within multilingual and multicultural contexts.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
SS-CTML: Self-Supervised Cross-Task Mutual Learning for CT Image Reconstruction
Considering that the ultimate goals of the three tasks are all to reconstruct high-quality CT images, we therefore construct a set of cross-task mutual learning objectives for the three tasks, in which way, the three neural networks can be self-supervised optimized by learning from each other.
SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models
Current vision-language models may incorporate single-dimensional spatial cues, such as depth, object boundary, and basic spatial directions (e. g. left, right, front, back), yet often lack the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications.
MERaLiON-AudioLLM: Bridging Audio and Language with Large Language Models
We introduce MERaLiON-AudioLLM (Multimodal Empathetic Reasoning and Learning in One Network), the first speech-text model tailored for Singapore's multilingual and multicultural landscape.
Importance Sampling With Stochastic Particle Flow and Diffusion Optimization
Recently proposed stochastic PFL introduces a diffusion term in the ordinary differential equation (ODE) that describes particle motion.
Detection of Sleep Apnea-Hypopnea Events Using Millimeter-wave Radar and Pulse Oximeter
Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a sleep-related breathing disorder associated with significant morbidity and mortality worldwide.
Deep Learning-based Automated Diagnosis of Obstructive Sleep Apnea and Sleep Stage Classification in Children Using Millimeter-wave Radar and Pulse Oximeter
Study Objectives: To evaluate the agreement between the millimeter-wave radar-based device and polysomnography (PSG) in diagnosis of obstructive sleep apnea (OSA) and classification of sleep stage in children.
MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders
The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text.
Particle Flows for Source Localization in 3-D Using TDOA Measurements
Our numerical results demonstrate that the proposed method can correctly determine the number of sources and provide accurate location estimates.
A Survey and Evaluation of Adversarial Attacks for Object Detection
Deep learning models excel in various computer vision tasks but are susceptible to adversarial examples-subtle perturbations in input data that lead to incorrect predictions.
Perception Helps Planning: Facilitating Multi-Stage Lane-Level Integration via Double-Edge Structures
In this work, we endeavor to integrate the perception of these elements into the planning task.
AudioBench: A Universal Benchmark for Audio Large Language Models
We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs).
Ranked #1 on
Audio Scene Understanding
on Clotho-AQA
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1, 300 indigenous languages and a population of 671 million people.
Evidentially Calibrated Source-Free Time-Series Domain Adaptation with Temporal Imputation
MAPU addresses the critical challenge of temporal consistency by introducing a novel temporal imputation task.
Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-Training
For adaptation, we propose the Co-learn algorithm to improve target pseudolabel quality collaboratively through the source model and a pre-trained feature extractor.
Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
UniSSDA is at the intersection of Universal Domain Adaptation (UniDA) and Semi-Supervised Domain Adaptation (SSDA): the UniDA setting does not allow for fine-grained categorization of target private classes not represented in the source domain, while SSDA focuses on the restricted closed-set setting where source and target label spaces match exactly.
Pixel Adapter: A Graph-Based Post-Processing Approach for Scene Text Image Super-Resolution
Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss ($\mathcal{L}_{lca}$) to enhance the model's perception of details.
Pixel-wise Graph Attention Networks for Person Re-identification
Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet).
DeepMA: End-to-end Deep Multiple Access for Wireless Image Transmission in Semantic Communication
Semantic communication is a new paradigm that exploits deep learning models to enable end-to-end communications processes, and recent studies have shown that it can achieve better noise resiliency compared with traditional communication schemes in a low signal-to-noise (SNR) regime.
Active Planning for Cooperative Localization: A Fisher Information Approach
A numerical case study demonstrates the intelligent behavior of a single controlled anchor in a 3-D scenario and the resulting significantly improved localization accuracy.
Multisensor Multiobject Tracking with Improved Sampling Efficiency
We perform a numerical evaluation in a passive acoustic monitoring scenario where multiple sources are tracked in 3-D from 1-D time-difference-of-arrival (TDOA) measurements provided by pairs of hydrophones.
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
We propose to distil useful target domain information through a co-learning strategy to improve target pseudolabel quality for finetuning the source model.
Data Fusion for Radio Frequency SLAM with Robust Sampling
A promising approach to address this problem is to exchange radio signals between mobile agents and static physical anchors (PAs) that bounce off flat surfaces in the indoor environment.
Domain Generalization via Selective Consistency Regularization for Time Series Classification
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains and without access to target domain samples during training.
Few-Shot Adaptation of Pre-Trained Networks for Domain Shift
Recent test-time adaptation methods update batch normalization layers of pre-trained source models deployed in new target environments with streaming data to mitigate such performance degradation.
PointVector: A Vector Representation In Point Cloud Analysis
In point cloud analysis, point-based methods have rapidly developed in recent years.
Ranked #1 on
3D Semantic Segmentation
on OpenTrench3D
Selective Cross-Domain Consistency Regularization for Time Series Domain Generalization
Domain generalization aims to learn models robust to domain shift, with limited source domains at training and without any access to target domain samples except at test time.
Source-Free Few-Shot Domain Adaptation
Test-time adaptation of pre-trained source models with streaming unlabelled target data is an attractive setting that protects the privacy of source data, but it has mini-batch size and class-distribution requirements on the streaming data which might not be desirable in practice.
An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series
Several techniques for multivariate time series anomaly detection have been proposed recently, but a systematic comparison on a common set of datasets and metrics is lacking.
Graph-Based Multiobject Tracking with Embedded Particle Flow
Seamless situational awareness provided by modern radar systems relies on effective methods for multiobject tracking (MOT).
Robust Domain-Free Domain Generalization with Class-aware Alignment
In this paper, we propose Domain-Free Domain Generalization (DFDG), a model-agnostic method to achieve better generalization performance on the unseen test domain without the need for source domain labels.
POLA: Online Time Series Prediction by Adaptive Learning Rates
We propose POLA (Predicting Online by Learning rate Adaptation) to automatically regulate the learning rate of recurrent neural network models to adapt to changing time series patterns across time.
Conformance Checking for a Medical Training Process Using Petri net Simulation and Sequence Alignment
Process Mining has recently gained popularity in healthcare due to its potential to provide a transparent, objective and data-based view on processes.
HALO: Learning to Prune Neural Networks with Shrinkage
Deep neural networks achieve state-of-the-art performance in a variety of tasks by extracting a rich set of features from unstructured data, however this performance is closely tied to model size.
Modeling a Nonlinear Biophysical Trend Followed by Long-Memory Equilibrium with Unknown Change Point
In this paper, we assume that measurements during the trend period are independent deviations from a smooth nonlinear function of time, and that measurements during the equilibrium period are characterized by a simple long memory model.
Applications Quantitative Methods
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
The purpose of these agents is to quickly adapt and/or generalize their notion of physics of interaction in the real world based on certain features about the interacting objects that provide different contexts to the predictive models.
Multi-label Prediction in Time Series Data using Deep Neural Networks
In the most general setting of these types of problems, one or more samples of data across multiple time series can be assigned several concurrent fault labels from a finite, known set and the task is to predict the possibility of fault occurrence over a desired time horizon.
ABACUS: Unsupervised Multivariate Change Detection via Bayesian Source Separation
Change detection involves segmenting sequential data such that observations in the same segment share some desired properties.
Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition
Accurate and computationally efficient means for classifying human activities have been the subject of extensive research efforts.
