Search Results for author:
Found 45 papers, 26 papers with code
Representation Learning of Structured Data for Medical Foundation Models
Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare.
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
We examine critical factors in SSL that impact the budget, including model architecture, model size, and data size.
Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?
State-of-the-art Large Language Models (LLMs) are accredited with an increasing number of different capabilities, ranging from reading comprehension, over advanced mathematical and reasoning skills to possessing scientific knowledge.
MEDSAGE: Enhancing Robustness of Medical Dialogue Summarization to ASR Errors with LLM-generated Synthetic Dialogues
Experimental results show that LLMs can effectively model ASR noise, and incorporating this noisy data into the training process significantly improves the robustness and accuracy of medical dialogue summarization systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
LLMs are not Zero-Shot Reasoners for Biomedical Information Extraction
Large Language Models (LLMs) are increasingly adopted for applications in healthcare, reaching the performance of domain experts on tasks such as question answering and document summarisation.
M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering
There is vivid research on adapting Large Language Models (LLMs) to perform a variety of tasks in high-stakes domains such as healthcare.
Automated Clinical Coding for Outpatient Departments
Computerised clinical coding approaches aim to automate the process of assigning a set of codes to medical records.
MaxEnt Loss: Constrained Maximum Entropy for Calibration under Out-of-Distribution Shift
We present a new loss function that addresses the out-of-distribution (OOD) calibration problem.
PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records
This paper describes PULSAR, our system submission at the ImageClef 2023 MediQA-Sum task on summarising patient-doctor dialogues into clinical records.
PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients' Problems and Data Augmentation with Black-box Large Language Models
Medical progress notes play a crucial role in documenting a patient's hospital journey, including his or her condition, treatment plan, and any updates for healthcare providers.
A Two-Stage Decoder for Efficient ICD Coding
Clinical notes in healthcare facilities are tagged with the International Classification of Diseases (ICD) code; a list of classification codes for medical diagnoses and procedures.
A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond
In this paper, we provide an overview of the different methods for sentence representation learning, focusing mostly on deep learning models.
Mimic-IV-ICD: A new benchmark for eXtreme MultiLabel Classification
Clinical notes are assigned ICD codes - sets of codes for diagnoses and procedures.
Ranked #1 on
Medical Code Prediction
on MIMIC-IV-ICD10-top50
Generating near-infrared facial expression datasets with dimensional affect labels
Facial expression analysis has long been an active research area of computer vision.
Trusted Media Challenge Dataset and User Study
To tackle the issue, we have organized the Trusted Media Challenge (TMC) to explore how Artificial Intelligence (AI) technologies could be leveraged to combat fake media.
Detecting Blurred Ground-based Sky/Cloud Images
To the best of our knowledge, our approach is the first of its kind in the automatic identification of blurred images for ground-based sky/cloud images.
Efficient Facial Expression Analysis For Dimensional Affect Recognition Using Geometric Features
Despite their continued popularity, categorical approaches to affect recognition have limitations, especially in real-life situations.
Morphset:Augmenting categorical emotion datasets with dimensional affect labels using face morphing
Emotion recognition and understanding is a vital component in human-machine interaction.
Forecasting Precipitable Water Vapor Using LSTMs
Long-Short-Term-Memory (LSTM) networks have been used extensively for time series forecasting in recent years due to their ability of learning patterns over different periods of time.
Empirical Analysis of Overfitting and Mode Drop in GAN Training
We examine two key questions in GAN training, namely overfitting and mode drop, from an empirical perspective.
Subjective Quality Assessment of Ground-based Camera Images
Image quality assessment is critical to control and maintain the perceived quality of visual content.
Estimating Solar Irradiance Using Sky Imagers
Unlike pyranometers, such sky images contain information about cloud coverage and can be used to derive cloud movement.
CloudSegNet: A Deep Network for Nychthemeron Cloud Image Segmentation
In the existing literature, however, analysis of daytime and nighttime images is considered separately, mainly because of differences in image characteristics and applications.
Recognition of Advertisement Emotions with Application to Computational Advertising
Advertisements (ads) often contain strong affective content to capture viewer attention and convey an effective message to the audience.
Multi-label Cloud Segmentation Using a Deep Network
Different empirical models have been developed for cloud detection.
Venn GAN: Discovering Commonalities and Particularities of Multiple Distributions
We propose a GAN design which models multiple distributions effectively and discovers their commonalities and particularities.
PersEmoN: A Deep Network for Joint Analysis of Apparent Personality, Emotion and Their Relationship
Apparent personality and emotion analysis are both central to affective computing.
The Unusual Effectiveness of Averaging in GAN Training
We examine two different techniques for parameter averaging in GAN training.
A Deep Network for Arousal-Valence Emotion Prediction with Acoustic-Visual Cues
In this paper, we comprehensively describe the methodology of our submissions to the One-Minute Gradual-Emotion Behavior Challenge 2018.
High-Dynamic-Range Imaging for Cloud Segmentation
It is thus difficult to capture the details of an entire scene with a regular camera in a single shot.
Autoregressive Generative Adversarial Networks
Generative Adversarial Networks (GANs) learn a generative model by playing an adversarial game between a generator and an auxiliary discriminator, which classifies data samples vs. generated ones.
Study of Clear Sky Models for Singapore
The estimation of total solar irradiance falling on the earth's surface is important in the field of solar energy generation and forecasting.
Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
However, during inference the lower layers do not know about high layer features, although they contain contextual high semantics that benefit low layers to adaptively extract informative features for later layers.
Episodic CAMN: Contextual Attention-Based Memory Networks With Iterative Feedback for Scene Labeling
Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification.
Nighttime sky/cloud image segmentation
An accurate segmentation of sky/cloud images is already challenging because of the clouds' non-rigid structure and size, and the lower and less stable illumination of the night sky increases the difficulty.
Design of low-cost, compact and weather-proof whole sky imagers for high-dynamic-range captures
Ground-based whole sky imagers are popular for monitoring cloud formations, which is necessary for various applications.
Cloud Radiative Effect Study Using Sky Camera
weather reporting, climate forecasting, and solar energy generation.
Systematic study of color spaces and components for the segmentation of sky/cloud images
Sky/cloud imaging using ground-based Whole Sky Imagers (WSI) is a cost-effective means to understanding cloud cover and weather patterns.
Rough Set Based Color Channel Selection
Color channel selection is essential for accurate segmentation of sky and clouds in images obtained from ground-based sky cameras.
Short-term prediction of localized cloud motion using ground-based sky imagers
Fine-scale short-term cloud motion prediction is needed for several applications, including solar energy generation and satellite communications.
Detecting Rainfall Onset Using Sky Images
Ground-based sky cameras (popularly known as Whole Sky Imagers) are increasingly used now-a-days for continuous monitoring of the atmosphere.
Color-based Segmentation of Sky/Cloud Images From Ground-based Cameras
Sky/cloud images captured by ground-based cameras (a. k. a.
Machine Learning Techniques and Applications For Ground-based Image Analysis
Ground-based whole sky cameras have opened up new opportunities for monitoring the earth's atmosphere.
Estimation of solar irradiance using ground-based whole sky imagers
Ground-based whole sky imagers (WSIs) can provide localized images of the sky of high temporal and spatial resolution, which permits fine-grained cloud observation.
WAHRSIS: A Low-cost, High-resolution Whole Sky Imager With Near-Infrared Capabilities
Cloud imaging using ground-based whole sky imagers is essential for a fine-grained understanding of the effects of cloud formations, which can be useful in many applications.
