研究成果 學術論文
智慧醫療，機器學習領域研究
由 AICS 團隊工程師、AI 研發科學家、技術顧問與博士生協作研究成果刊登於各大頂級國際學術會議與期刊。以生技醫療、自然語言處理與電腦視覺三個面向為主題。
研究論文
生技醫療
Unsupervised clustering identified clinically relevant metabolic syndrome endotypes in UK and Taiwan Biobanks
iScience, April 2024
Unsupervised clustering identified clinically relevant metabolic syndrome endotypes in UK and Taiwan Biobanks
iScience, April 2024
Artificial intelligence-generated peripheral blood film images using generative adversarial networks and diffusion models
The American Journal of Hematology, September 2023
Real-World Evaluation of a Semi-Supervised AI Model (ASUS Blade) with the Cellavision DM9600
International Symposium on Technical Innovations in Laboratory Hematology (ISLH), May 2023
Virofree, an Herbal Medicine-Based Formula, Interrupts the Viral Infection of Delta and Omicron Variants of SARS-CoV-2
Frontiers in Pharmacology, July 2022
Artificial Intelligence In Peripheral Blood Films: An Evolving Landscape
The Lancet Haematology, January 2022
Artificial Intelligence-Generated Facial Images for Medical Education
Medical Science Educator, November 2023
From microscope to micropixels: A rapid review of artificial intelligence for the peripheral blood film
Blood Reviews, November 2023
Artificial intelligence generated leukemia cell images
The American Journal of Hematology, July 2023
Artificial intelligence for malaria: Bridging the gap for real world usage
The Lancet Regional Health - Southeast Asia, September 2022
Honeysuckle (Lonicera japonica) and Huangqi (Astragalus membranaceus) suppress SARS-CoV2 entry and COVID-19 related cytokine storm in vitro
Frontiers in Pharmacology, March 2022
自然語言處理
Unveiling the Achilles’ Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models
arXiv preprint, October 2024
A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the ChatGPT Era and Beyond
EACL, March 2024
Few-shot entity linking of food names
Information Processing & Management, September 2023
ADAPTERMIX: Exploring the Efficacy of Mixture of Adapters for Low-Resource TTS Adaptation
InterSpeech, August 2023
Entity Coreference and Co-occurrence Aware Argument Mining from Biomedical Literature
CODI Workshop @ Association for Computational Linguistics (ACL), July 2023
Linear Classifier: An Often-Forgotten Baseline for Text Classification
Association for Computational Linguistics (ACL), July 2023
Ensemble knowledge distillation of self-supervised speech models
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), June 2023
Scientific Document Processing: Challenges for Modern Learning Methods
International Journal on Digital Libraries, March 2023
Can Transformers Reason in Fragments of Natural Language?
Empirical Methods in Natural Language Processing (EMNLP), December 2022
Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022
Parameter Selection: Why We Should Pay More Attention to It
Association for Computational Linguistics (ACL), August 2021
Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation
AAAI Conference on Artificial Intelligence, February 2021
M-QALM: A Benchmark to Assess Clinical Reading Comprehension and Knowledge Recall in Large Language Models via Question Answering
Association for Computational Linguistics (ACL), June 2024
PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records
MEDIQA-Sum @ CLEF, September 2023
Global information-aware argument mining based on a top-down multi-turn QA model
Information Processing & Management, September 2023
PULSAR: Pre-training with Extracted Healthcare Terms for Summarising Patients’ Problems and Data Augmentation with Black-box Large Language Models
BioNLP Workshop @ Association for Computational Linguistics (ACL), July 2023
Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation
Association for Computational Linguistics (ACL), July 2023
A Two-Stage Decoder for Efficient ICD Coding
Association for Computational Linguistics (ACL), July 2023
UDAPTER – Efficient Domain Adaptation Using Adapter
European Chapter of the Association for Computational Linguistics (EACL), May 2023
Improving generalizability of distilled self-supervised speech processing models under distorted settings
IEEE Spoken Language Technology Workshop (SLT), January 2023
Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNN
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022), July 2022
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
Association for Computational Linguistics (ACL), May 2022
Artificial intelligence in peripheral blood films: an evolving landscape
The Lancet Haematology, March 2022
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech
IEEE/ACM Transactions on Audio, Speech, and Language Processing, July 2021
電腦視覺
Efficient Zero-Shot HOI Detection: Enhancing VLM Adaptation with Innovative Prompt Learning
NeurIPS, 2024
NightCC: Nighttime Color Constancy via Adaptive Channel Masking
Computer Vision and Pattern Recognition (CVPR), 2024
Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022
A Pixel-Level Meta-Learner for Weakly Supervised Few-Shot Semantic Segmentation
IEEE Winter Conference on Applications of Computer Vision (WACV), January 2022
ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss
International Conference on Computer Vision (ICCV), October 2021
All Characteristics Preservation: Single Image Dehazing based on Hierarchical Detail Reconstruction Wavelet Decomposition Network
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2021
Self-Supervised Bodymap-to-Appearance Co-Attention for Partial Person Re-Identification
IEEE International Conference on Image Processing (ICIP), September 2021
Meta-Learned Feature Critics for Domain-Generalized Semantic Segmentation
IEEE International Conference on Image Processing (ICIP), September 2021
HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021
S3Net: A Single Stream Structure for Depth Guided Image Relighting
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2021
LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
IEEE International Conference on Robotics and Automation (ICRA), June 2021
Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning
IEEE International Conference on Pattern Recognition (ICPR), January 2021
Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis
IEEE International Conference on Computer Vision (CVPR), June 2020
Y-Net: Multi-Scale Feature Aggregation Network With Wavelet Structure Similarity Loss Function For Single Image Dehazing
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2020
A Multi-domain and Multi-modal Representation Disentangler for Cross-Domain Image Manipulation and Classification
IEEE Transactions on Image Processing, January 2020
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
IEEE International Conference on Computer Vision (ICCV), October 2019
CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection
Computer Vision and Pattern Recognition (CVPR), 2024
Missing Recovery: Single Image Reflection Removal Based on Auxiliary Prior Learning
IEEE Transactions on Image Processing, December 2022
Image data augmentation with unpaired image-to-image camera model translation
IEEE International Conference on Image Processing (ICIP), October 2022
SJDL-Vehicle: Semi-supervised Joint Defogging Learning for Foggy Vehicle Re-identification
AAAI Conference on Artificial Intelligence, February 2022
ContourletNet: A Generalized Rain Removal Architecture Using Multi-Direction Hierarchical Representation
British Machine Vision Conference (BMVC), November 2021
Leveraging Auxiliary Information from EMR for Weakly Supervised Pulmonary Nodule Detection
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), September 2021
Adversarial Teacher-Student Representation Learning for Domain Generalization
Neural Information Processing Systems (NeurIPS), September 2021
Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains
IEEE International Conference on Image Processing (ICIP), September 2021
DesmokeNet: A Two-Stage Smoke Removal Pipeline Based on Self-Attentive Feature Consensus and Multi-Level Contrastive Regularization
IEEE Trans. Circuits and Systems for Video Technology, August 2021
Multi-modal Bifurcated Network for Depth Guided Image Relighting
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), June 2021
Indoor Panorama Planar 3D Reconstruction via Divide and Conquer
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2021
Dual-MTGAN: Stochastic and Deterministic Motion Transfer for Image-to-Video Synthesis
IEEE International Conference on Pattern Recognition (ICPR), January 2021
Wavelet Channel Attention Module With A Fusion Network For Single Image Deraining
IEEE International Conference on Image Processing (ICIP), October 2020
Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment
IEEE International Conference on Computer Vision (CVPR), June 2020
Self-Supervised Deep Learning for Fisheye Image Rectification
IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2020
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation
IEEE International Conference on Computer Vision (ICCV), October 2019
大語言模型
Representation Learning of Structured Data for Medical Foundation Models
Association for Computational Linguistics (ACL), October 2024
自動語音識別
Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models
arXiv preprint, October 2021
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
arXiv preprint, September 2024
Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2024
Noise robust distillation of self-supervised speech models via correlation metrics
IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, December 2023
Dataset-Distillation Generative Model for Speech Emotion Recognition
arXiv preprint, September 2021
On the social bias of speech self-supervised models
arXiv preprint, June 2024
Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models...
IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), December 2023
其他研究領域
Multi-Scale Aggregation with Self-Attention Network for Modeling Electrical Motor Dynamics
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2021
LRG-Net: Lightweight Residual Grid Network for Modeling Electrical Induction Motor Dynamics
European Signal Processing Conference (EUSIPCO), August 2021