22 citations · 23 across the 13 of their papers we have counts for
15 papers
TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight Detection
Bo-Yuan Cheng, Kuan-Yu Chen, Po-Han Huang +2
Existing multimodal video highlight detectors typically assume that visual, audio, and textual streams are continuously available. In practice, however, inputs may suffer from loca…
DuoAD: Leveraging [CLS] Dual Characteristics for Training-Free Few-Shot Anomaly Detection
Jyun-Ze Tang, Po-Han Huang, Ming-Ching Chang +2
Vision foundation models have enabled strong training-free anomaly detection (AD). However, most existing approaches rely primarily on independent local patch features, leaving the…
The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS
Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh +5
Current bias evaluations in Instruction Text-to-Speech (ITTS) often rely on univariate testing, overlooking the compositional structure of social cues. In this work, we investigate…
Dual-Process Scaffold Reasoning for Enhancing LLM Code Debugging
Po-Chung Hsieh, Chin-Po Chen, Jeng-Lin Li +1
Recent LLMs have demonstrated sophisticated problem-solving capabilities on various benchmarks through advanced reasoning algorithms. However, the key research question of identify…
How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen
Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextu…
Bloodroot: When Watermarking Turns Poisonous For Stealthy Backdoor
Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li +1
Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model out…
PatchEAD: Unifying Industrial Visual Prompting Frameworks for Patch-Exclusive Anomaly Detection
Po-Han Huang, Jeng-Lin Li, Po-Hsuan Huang +2
Industrial anomaly detection is increasingly relying on foundation models, aiming for strong out-of-distribution generalization and rapid adaptation in real-world deployments. Nota…
Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detection
Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen
Out-of-distribution (OOD) detection ensures safe and reliable model deployment. Contemporary OOD algorithms using geometry projection can detect OOD or adversarial samples from cle…
SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
Kuan-Yu Chen, Jeng-Lin Li, De-Yan Lu +1
With the fast development of zero-shot text-to-speech technologies, it is possible to generate high-quality speech signals that are indistinguishable from the real ones. Speech edi…
Who Brings the Frisbee: Probing Hidden Hallucination Factors in Large Vision-Language Model via Causality Analysis
Po-Hsuan Huang, Jeng-Lin Li, Chin-Po Chen +2
Recent advancements in large vision-language models (LVLM) have significantly enhanced their ability to comprehend visual inputs alongside natural language. However, a major challe…
Profiling Patient Transcript Using Large Language Model Reasoning Augmentation for Alzheimer's Disease Detection
Chin-Po Chen, Jeng-Lin Li
Alzheimer's disease (AD) stands as the predominant cause of dementia, characterized by a gradual decline in speech and language capabilities. Recent deep-learning advancements have…
Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen
Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, V…
Improving the Robustness and Clinical Applicability of Automatic Respiratory Sound Classification Using Deep Learning-Based Audio Enhancement: Algorithm Development and Validation
Jing-Tong Tzeng, Jeng-Lin Li, Huan-Yu Chen +5
Deep learning techniques have shown promising results in the automatic classification of respiratory sounds. However, accurately distinguishing these sounds in real-world noisy con…
A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective
Jeng-Lin Li, Chih-Fan Hsu, Ming-Ching Chang +1
Recent artificial intelligence (AI) technologies show remarkable evolution in various academic fields and industries. However, in the real world, dynamic data lead to principal cha…
Improving Limited Supervised Foot Ulcer Segmentation Using Cross-Domain Augmentation
Shang-Jui Kuo, Po-Han Huang, Chia-Ching Lin +2
Diabetic foot ulcers pose health risks, including higher morbidity, mortality, and amputation rates. Monitoring wound areas is crucial for proper care, but manual segmentation is s…