Search

Your search keyword '"Liu, Yen-Ting"' showing total 280 results
Start Over Author "Liu, Yen-Ting"
280 results on '"Liu, Yen-Ting"'

2. Transforming Multi-Concept Attention into Video Summarization

Author

Liu, Yen-Ting, Li, Yu-Jhe, and Wang, Yu-Chiang Frank

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input. In this paper, we propose an novel attention-based framework for video summarization with complex video data. Unlike previous works which only apply attention mechanism on the correspondence between frames, our multi-concept video self-attention (MC-VSA) model is presented to identify informative regions across temporal and concept video features, which jointly exploit context diversity over time and space for summarization purposes. Together with consistency between video and summary enforced in our framework, our model can be applied to both labeled and unlabeled data, making our method preferable to real-world applications. Extensive and complete experiments on two benchmarks demonstrate the effectiveness of our model both quantitatively and qualitatively, and confirms its superiority over the stateof-the-arts.

Published
2020

3. Gender- and age-related differences in foveal pit morphology

Author

Liu, Yen-Ting, Ma, I-Hsin, and Hsieh, Yi-Ting

Subjects
Health
Abstract

Byline: Yen-Ting. Liu, I-Hsin. Ma, Yi-Ting. Hsieh Aims: To measure the foveal pit morphology parameters and evaluate their correlations with age and sex. Settings and Design: A retrospective cross-sectional matched [...]

Published
2024

5. Transforming Multi-concept Attention into Video Summarization

Author

Liu, Yen-Ting, Li, Yu-Jhe, Wang, Yu-Chiang Frank, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ishikawa, Hiroshi, editor, Liu, Cheng-Lin, editor, Pajdla, Tomas, editor, and Shi, Jianbo, editor

Published
2021
Full Text
View/download PDF

7. Rapid and Label-Free Histopathology of Oral Lesions Using Deep Learning Applied to Optical and Infrared Spectroscopic Imaging Data

Author

Confer, Matthew P., primary, Falahkheirkhah, Kianoush, additional, Surendran, Subin, additional, Sunny, Sumsum P., additional, Yeh, Kevin, additional, Liu, Yen-Ting, additional, Sharma, Ishaan, additional, Orr, Andres C., additional, Lebovic, Isabella, additional, Magner, William J., additional, Sigurdson, Sandra Lynn, additional, Aguirre, Alfredo, additional, Markiewicz, Michael R., additional, Suresh, Amritha, additional, Hicks, Wesley L., additional, Birur, Praveen, additional, Kuriakose, Moni Abraham, additional, and Bhargava, Rohit, additional

Published
2024
Full Text
View/download PDF

13. Automated Defect Detection for Mass-Produced Electronic Components Based on YOLO Object Detection Models

Author

Mao, Wei-Lung, Wang, Chun-Chi, Chou, Po-Heng, and Liu, Yen-Ting

Abstract

Since the defect detection of conventional industry components is time-consuming and labor-intensive, it leads to a significant burden on quality inspection personnel and difficult to manage product quality. In this article, we propose an automated defect detection system for the dual in-line package (DIP) that is widely used in industry, using digital camera optics and deep learning (DL)-based model. The two most common defect categories of DIP are examined: $\text {1)}$ surface defects and $\text {2)}$ pin-leg defects. However, the lack of defective component images leads to a challenge for detection tasks. To solve this problem, the ConSinGAN is used to generate a suitable size dataset for training and testing. Four varieties of the you only look once (YOLO) model are investigated (v3, v4, v7, and v9), both in isolation and with the ConSinGAN augmentation. The proposed YOLOv7 with ConSinGAN is superior to the other YOLO versions in accuracy of 95.50%, detection time of 285 ms, and is far superior to threshold-based approaches. In addition, the supervisory control and data acquisition (SCADA) system is developed, and the associated sensor architecture is described. The proposed automated defect detection can be easily established with numerous types of defects or insufficient defect data.

Published
2024
Full Text
View/download PDF

43. A digitally calibrated CMOS transconductor with a 100-MHz bandwidth and 75-dB SFDR

Author

Chang, Soon-Jyh, Lin, Ying-Zu, and Liu, Yen-Ting

Subjects
Operational amplifiers -- Design and construction, Complementary metal oxide semiconductors -- Design and construction, Circuit design, Circuit designer, Integrated circuit design, Business, Computers and office automation industries, Electronics, Electronics and electrical industries
Abstract

This paper proposes a high-speed CMOS transconductor with its linearity enhanced by current--voltage negative feedback. This voltage-to-current converter is mainly composed of two parts: an operational transconductance amplifier and a pair of feedback resistors. The measured spurious-free dynamic range of the transconductor achieves 72.6 dB when the input frequency is 100 MHz. To compensate for common-mode deviation due to process and temperature variation, digital calibration circuits are added. With the proposed calibration scheme, the common-mode voltage deviation is eliminated within 24 clock cycles. Fabricated in TSMC 0.13-[micro]m CMOS process, the transconductor occupies 220 x 160 [micro][m.sup.2] active area and consumes 6 mW from a 1.2-V supply where the calibration circuits only consume 16% of the overall power consumption. Index Terms--High-linearity amplifier, operational transconductance amplifier (OTA), transconductor, voltage-to-current converter.

Published
2008

Catalog

Books, media, physical & digital resources
See catalog results