Search Results - "Ng, Chun Chet"

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering by Wang, Xinyu, Liu, Yuliang, Shen, Chunhua, Ng, Chun Chet, Luo, Canjie, Jin, Lianwen, Chan, Chee Seng, van den Hengel, Anton, Wang, Liangwei

“…Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are…”
Get full text

Rethinking Long-Tailed Visual Recognition with Dynamic Probability Smoothing and Frequency Weighted Focusing by Nah, Wan Jun, Chet Ng, Chun, Lin, Che-Tsung, Lee, Yeong Khang, Long Kew, Jie, Tan, Zhi Qin, Seng Chan, Chee, Zach, Christopher, Lai, Shang-Hong

“…Deep learning models trained on long-tailed (LT) datasets often exhibit bias towards head classes with high frequency. This paper highlights the limitations of…”
Get full text

ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT by Chng, Chee Kheng, Ding, Errui, Liu, Jingtuo, Karatzas, Dimosthenis, Chan, Chee Seng, Jin, Lianwen, Liu, Yuliang, Sun, Yipeng, Ng, Chun Chet, Luo, Canjie, Ni, Zihan, Fang, ChuanMing, Zhang, Shuaitao, Han, Junyu

“…This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT that consists of three major challenges: i) scene text detection,…”
Get full text

When IC meets text: Towards a rich annotated integrated circuit text dataset by Ng, Chun Chet, Lin, Che-Tsung, Tan, Zhi Qin, Wang, Xinyu, Kew, Jie Long, Chan, Chee Seng, Zach, Christopher

“…Automated Optical Inspection (AOI) is a process that uses cameras to autonomously scan printed circuit boards for quality control. Text is often printed on…”
Get full text

Text in the dark: Extremely low-light text image enhancement by Lin, Che-Tsung, Ng, Chun Chet, Tan, Zhi Qin, Nah, Wan Jun, Wang, Xinyu, Kew, Jie Long, Hsu, Pohao, Lai, Shang Hong, Chan, Chee Seng, Zach, Christopher

“…Extremely low-light text images pose significant challenges for scene text detection. Existing methods enhance these images using low-light image enhancement…”
Get full text

Extremely Low-Light Image Enhancement with Scene Text Restoration by Hsu, Po-Hao, Lin, Che-Tsung, Ng, Chun Chet, Long Kew, Jie, Tan, Mei Yih, Lai, Shang-Hong, Chan, Chee Seng, Zach, Christopher

“…Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally…”
Get full text

ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT by Sun, Yipeng, Karatzas, Dimosthenis, Chan, Chee Seng, Jin, Lianwen, Ni, Zihan, Chng, Chee-Kheng, Liu, Yuliang, Luo, Canjie, Ng, Chun Chet, Han, Junyu, Ding, Errui, Liu, Jingtuo

“…Robust text reading from street view images provides valuable information for various applications. Performance improvement of existing methods in such a…”
Get full text

Text in the Dark: Extremely Low-Light Text Image Enhancement by Lin, Che-Tsung, Ng, Chun Chet, Tan, Zhi Qin, Nah, Wan Jun, Wang, Xinyu, Kew, Jie Long, Hsu, Pohao, Lai, Shang Hong, Chan, Chee Seng, Zach, Christopher

“…Extremely low-light text images are common in natural scenes, making scene text detection and recognition challenging. One solution is to enhance these images…”
Get full text

Extremely Low-light Image Enhancement with Scene Text Restoration by Hsu, Pohao, Lin, Che-Tsung, Ng, Chun Chet, Kew, Jie-Long, Tan, Mei Yih, Lai, Shang-Hong, Chan, Chee Seng, Zach, Christopher

“…Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally…”
Get full text

ICDAR 2021 Competition on Integrated Circuit Text Spotting and Aesthetic Assessment by Ng, Chun Chet, Nazaruddin, Akmalul Khairi Bin, Lee, Yeong Khang, Wang, Xinyu, Liu, Yuliang, Chan, Chee Seng, Jin, Lianwen, Sun, Yipeng, Fan, Lixin

“…International Conference on Document Analysis and Recognition (ICDAR) 2021 With hundreds of thousands of electronic chip components are being manufactured…”
Get full text

On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering by Wang, Xinyu, Liu, Yuliang, Shen, Chunhua, Ng, Chun Chet, Luo, Canjie, Jin, Lianwen, Chan, Chee Seng, Hengel, Anton van den, Wang, Liangwei

“…Visual Question Answering (VQA) methods have made incredible progress, but suffer from a failure to generalize. This is visible in the fact that they are…”
Get full text

ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT by Sun, Yipeng, Ni, Zihan, Chng, Chee-Kheng, Liu, Yuliang, Luo, Canjie, Ng, Chun Chet, Han, Junyu, Ding, Errui, Liu, Jingtuo, Karatzas, Dimosthenis, Chan, Chee Seng, Jin, Lianwen

“…Robust text reading from street view images provides valuable information for various applications. Performance improvement of existing methods in such a…”
Get full text

ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT) by Chng, Chee-Kheng, Liu, Yuliang, Sun, Yipeng, Ng, Chun Chet, Luo, Canjie, Ni, Zihan, Fang, ChuanMing, Zhang, Shuaitao, Han, Junyu, Ding, Errui, Liu, Jingtuo, Karatzas, Dimosthenis, Chan, Chee Seng, Jin, Lianwen

“…This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT) that consists of three major challenges: i) scene text detection,…”
Get full text