no code implementations • 26 Apr 2022 • Li-Heng Chen, Christos G. Bampis, Zhi Li, Lukáš Krasula, Alan C. Bovik
By conducting extensive experimental tests on existing deep image compression models, we show results that our new resizing parameter estimation framework can provide Bj{\o}ntegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines.
no code implementations • 20 May 2021 • Li-Heng Chen, Christos G. Bampis, Zhi Li, Chao Chen, Alan C. Bovik
The layers of convolutional neural networks (CNNs) can be used to alter the resolution of their inputs, but the scaling factors are limited to integer values.
no code implementations • 30 Jan 2021 • Zhengzhong Tu, Chia-Ju Chen, Li-Heng Chen, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik
Video and image quality assessment has long been projected as a regression problem, which requires predicting a continuous quality score given an input stimulus.
no code implementations • 3 Jul 2020 • Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik
Mean squared error (MSE) and $\ell_p$ norms have largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties.
1 code implementation • ICML 2020 • Yaodong Yang, Ying Wen, Li-Heng Chen, Jun Wang, Kun Shao, David Mguni, Wei-Nan Zhang
Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution.
no code implementations • 25 Feb 2020 • Zhengzhong Tu, Chia-Ju Chen, Li-Heng Chen, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik
Many objective video quality assessment (VQA) algorithms include a key step of temporal pooling of frame-level quality scores.
no code implementations • 19 Oct 2019 • Ching-Da Wu, Li-Heng Chen
We aim to construct a system that captures real-world facial images through the front camera on a laptop.
1 code implementation • 19 Oct 2019 • Li-Heng Chen, Christos G. Bampis, Zhi Li, Andrey Norkin, Alan C. Bovik
By building on top of an existing deep image compression model, we are able to demonstrate a bitrate reduction of as much as $31\%$ over MSE optimization, given a specified perceptual quality (VMAF) level.
no code implementations • NAACL 2018 • Zhenghui Wang, Yanru Qu, Li-Heng Chen, Jian Shen, Wei-Nan Zhang, Shaodian Zhang, Yimei Gao, Gen Gu, Ken Chen, Yong Yu
We study the problem of named entity recognition (NER) from electronic medical records, which is one of the most fundamental and critical problems for medical text mining.
Medical Named Entity Recognition named-entity-recognition +3