Search Results for author: Chiu Man Ho

Found 12 papers, 2 papers with code

Real-Time Super-Resolution for Real-World Images on Mobile Devices

no code implementations3 Jun 2022 Jie Cai, Zibo Meng, Jiaming Ding, Chiu Man Ho

Image Super-Resolution (ISR), which aims at recovering High-Resolution (HR) images from the corresponding Low-Resolution (LR) counterparts.

Image Super-Resolution SSIM

MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition

no code implementations20 Aug 2021 Jiawei Chen, Chiu Man Ho

This paper presents a pure transformer-based approach, dubbed the Multi-Modal Video Transformer (MM-ViT), for video action recognition.

Action Recognition Optical Flow Estimation +1

RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection

no code implementations26 May 2021 Jiachen Li, Yuan Lin, Rongrong Liu, Chiu Man Ho, Humphrey Shi

Segmentation-based scene text detection methods have been widely adopted for arbitrary-shaped text detection recently, since they make accurate pixel-level predictions on curved text instances and can facilitate real-time inference without time-consuming processing on anchors.

Scene Text Detection Text Detection

GIA-Net: Global Information Aware Network for Low-light Imaging

no code implementations14 Sep 2020 Zibo Meng, Runsheng Xu, Chiu Man Ho

In this paper, we propose a global information aware (GIA) module, which is capable of extracting and integrating the global information into the network to improve the performance of low-light imaging.

Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition

no code implementations3 Aug 2020 Jiawei Chen, Jenson Hsiao, Chiu Man Ho

Empirical results confirm the efficiency and effectiveness of residual frames as well as the proposed pseudo-3D convolution module.

Action Recognition Optical Flow Estimation +2

Residual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction

no code implementations28 Apr 2020 Jie Cai, Zibo Meng, Chiu Man Ho

In this paper, we propose a Residual Channel Attention-Generative Adversarial Network(RCA-GAN) to solve these problems.

Image Super-Resolution

Gradient-Coherent Strong Regularization for Deep Neural Networks

no code implementations20 Nov 2018 Dae Hoon Park, Chiu Man Ho, Yi Chang, Huaqing Zhang

However, we observe that imposing strong L1 or L2 regularization with stochastic gradient descent on deep neural networks easily fails, which limits the generalization ability of the underlying neural networks.

L2 Regularization

Sequenced-Replacement Sampling for Deep Learning

no code implementations ICLR 2019 Chiu Man Ho, Dae Hoon Park, Wei Yang, Yi Chang

We propose sequenced-replacement sampling (SRS) for training deep neural networks.

Achieving Strong Regularization for Deep Neural Networks

no code implementations ICLR 2018 Dae Hoon Park, Chiu Man Ho, Yi Chang

L1 and L2 regularizers are critical tools in machine learning due to their ability to simplify solutions.

L2 Regularization

Cannot find the paper you are looking for? You can Submit a new open access paper.