default author photo

Rae-Hong Park

Sogang University

Seoul 121-742

Korea, Republic of (South Korea)

SCHOLARLY PAPERS

3

DOWNLOADS

246

TOTAL CITATIONS

1

Scholarly Papers (3)

1.

Swinlip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer

Number of pages: 12 Posted: 14 Dec 2024
Young-Hu Park, Rae-Hong Park and Hyung-Min Park
Sogang University, Sogang University and Sogang University
Downloads 112 (635,507)
Citation 1

Abstract:

Loading...

Lip reading, visual speech recognition, visual speech encoder, Swin Transformer, ResNet

2.

Multi-Scale Foreground-Background Separation for Light Field Depth Estimation with Deep Convolutional Networks

Number of pages: 7 Posted: 10 Oct 2022
Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering, Sogang University and Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering
Downloads 75 (837,727)

Abstract:

Loading...

Light Field, Depth Estimation, Foreground-Background Separation

3.

Light Field Salient Object Detection Based on Foreground-Background Separation

Number of pages: 7 Posted: 19 Oct 2022
Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), affiliation not provided to SSRN, affiliation not provided to SSRN, Sogang University and Korea Advanced Institute of Science and Technology (KAIST), School of Electrical Engineering
Downloads 59 (1,000,027)

Abstract:

Loading...

light field, saliency detection, salient object detection, foreground-background separation