Search Results for author: Lai-Man Po

Found 12 papers, 10 papers with code

Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN

1 code implementation4 Sep 2023 Kin Wai Lau, Lai-Man Po, Yasar Abbas Ur Rehman

Our extensive experimental results show that the proposed LSKA module in VAN provides a significant reduction in computational complexity and memory footprints with increasing kernel size while outperforming ViTs, ConvNeXt, and providing similar performance compared to the LKA module in VAN on object recognition, object detection, semantic segmentation, and robustness tests.

object-detection Object Detection +2

Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer

1 code implementation ICCV 2023 Wing-Yin Yu, Lai-Man Po, Ray C. C. Cheung, Yuzhi Zhao, Yu Xue, Kun Li

To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer.

motion prediction Pose Transfer +2

SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation

1 code implementation21 Mar 2023 Yuzhi Zhao, Lai-Man Po, Kangcheng Liu, Xuehui Wang, Wing-Yin Yu, Pengfei Xian, Yujia Zhang, Mengyang Liu

It addresses three common issues in the scribble-based video colorization area: colorization vividness, temporal consistency, and color bleeding.

Colorization Super-Resolution

D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration

1 code implementation7 Jul 2022 Yuzhi Zhao, Yongzhe Xu, Qiong Yan, Dingdong Yang, Xuehui Wang, Lai-Man Po

Night imaging with modern smartphone cameras is troublesome due to low photon count and unavoidable noise in the imaging system.

Deblurring Denoising +1

ChildPredictor: A Child Face Prediction Framework with Disentangled Learning

1 code implementation21 Apr 2022 Yuzhi Zhao, Lai-Man Po, Xuehui Wang, Qiong Yan, Wei Shen, Yujia Zhang, Wei Liu, Chun-Kit Wong, Chiu-Sing Pang, Weifeng Ou, Wing-Yin Yu, Buhua Liu

On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors.

Age-Invariant Face Recognition Image-to-Image Translation +1

Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation

1 code implementation16 Dec 2021 Yujia Zhang, Lai-Man Po, Xuyuan Xu, Mengyang Liu, Yexin Wang, Weifeng Ou, Yuzhi Zhao, Wing-Yin Yu

Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning.

Contrastive Learning Representation Learning +1

CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation

no code implementations8 Jun 2021 Jingjing Xiong, Lai-Man Po, Wing-Yin Yu, Chang Zhou, Pengfei Xian, Weifeng Ou

Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc.

Autonomous Vehicles Real-Time Semantic Segmentation +1

VCGAN: Video Colorization with Hybrid Generative Adversarial Network

1 code implementation26 Apr 2021 Yuzhi Zhao, Lai-Man Po, Wing-Yin Yu, Yasar Abbas Ur Rehman, Mengyang Liu, Yujia Zhang, Weifeng Ou

We propose a hybrid recurrent Video Colorization with Hybrid Generative Adversarial Network (VCGAN), an improved approach to video colorization using end-to-end learning.

Colorization Image Colorization

Spatial Content Alignment For Pose Transfer

1 code implementation31 Mar 2021 Wing-Yin Yu, Lai-Man Po, Yuzhi Zhao, Jingjing Xiong, Kin-Wai Lau

Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images.

Geometric Matching Pose Transfer

SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network

1 code implementation23 Nov 2020 Yuzhi Zhao, Lai-Man Po, Kwok-Wai Cheung, Wing-Yin Yu, Yasar Abbas Ur Rehman

It jointly predicts the colorization and saliency map to minimize semantic confusion and color bleeding in the colorized image.


Hierarchical Regression Network for Spectral Reconstruction from RGB Images

1 code implementation10 May 2020 Yuzhi Zhao, Lai-Man Po, Qiong Yan, Wei Liu, Tingyu Lin

Hyperspectral reconstruction from RGB images denotes a reverse process of hyperspectral imaging by discovering an inverse response function.

regression Spectral Reconstruction

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