Alert button
Picture for Lai-Man Po

Lai-Man Po

Alert button

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

Sep 06, 2023
Kin Wai Lau, Lai-Man Po, Yasar Abbas Ur Rehman

Figure 1 for Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN
Figure 2 for Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN
Figure 3 for Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN
Figure 4 for Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN
Viaarxiv icon

Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer

Jul 18, 2023
Wing-Yin Yu, Lai-Man Po, Ray C. C. Cheung, Yuzhi Zhao, Yu Xue, Kun Li

Figure 1 for Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Figure 2 for Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Figure 3 for Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Figure 4 for Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Viaarxiv icon

SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation

Mar 21, 2023
Yuzhi Zhao, Lai-Man Po, Kangcheng Liu, Xuehui Wang, Wing-Yin Yu, Pengfei Xian, Yujia Zhang, Mengyang Liu

Figure 1 for SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
Figure 2 for SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
Figure 3 for SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
Figure 4 for SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
Viaarxiv icon

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

Jul 14, 2022
Yuzhi Zhao, Yongzhe Xu, Qiong Yan, Dingdong Yang, Xuehui Wang, Lai-Man Po

Figure 1 for D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Figure 2 for D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Figure 3 for D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Figure 4 for D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Viaarxiv icon

ChildPredictor: A Child Face Prediction Framework with Disentangled Learning

Apr 21, 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

Figure 1 for ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
Figure 2 for ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
Figure 3 for ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
Figure 4 for ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
Viaarxiv icon

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

Dec 19, 2021
Yujia Zhang, Lai-Man Po, Xuyuan Xu, Mengyang Liu, Yexin Wang, Weifeng Ou, Yuzhi Zhao, Wing-Yin Yu

Figure 1 for Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Figure 2 for Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Figure 3 for Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Figure 4 for Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Viaarxiv icon

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

Jun 08, 2021
Jingjing Xiong, Lai-Man Po, Wing-Yin Yu, Chang Zhou, Pengfei Xian, Weifeng Ou

Figure 1 for CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
Figure 2 for CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
Figure 3 for CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
Figure 4 for CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
Viaarxiv icon

VCGAN: Video Colorization with Hybrid Generative Adversarial Network

Apr 26, 2021
Yuzhi Zhao, Lai-Man Po, Wing-Yin Yu, Yasar Abbas Ur Rehman, Mengyang Liu, Yujia Zhang, Weifeng Ou

Figure 1 for VCGAN: Video Colorization with Hybrid Generative Adversarial Network
Figure 2 for VCGAN: Video Colorization with Hybrid Generative Adversarial Network
Figure 3 for VCGAN: Video Colorization with Hybrid Generative Adversarial Network
Figure 4 for VCGAN: Video Colorization with Hybrid Generative Adversarial Network
Viaarxiv icon

Spatial Content Alignment For Pose Transfer

Mar 31, 2021
Wing-Yin Yu, Lai-Man Po, Yuzhi Zhao, Jingjing Xiong, Kin-Wai Lau

Figure 1 for Spatial Content Alignment For Pose Transfer
Figure 2 for Spatial Content Alignment For Pose Transfer
Figure 3 for Spatial Content Alignment For Pose Transfer
Figure 4 for Spatial Content Alignment For Pose Transfer
Viaarxiv icon