1 code implementation • 29 Dec 2024 • Xiu-Feng Huang, Lai-Man Po, Wei-Feng Ou
To address this issue, we propose a novel motion transfer (MT) model for finger vein image data augmentation via modeling the actual finger posture and rotational movements.
1 code implementation • 10 Dec 2024 • Yuzhi Zhao, Lai-Man Po, Xin Ye, Yongzhe Xu, Qiong Yan
Long exposures reduce noise but introduce blur.
no code implementations • 24 Sep 2024 • Kin Wai Lau, Yasar Abbas Ur Rehman, Pedro Porto Buarque de Gusmão, Lai-Man Po, Lan Ma, Yuyang Xie
The gradient re-parameterized method allows training a simple local model with a similar performance as a complex model by modifying the optimizer's gradients according to a set of model-specific hyperparameters obtained from the complex models.
1 code implementation • 7 Jul 2024 • Lai-Man Po, Yuyang Liu, Haoxuan Wu, Tianqi Zhang, Wing-Yin Yu, Zhuohan Wang, Zeyu Jiang, Kun Li
This paper introduces Standard Basis LoRA (SBoRA), a novel parameter-efficient fine-tuning approach for Large Language Models that builds upon the pioneering works of Low-Rank Adaptation (LoRA) and Orthogonal Adaptation.
1 code implementation • 4 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.
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.
1 code implementation • 21 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.
2 code implementations • 7 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.
1 code implementation • 21 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
+3
1 code implementation • 16 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.
no code implementations • 8 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.
1 code implementation • 26 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.
1 code implementation • 31 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.
1 code implementation • 23 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.
no code implementations • 18 Aug 2020 • Yuqian Zhou, Michael Kwan, Kyle Tolentino, Neil Emerton, Sehoon Lim, Tim Large, Lijiang Fu, Zhihong Pan, Baopu Li, Qirui Yang, Yihao Liu, Jigang Tang, Tao Ku, Shibin Ma, Bingnan Hu, Jiarong Wang, Densen Puthussery, Hrishikesh P. S, Melvin Kuriakose, Jiji C. V, Varun Sundar, Sumanth Hegde, Divya Kothandaraman, Kaushik Mitra, Akashdeep Jassal, Nisarg A. Shah, Sabari Nathan, Nagat Abdalla Esiad Rahel, Dafan Chen, Shichao Nie, Shuting Yin, Chengconghui Ma, Haoran Wang, Tongtong Zhao, Shanshan Zhao, Joshua Rego, Huaijin Chen, Shuai Li, Zhenhua Hu, Kin Wai Lau, Lai-Man Po, Dahai Yu, Yasar Abbas Ur Rehman, Yiqun Li, Lianping Xing
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
1 code implementation • 10 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.
Ranked #10 on
Spectral Reconstruction
on ARAD-1K