80 citations · 174 across the 24 of their papers we have counts for
24 papers
Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models
Haoxuan Wu, Lai Man Po, Mengyang Liu +3
Video reward models are central to aligning video diffusion models with human preferences, yet existing ones are external vision-language models that score clean, decoded pixels. S…
SpecPL: Disentangling Spectral Granularity for Prompt Learning
Jingtao Zhou, Xirui Kang, Feiyang Huang +1
Existing prompt learning for VLMs exhibits a modality asymmetry, predominantly optimizing text tokens while still relying on frozen visual encoder as holistic extractor and neglect…
Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder
Kin Wai Lau, Yasar Abbas Ur Rehman, Lai-Man Po +1
Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Om…
From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training
Donglai Xu, Hongzheng Yang, Yuzhi Zhao +10
Reinforcement Learning with Verifiable Rewards (RLVR) for Multimodal Large Language Models (MLLMs) is highly dependent on high-quality labeled data, which is often scarce and prone…
AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
Kun Li, Lai-Man Po, Hongzheng Yang +3
Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their…
Motion Transfer-Driven intra-class data augmentation for Finger Vein Recognition
Xiu-Feng Huang, Lai-Man Po, Wei-Feng Ou
Finger vein recognition (FVR) has emerged as a secure biometric technique because of the confidentiality of vascular bio-information. Recently, deep learning-based FVR has gained i…
Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring
Yuzhi Zhao, Lai-Man Po, Xin Ye +2
Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions fac…
FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning
Kin Wai Lau, Yasar Abbas Ur Rehman, Pedro Porto Buarque de Gusmão +3
Federated Learning (FL) has emerged as a privacy-preserving method for training machine learning models in a distributed manner on edge devices. However, on-device models face inhe…
SBoRA: Low-Rank Adaptation with Regional Weight Updates
Lai-Man Po, Yuyang Liu, Haoxuan Wu +5
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 Adap…
AudioRepInceptionNeXt: A lightweight single-stream architecture for efficient audio recognition
Kin Wai Lau, Yasar Abbas Ur Rehman, Lai-Man Po
Recent research has successfully adapted vision-based convolutional neural network (CNN) architectures for audio recognition tasks using Mel-Spectrograms. However, these CNNs have…
Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN
Kin Wai Lau, Lai-Man Po, Yasar Abbas Ur Rehman
Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs), on a range o…
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Wing-Yin Yu, Lai-Man Po, Ray C. C. Cheung +3
Video-based human pose transfer is a video-to-video generation task that animates a plain source human image based on a series of target human poses. Considering the difficulties i…
SVCNet: Scribble-based Video Colorization Network with Temporal Aggregation
Yuzhi Zhao, Lai-Man Po, Kangcheng Liu +5
In this paper, we propose a scribble-based video colorization network with temporal aggregation called SVCNet. It can colorize monochrome videos based on different user-given color…
D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration
Yuzhi Zhao, Yongzhe Xu, Qiong Yan +3
Night imaging with modern smartphone cameras is troublesome due to low photon count and unavoidable noise in the imaging system. Directly adjusting exposure time and ISO ratings ca…
ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
Yuzhi Zhao, Lai-Man Po, Xuehui Wang +9
The appearances of children are inherited from their parents, which makes it feasible to predict them. Predicting realistic children's faces may help settle many social problems, s…
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Yujia Zhang, Lai-Man Po, Xuyuan Xu +5
Spatio-temporal representation learning is critical for video self-supervised representation. Recent approaches mainly use contrastive learning and pretext tasks. However, these ap…
CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
Jingjing Xiong, Lai-Man Po, Wing-Yin Yu +3
Real-time semantic segmentation has received considerable attention due to growing demands in many practical applications, such as autonomous vehicles, robotics, etc. Existing real…
VCGAN: Video Colorization with Hybrid Generative Adversarial Network
Yuzhi Zhao, Lai-Man Po, Wing-Yin Yu +4
We propose a hybrid recurrent Video Colorization with Hybrid Generative Adversarial Network (VCGAN), an improved approach to video colorization using end-to-end learning. The VCGAN…
Spatial Content Alignment For Pose Transfer
Wing-Yin Yu, Lai-Man Po, Yuzhi Zhao +2
Due to unreliable geometric matching and content misalignment, most conventional pose transfer algorithms fail to generate fine-trained person images. In this paper, we propose a n…
Legacy Photo Editing with Learned Noise Prior
Zhao Yuzhi, Po Lai-Man, Wang Xuehui +5
There are quite a number of photographs captured under undesirable conditions in the last century. Thus, they are often noisy, regionally incomplete, and grayscale formatted. Conve…
SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
Yuzhi Zhao, Lai-Man Po, Kwok-Wai Cheung +2
Given a grayscale photograph, the colorization system estimates a visually plausible colorful image. Conventional methods often use semantics to colorize grayscale images. However,…
UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
Yuqian Zhou, Michael Kwan, Kyle Tolentino +42
This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-co…
Hierarchical Regression Network for Spectral Reconstruction from RGB Images
Yuzhi Zhao, Lai-Man Po, Qiong Yan +2
Capturing visual image with a hyperspectral camera has been successfully applied to many areas due to its narrow-band imaging technology. Hyperspectral reconstruction from RGB imag…
NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image
Boaz Arad, Radu Timofte, Ohad Ben-Shahar +4
This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image. As…