no code implementations • 12 Dec 2023 • Jingchun Zhou, Qilin Gai, Kin-Man Lam, Xianping Fu
In underwater environments, variations in suspended particle concentration and turbidity cause severe image degradation, posing significant challenges to image enhancement (IE) and object detection (OD) tasks.
no code implementations • 1 Sep 2023 • Tsun-Hin Cheung, Kin-Man Lam
Then, we instruct-tune an open-sourced language model, called LLaMA, using this evidence, enabling it to predict the veracity of the input claim more accurately.
1 code implementation • 23 Aug 2023 • Jingchun Zhou, Zongxin He, Kin-Man Lam, Yudong Wang, Weishi Zhang, Chunle Guo, Chongyi Li
In this paper, we present a novel Amplitude-Modulated Stochastic Perturbation and Vortex Convolutional Network, AMSP-UOD, designed for underwater object detection.
1 code implementation • 13 Mar 2023 • Hongxiang Huang, Daihui Yang, Gang Dai, Zhen Han, Yuyi Wang, Kin-Man Lam, Fan Yang, Shuangping Huang, Yongge Liu, Mengchao He
We evaluate our approach on the photographic ancient character datasets, e. g., OBC306 and CSDD.
1 code implementation • 16 Dec 2022 • Yakun Ju, Kin-Man Lam, Wuyuan Xie, Huiyu Zhou, Junyu Dong, Boxin Shi
We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set.
1 code implementation • 18 Aug 2022 • Hongming Luo, Fei Zhou, Kin-Man Lam, Guoping Qiu
This paper presents a new general video restoration framework for the restoration of user videos shared on social media platforms.
no code implementations • 4 Aug 2022 • Jun Xiao, Xinyang Jiang, Ningxin Zheng, Huan Yang, Yifan Yang, Yuqing Yang, Dongsheng Li, Kin-Man Lam
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
no code implementations • 4 Aug 2022 • Jun Xiao, Qian Ye, Tianshan Liu, Cong Zhang, Kin-Man Lam
The primary challenges are ghosting artifacts caused by object motion between low dynamic range images and distorted content in under and overexposed regions.
no code implementations • 3 Jan 2022 • Parnian Afshar, Arash Mohammadi, Konstantinos N. Plataniotis, Keyvan Farahani, Justin Kirby, Anastasia Oikonomou, Amir Asif, Leonard Wee, Andre Dekker, Xin Wu, Mohammad Ariful Haque, Shahruk Hossain, Md. Kamrul Hasan, Uday Kamal, Winston Hsu, Jhih-Yuan Lin, M. Sohel Rahman, Nabil Ibtehaz, Sh. M. Amir Foisol, Kin-Man Lam, Zhong Guang, Runze Zhang, Sumohana S. Channappayya, Shashank Gupta, Chander Dev
Lung cancer is one of the deadliest cancers, and in part its effective diagnosis and treatment depend on the accurate delineation of the tumor.
no code implementations • CVPR 2022 • Tianshan Liu, Kin-Man Lam
Furthermore, to resolve the limitation (ii), a one-shot transferring paradigm is proposed to enrich the forecasted representations, by distilling the holistic activity semantics after the target anticipation moment, in the offline training.
1 code implementation • 19 Aug 2021 • Qian Ye, Jun Xiao, Kin-Man Lam, Takayuki Okatani
We propose a novel method that can better fuse the features based on two ideas.
no code implementations • 9 Sep 2020 • Rui Zhao, Daniel P. K. Lun, Kin-Man Lam
Recent studies on learning-based image denoising have achieved promising performance on various noise reduction tasks.
no code implementations • 9 Jul 2020 • Rui Zhao, Tianshan Liu, Jun Xiao, Daniel P. K. Lun, Kin-Man Lam
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks.
Facial Expression Recognition Facial Expression Recognition (FER) +2
no code implementations • 28 Jun 2020 • Rui Zhao, Kin-Man Lam, Daniel P. K. Lun
Since most of the content or energy of natural images resides in the low-frequency spectrum, their transformed coefficients in the frequency domain are highly imbalanced.
1 code implementation • ECCV 2018 • Hongmei Song, Wenguan Wang, Sanyuan Zhao, Jianbing Shen, Kin-Man Lam
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).
Ranked #1 on Video Salient Object Detection on UVSD (using extra training data)
no code implementations • 11 Jan 2018 • Cigdem Turan, Kin-Man Lam, Xiangjian He
Furthermore, the proposed feature-generation method can improve the generalizability of the underlying manifolds for facial expression recognition.
1 code implementation • 14 Dec 2017 • Hailiang Li, Kin-Man Lam, Miaohui Wang
In this paper, we present a novel feature-augmented random forest (FARF) for image super-resolution, where the conventional gradient-based features are augmented with gradient magnitudes and different feature recipes are formulated on different stages in an RF.
Ranked #48 on Image Super-Resolution on BSD100 - 4x upscaling
1 code implementation • 30 Aug 2017 • Hailiang Li, Kin-Man Lam, Dong Li
In the JMPF scheme, the original feature space is transformed into a compactly pre-clustered feature space, via a trained rotation matrix.
Ranked #50 on Image Super-Resolution on BSD100 - 4x upscaling
no code implementations • 28 Feb 2017 • Long Chen, Junyu Dong, Shengke Wang, Kin-Man Lam, Muwei Jian, Hua Zhang, Xiaochun Cao
To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories.
no code implementations • 30 Nov 2016 • Hailiang Li, Kin-Man Lam, Man-Yau Chiu, Kangheng Wu, Zhibin Lei
The constrained local model (CLM) proposes a paradigm that the locations of a set of local landmark detectors are constrained to lie in a subspace, spanned by a shape point distribution model (PDM).
no code implementations • 25 Nov 2016 • Xiaolong Ma, Xiatian Zhu, Shaogang Gong, Xudong Xie, Jianming Hu, Kin-Man Lam, Yisheng Zhong
Crucially, this model does not require pairwise labelled training data (i. e. unsupervised) therefore readily scalable to large scale camera networks of arbitrary camera pairs without the need for exhaustive data annotation for every camera pair.
no code implementations • 21 Nov 2016 • Hailiang Li, Kin-Man Lam, Edmond M. Y. Chiu, Kangheng Wu, Zhibin Lei
In this paper, we present a random-forest based fast cascaded regression model for face alignment, via a novel local feature.
no code implementations • 30 May 2013 • Kaihua Zhang, Lei Zhang, Kin-Man Lam, David Zhang
The means of the Gaussian distributions in the transformed domain can be adaptively estimated by multiplying a bias field with the original signal within the window.