80 citations
- City University of Hong KongHK2 papers
- Beijing Academy of Artificial IntelligenceCN1 paper
- Centre for Artificial Intelligence and RoboticsIN1 paper
- Chinese University of Hong KongHK1 paper
- Education University of Hong KongHK1 paper
- Guangdong Polytechnic Normal UniversityCN1 paper
- Guangxi Normal UniversityCN1 paper
- Hong Kong Polytechnic UniversityHK1 paper
- Lanzhou University of Finance and EconomicsCN1 paper
- Nanjing UniversityCN1 paper
- Northeast Normal UniversityCN1 paper
- Renmin University of ChinaCN1 paper
10 papers
Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning
Yupei Zhang, Li Pan, Qiushi Yang +2
Medical multi-modal pre-training has revealed promise in computer-aided diagnosis by leveraging large-scale unlabeled datasets. However, existing methods based on masked autoencode…
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,…
EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogue
Linkai Luo, Haiqing Yang, Francis Y. L. Chin
In this paper, we propose a self-attentive bidirectional long short-term memory (SA-BiLSTM) network to predict multiple emotions for the EmotionX challenge. The BiLSTM exhibits the…
Estimation of Treatment Effects for Heterogeneous Matched Pairs Data with Probit Models
Jun Wang, Wei Gao, Man-Lai Tang
Estimating the effect of medical treatments on subject responses is one of the crucial problems in medical research. Matched-pairs designs are commonly implemented in the field of…
Incremental Subgradient Methods for Minimizing The Sum of Quasi-convex Functions
Yaohua Hu, Carisa Kwok Wai Yu, Xiaoqi Yang
The sum of ratios problem has a variety of important applications in economics and management science, but it is difficult to globally solve this problem. In this paper, we conside…
Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee
Yi Xu, Haiqin Yang, Lijun Zhang +1
In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random…