J
Jianhuang Lai
Researcher at Sun Yat-sen University
Publications - 272
Citations - 5182
Jianhuang Lai is an academic researcher from Sun Yat-sen University. The author has contributed to research in topics: Facial recognition system & Cluster analysis. The author has an hindex of 34, co-authored 272 publications receiving 3746 citations. Previous affiliations of Jianhuang Lai include Chinese Ministry of Education & Hong Kong Baptist University.
Papers
More filters
Proceedings ArticleDOI
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection
TL;DR: This paper first analyzes the correlation between saliency and contour, then proposes an interactive two-stream decoder to explore multiple cues, including saliency, contour and their correlation, and develops an adaptive contour loss to automatically discriminate hard examples during learning process.
Journal ArticleDOI
Learning Modality-Specific Representations for Visible-Infrared Person Re-Identification
TL;DR: This paper proposes a novel framework that employs modality-specific networks to tackle with the heterogeneous matching problem and demonstrates that the MSR effectively improves the performance of deep networks on VI-REID and remarkably outperforms the state-of-the-art methods.
Journal ArticleDOI
Multi-View Clustering Based on Belief Propagation
TL;DR: This work proposes a novel multi-view clustering algorithm termed multi-View affinity propagation (MVAP), which works by passing messages both within individual views and across different views, and is especially suitable for clustering more than two views.
Journal ArticleDOI
Early Action Prediction by Soft Regression
TL;DR: The proposed regression-based early action prediction model outperforms existing models significantly and is more accurate than that on RGB channel and a new RGB-D feature called “local accumulative frame feature (LAFF)”, which can be computed efficiently by constructing an integral feature map.
Proceedings ArticleDOI
Interleaved Structured Sparse Convolutional Neural Networks
TL;DR: This paper presents a modularized building block, IGC-V2: interleaved structured sparse convolutions, which generalizes interleaves group convolutions to the product of more structured sparse kernels, further eliminating the redundancy.