Search Results for author: Siew-Kei Lam

Found 6 papers, 2 papers with code

Multi-fold Correlation Attention Network for Predicting Traffic Speeds with Heterogeneous Frequency

no code implementations19 Apr 2021 Yidan Sun, Guiyuan Jiang, Siew-Kei Lam, Peilan He, Fangxin Ning

We propose a Heterogeneous Spatial Correlation (HSC) model to capture the spatial correlation based on a specific measurement, where the traffic data of varying road segments can be heterogeneous (i. e. obtained with different sampling frequency).

Traffic Prediction

CAP-Context-Aware-Pruning-for-Semantic-Segmentation

1 code implementation6 Jan 2021 wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

In this paper, we advocate the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework.

Network Pruning Segmentation +1

CAP: Context-Aware Pruning for Semantic-Segmentation

1 code implementation6 Jan 2021 wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

In this paper, we advocate the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework.

Network Pruning Segmentation +1

Self-Growing Spatial Graph Network for Context-Aware Pedestrian Trajectory Prediction

no code implementations11 Dec 2020 Sirin Haddad, Siew-Kei Lam

To fill this gap, we propose Social Trajectory Recommender-Gated Graph Recurrent Neighborhood Network, (STR-GGRNN), which uses data-driven adaptive online neighborhood recommendation based on the contextual scene features and pedestrian visual cues.

Pedestrian Trajectory Prediction Trajectory Prediction

SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection

no code implementations25 Feb 2019 Chengju Zhou, Meiqing Wu, Siew-Kei Lam

We propose a method that explores semantic segmentation results as self-attention cues to significantly improve the pedestrian detection performance.

Autonomous Driving Computational Efficiency +3

Cannot find the paper you are looking for? You can Submit a new open access paper.