3.5k citations
- National University of SingaporeSG766 papers
- Centre for Quantum TechnologiesSG406 papers
- Centre National de la Recherche ScientifiqueFR286 papers
- Agency for Science, Technology and ResearchSG280 papers
- UMI MajuLabSG225 papers
- Centre for Disruptive Photonic TechnologiesSG157 papers
- Institute of High Performance ComputingSG132 papers
- Chinese Academy of SciencesCN131 papers
- Tsinghua UniversityCN129 papers
- Zhejiang UniversityCN126 papers
- National Institute of Education123 papers
- Singapore University of Technology and DesignSG120 papers
515 papers · 1 filter
Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration
Aoru Xue, Yujing Sun, Yiming Ren +3
We propose Sen-Cap, a Sensor-Flexible and Noise-Resilient 3D human motion Capture framework that integrates multi-modal data from LiDAR and camera. While multi-modal sensors provid…
Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning
Hao Kong, Di Liu, Xiangzhong Luo +5
In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks…
FedTR: Federated Learning Framework with Transfer Learning for Industrial Visual Inspection
Vikash Sathiamoorthy, Shuo Huai, Hao Kong +7
Federated learning (FL) is a collaborative learning scheme to train deep learning models, where collaborating parties can consolidate their models without sharing local data with o…
CarbonCLIP: Enhance Carbon Prediction from Satellite Imagery via Integrated Street-View Semantics and Temporal Context Training
Zeru Yang, Fang-Ying Gong, Steve H. L. Yim +1
Accurately estimating urban carbon emissions is critical for sustainable urban planning, yet many existing approaches remain difficult to apply consistently across cities due to da…
EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
Hao Kong, Di Liu, Shuo Huai +5
Convolutional neural networks (CNNs) have demonstrated encouraging results in image classification tasks. However, the prohibitive computational cost of CNNs hinders the deployment…
Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware
Hao Kong, Di Liu, Shuo Huai +5
Scaling down the resolution of input images can greatly reduce the computational overhead of convolutional neural networks (CNNs), which is promising for edge AI. However, as an im…