1.5k citations
- Research!America (United States)US21 papers
- Samsung (South Korea)KR17 papers
- Korea Advanced Institute of Science and TechnologyKR9 papers
- Korea Institute of Science and TechnologyKR7 papers
- University of CambridgeGB5 papers
- University of Southern CaliforniaUS5 papers
- Imperial College LondonGB4 papers
- Purdue University West LafayetteUS4 papers
- Samsung Electronics (South Korea)KR4 papers
- Samsung (India)IN4 papers
- Stanford UniversityUS4 papers
- Texas A&M UniversityUS4 papers
Showing 2017 · cs.CVShow all
3 papers · 2 filters
cs.CV2017★ 2 cited
CT-SRCNN: Cascade Trained and Trimmed Deep Convolutional Neural Networks for Image Super Resolution
Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
We propose methodologies to train highly accurate and efficient deep convolutional neural networks (CNNs) for image super resolution (SR). A cascade training approach to deep learn…
cs.CV2017★ 44 cited
Dual-fisheye lens stitching for 360-degree imaging
Tuan Ho, Madhukar Budagavi
Dual-fisheye lens cameras have been increasingly used for 360-degree immersive imaging. However, the limited overlapping field of views and misalignment between the two lenses give…
cs.CV2017★ 30 cited
DeepRebirth: Accelerating Deep Neural Network Execution on Mobile Devices
Dawei Li, Xiaolong Wang, Deguang Kong
Deploying deep neural networks on mobile devices is a challenging task. Current model compression methods such as matrix decomposition effectively reduce the deployed model size, b…