10.9k citations
- Michigan State UniversityUS326 papers
- University of MichiganUS321 papers
- Joint Institute for Nuclear ResearchRU318 papers
- Centre National de la Recherche ScientifiqueFR317 papers
- Lawrence Berkeley National LaboratoryUS311 papers
- Institute for High Energy PhysicsES302 papers
- McGill UniversityCA299 papers
- Fermi National Accelerator LaboratoryUS298 papers
- Institute for Theoretical and Experimental PhysicsRU296 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR294 papers
- TRIUMFCA291 papers
- Sorbonne UniversitéFR279 papers
16 papers · 2 filters
Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks
Mohammad Akbari, Jie Liang, Jingning Han +1
Recently deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rat…
LayoutGMN: Neural Graph Matching for Structural Layout Similarity
Akshay Gadi Patil, Manyi Li, Matthew Fisher +2
We present a deep neural network to predict structural similarity between 2D layouts by leveraging Graph Matching Networks (GMN). Our network, coined LayoutGMN, learns the layout m…
SFU-Store-Nav: A Multimodal Dataset for Indoor Human Navigation
Zhitian Zhang, Jimin Rhim, Taher Ahmadi +3
This article describes a dataset collected in a set of experiments that involves human participants and a robot. The set of experiments was conducted in the computing science robot…
Moving object detection for visual odometry in a dynamic environment based on occlusion accumulation
Haram Kim, Pyojin Kim, H. Jin Kim
Detection of moving objects is an essential capability in dealing with dynamic environments. Most moving object detection algorithms have been designed for color images without dep…
Unsupervised Single-Image Reflection Separation Using Perceptual Deep Image Priors
Suhong Kim, Hamed RahmaniKhezri, Seyed Mohammad Nourbakhsh +1
Reflections often degrade the quality of the image by obstructing the background scene. This is not desirable for everyday users, and it negatively impacts the performance of multi…
Hierarchical Action Classification with Network Pruning
Mahdi Davoodikakhki, KangKang Yin
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network comp…