501 citations
- University of WaterlooCA11 papers
- University of TorontoCA7 papers
- Institut de Mathématiques de BordeauxFR6 papers
- Institut de recherche mathématique de RennesFR6 papers
- Laboratoire de Mathématiques et Physique ThéoriqueFR5 papers
- Sapienza University of RomeIT5 papers
- Tsinghua UniversityCN5 papers
- Carleton UniversityCA4 papers
- University of KansasUS4 papers
- York UniversityCA4 papers
- Zhengzhou UniversityCN4 papers
- Brown UniversityUS3 papers
23 papers · 1 filter
Semantic keypoint-based pose estimation from single RGB frames
Karl Schmeckpeper, Philip R. Osteen, Yufu Wang +6
This paper presents an approach to estimating the continuous 6-DoF pose of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional…
Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs
Md Amirul Islam, Matthew Kowal, Sen Jia +2
In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via…
Direction-aware Feature-level Frequency Decomposition for Single Image Deraining
Sen Deng, Yidan Feng, Mingqiang Wei +5
We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compel…
An interpretable object detection based model for the diagnosis of neonatal lung diseases using Ultrasound images
Rodina Bassiouny, Adel Mohamed, Karthi Umapathy +1
Over the last few decades, Lung Ultrasound (LUS) has been increasingly used to diagnose and monitor different lung diseases in neonates. It is a non invasive tool that allows a fas…
Parallel Scale-wise Attention Network for Effective Scene Text Recognition
Usman Sajid, Michael Chow, Jin Zhang +2
The paper proposes a new text recognition network for scene-text images. Many state-of-the-art methods employ the attention mechanism either in the text encoder or decoder for the…
The Labeled Multiple Canonical Correlation Analysis for Information Fusion
Lei Gao, Rui Zhang, Lin Qi +2
The objective of multimodal information fusion is to mathematically analyze information carried in different sources and create a new representation which will be more effectively…