Related papers: Image Retrieval for Structure-from-Motion via Grap…

Graph Neural Networks (GNNs) have achieved tremendous success in various real-world applications due to their strong ability in graph representation learning. GNNs explore the graph structure and node features by aggregating and…

2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the…

The shared topology of human skeletons motivated the recent investigation of graph convolutional network (GCN) solutions for action recognition. However, most of the existing GCNs rely on the binary connection of two neighboring vertices…

In this paper, we aim at improving the computational efficiency of graph convolutional networks (GCNs) for learning on point clouds. The basic graph convolution that is typically composed of a $K$-nearest neighbor (KNN) search and a…

Structure-from-Motion (SfM), a task aiming at jointly recovering camera poses and 3D geometry of a scene given a set of images, remains a hard problem with still many open challenges despite decades of significant progress. The traditional…

Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors.…

Image retrieval is a critical step for reducing the quadratic cost of image matching in unconstrained Structure-from-Motion (SfM). Unlike generic image retrieval, however, the relevant goal of SfM is to identify geometrically matchable…

Convolutional neural networks (CNNs) are usually built by stacking convolutional operations layer-by-layer. Although CNN has shown strong capability to extract semantics from raw pixels, its capacity to capture spatial relationships of…

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their…

Graph Neural Networks (GNNs) have achieved promising performance in semi-supervised node classification in recent years. However, the problem of insufficient supervision, together with representation collapse, largely limits the performance…

Image-based characterization and disease understanding involve integrative analysis of morphological, spatial, and topological information across biological scales. The development of graph convolutional networks (GCNs) has created the…

Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping…

Recent years have witnessed some exciting developments in the domain of generating images from scene-based text descriptions. These approaches have primarily focused on generating images from a static text description and are limited to…

We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN…

This paper introduces Graph Convolutional Recurrent Network (GCRN), a deep learning model able to predict structured sequences of data. Precisely, GCRN is a generalization of classical recurrent neural networks (RNN) to data structured by…

Graph representation learning is of paramount importance for a variety of graph analytical tasks, ranging from node classification to community detection. Recently, graph convolutional networks (GCNs) have been successfully applied for…

Bottom-up approaches for image-based multi-person pose estimation consist of two stages: (1) keypoint detection and (2) grouping of the detected keypoints to form person instances. Current grouping approaches rely on learned embedding from…

Recently, graph convolutional networks (GCNs) have been developed to explore spatial relationship between pixels, achieving better classification performance of hyperspectral images (HSIs). However, these methods fail to sufficiently…

Graph Convolutional Networks (GCNs) have become a crucial tool on learning representations of graph vertices. The main challenge of adapting GCNs on large-scale graphs is the scalability issue that it incurs heavy cost both in computation…

We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes. Two steps, namely line splitting and line clustering, are performed to extract paragraphs from…