相关论文: High Order Structure Descriptors for Scene Images
After a somewhat rocky start, geometry and topology have established a foothold in machine learning. Message passing, either on graphs or higher-order complexes, is one of the main drivers of geometric deep learning, and paradigms that were…
Scene understanding requires the extraction and representation of scene components together with their properties and inter-relations. We describe a model in which meaningful scene structures are extracted from the image by an iterative…
The inclusion of spatial information into spectral classifiers for fine-resolution hyperspectral imagery has led to significant improvements in terms of classification performance. The task of spectral-spatial hyperspectral image…
Image feature matching plays a vital role in many computer vision tasks. Although many image feature detection and matching techniques have been proposed over the past few decades, it is still time-consuming to match feature points in two…
Current Visual Simultaneous Localization and Mapping (VSLAM) systems often struggle to create maps that are both semantically rich and easily interpretable. While incorporating semantic scene knowledge aids in building richer maps with…
In this lecture notes I concentrate on the classic and widely applicable characterization of higher order statistics by joint moments, a.k.a. higher order correlation functions, and directly related statistics. I put special emphasis on…
We present a formalism that leads very naturally to a hierarchical description of the different contrast structures in images, providing precise definitions of sharp edges and other texture components. Within this formalism, we achieve a…
This paper initiates the study of picture fuzzy topological spaces. In order to develop a mechanism to construct picture fuzzy topological spaces, we prove some basic results related to picture fuzzy sets together with the introduction of…
A growing demand for natural-scene text detection has been witnessed by the computer vision community since text information plays a significant role in scene understanding and image indexing. Deep neural networks are being used due to…
In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneously recognise…
Current semantic segmentation models only exploit first-order statistics, while rarely exploring high-order statistics. However, common first-order statistics are insufficient to support a solid unanimous representation. In this paper, we…
Common visual recognition tasks such as classification, object detection, and semantic segmentation are rapidly reaching maturity, and given the recent rate of progress, it is not unreasonable to conjecture that techniques for many of these…
Multi-view unsupervised feature selection (MUFS) has recently emerged as an effective dimensionality reduction method for unlabeled multi-view data. However, most existing methods mainly use first-order similarity graphs to preserve local…
Networks are a fundamental tool for understanding and modeling complex systems in physics, biology, neuroscience, engineering, and social science. Many networks are known to exhibit rich, lower-order connectivity patterns that can be…
Recent approaches on visual scene understanding attempt to build a scene graph -- a computational representation of objects and their pairwise relationships. Such rich semantic representation is very appealing, yet difficult to obtain from…
Self-organizing maps (SOMs) are a technique that has been used with high-dimensional data vectors to develop an archetypal set of states (nodes) that span, in some sense, the high-dimensional space. Noteworthy applications include weather…
Visual localization techniques rely upon some underlying scene representation to localize against. These representations can be explicit such as 3D SFM map or implicit, such as a neural network that learns to encode the scene. The former…
Image-text retrieval of natural scenes has been a popular research topic. Since image and text are heterogeneous cross-modal data, one of the key challenges is how to learn comprehensive yet unified representations to express the…
We present an approach for mobile robots to recognize scenes in object arrangements distributed across cluttered environments. Recognition is enabled by intertwining the robot's search for objects and the assignment of found objects to…
Foreground object search (FOS) aims to find compatible foreground objects for a given background image, producing realistic composite image. We observe that competitive retrieval performance could be achieved by using a discriminator to…