Topic
Spatial relation
About: Spatial relation is a research topic. Over the lifetime, 2127 publications have been published within this topic receiving 54096 citations. The topic is also known as: spatial relationship.
Papers published on a yearly basis
1 / 2
Papers
16 Aug 2019
TL;DR: This paper proposes a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling by developing a novel adaptive dependency matrix and learn it through node embedding, which can precisely capture the hidden spatial dependency in the data.
Abstract: Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.
1,614 citations
TL;DR: The problem of consistent registration of multiple frames of measurements (range scans), together with therelated issues of representation and manipulation of spatialuncertainties are studied, to maintain all the local frames of data as well as the relative spatial relationships between localframes.
Abstract: A robot exploring an unknown environment may need to build a world model from sensor measurements. In order to integrate all the frames of sensor data, it is essential to align the data properly. An incremental approach has been typically used in the past, in which each local frame of data is aligned to a cumulative global model, and then merged to the model. Because different parts of the model are updated independently while there are errors in the registration, such an approach may result in an inconsistent model.
In this paper, we study the problem of consistent registration of multiple frames of measurements (range scans), together with the related issues of representation and manipulation of spatial uncertainties. Our approach is to maintain all the local frames of data as well as the relative spatial relationships between local frames. These spatial relationships are modeled as random variables and are derived from matching pairwise scans or from odometry. Then we formulate a procedure based on the maximum likelihood criterion to optimally combine all the spatial relations. Consistency is achieved by using all the spatial relations as constraints to solve for the data frame poses simultaneously. Experiments with both simulated and real data will be presented.
1,553 citations
Posted Content•
TL;DR: Wang et al. as discussed by the authors proposed a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling, which can precisely capture the hidden spatial dependency in the data.
Abstract: Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.
1,431 citations
[...]
TL;DR: In this article, the visual system decomposes shapes into parts, and uses a rule defining part boundaries rather than part shapes, exploiting a uniformity of nature, which allows an explanation of visual illusions.
1,338 citations
TL;DR: Models of the spatial knowledge people acquire from maps and navigation and the procedures required for spatial judgments using this knowledge are proposed and results are consonant with the proposed mechanisms.
1,308 citations
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2026 | 1 |
| 2025 | 11 |
| 2024 | 27 |
| 2023 | 39 |
| 2022 | 89 |
| 2021 | 66 |