A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Filters
Learning Spatio-Temporal Representation With Local and Global Diffusion
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
In this paper, we present a novel framework to boost the spatio-temporal representation learning by Local and Global Diffusion (LGD). ...
We further examine the generalization of both the global and local representations produced by our pre-trained LGD networks on four different benchmarks for video action recognition and spatio-temporal ...
Local and Global Diffusion Blocks Unlike the existing methods which stack the local operations to learn spatio-temporal representations, our proposed Local and Global Diffusion (LGD) model additionally ...
doi:10.1109/cvpr.2019.01233
dblp:conf/cvpr/QiuYNTM19
fatcat:jqa3mai3wvddxlturmjnf23yhm
HiSTGNN: Hierarchical Spatio-temporal Graph Neural Networks for Weather Forecasting
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
An adaptive graph learning layer and spatial graph convolution are employed to construct self-learning graph and study hidden dependency among nodes of variable-level and station-level graph. ...
However, the canonical GNNs-based methods only individually model the local graph of meteorological variables per station or the global graph of whole stations, lacking information interaction between ...
ACKNOWLEDGMENT This research was supported by the National Key R&D Program of China (2019YFB2101802) and the National Natural Science Foundation of China (No. 61773324). ...
arXiv:2201.09101v1
fatcat:2x3synujnvfmrhdvctqdsviay4
STJLA: A Multi-Context Aware Spatio-Temporal Joint Linear Attention Network for Traffic Forecasting
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Furthermore, the multi-head diffusion convolution network based dynamic spatial context enhances the local spatial perception ability, and the GRU based dynamic temporal context stabilizes sequence position ...
joint graph to capture global dependence between all spatio-temporal nodes efficiently. ...
local spatio-temporal dependencies to make up for the prior biases and augment order information of long sequence. ...
arXiv:2112.02262v1
fatcat:e2bagkvdpjdu7awhyoig2pbxeu
MFDGCN: Multi-Stage Spatio-Temporal Fusion Diffusion Graph Convolutional Network for Traffic Prediction
2022
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Therefore, we propose a new deep learning model Multi-Stage Spatio-Temporal Fusion Diffusion Graph Convolutional Network (MFDGCN). ...
This promotes the effective fusion of a spatio-temporal multimodal and uses the diffuse convolution method to model the graph structure and time series in traffic prediction, respectively. ...
For each head attention, we determine the importance of the spatio-temporal representation as predicted from the historical spatio-temporal representation and sum it with the weighted feature matrix after ...
doi:10.3390/app12052688
fatcat:u2v25562ubhabbi54mtfrdwabm
Spatio-Temporal Laplacian Pyramid Coding for Action Recognition
2014
IEEE Transactions on Cybernetics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In contrast to sparse representations based on detected local interest points, STLPC regards a video sequence as a whole with spatio-temporal features directly extracted from it, which prevents the loss ...
and over spatio-temporal neighborhoods. ...
Neural networks and deep learning algorithms are also exploited for learning spatio-temporal global features for holistic representations. ...
doi:10.1109/tcyb.2013.2273174
pmid:23912503
fatcat:jjqjkgwdcnhsdm4adfwgppcbpy
Spatio-Temporal Dual Graph Neural Networks for Travel Time Estimation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In order to extract the joint spatio-temporal correlations of the intersections and road segments, we adopt the spatio-temporal dual graph learning approach that incorporates multiple spatial-temporal ...
dual graph learning modules with multi-scale network architectures for capturing multi-level spatial-temporal information from the dual graph. ...
Therefore, to better capture both global and local spatio-temporal dependencies, we make full of the multi-scale information. ...
arXiv:2105.13591v2
fatcat:rltzfzmpufc7hly6ty72q62mw4
BiST: Bi-directional Spatio-Temporal Reasoning for Video-Grounded Dialogues
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Specifically, our approach not only exploits both spatial and temporal-level information, but also learns dynamic information diffusion between the two feature spaces through spatial-to-temporal and temporal-to-spatial ...
To address this drawback, we propose Bi-directional Spatio-Temporal Learning (BiST), a vision-language neural framework for high-resolution queries in videos based on textual cues. ...
., 2019) in which local and global visual signals are learned and diffused iteratively. ...
arXiv:2010.10095v1
fatcat:jiipwofx3fcvhh2vomtjrhlxrm
Spatio-Temporal Graph Routing for Skeleton-Based Action Recognition
2019
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
With the representation effectiveness, skeleton-based human action recognition has received considerable research attention, and has a wide range of real applications. ...
In this paper, we propose a novel spatio-temporal graph routing (STGR) scheme for skeletonbased action recognition, which adaptively learns the intrinsic high-order connectivity relationships for physicallyapart ...
considers the spatio-temporal graph in a global way. ...
doi:10.1609/aaai.v33i01.33018561
fatcat:7muszebqybeyjmr44m2la5aova
ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
in local or global scope from spatio-temporal graphs simultaneously. ...
The spatio-temporal graph learning is becoming an increasingly important object of graph study. ...
Overall, with contributions of hierarchical U-shaped design, ST-UNet is able to effectively derive multi-scale features and precisely learn representations from the spatio-temporal graph. ...
arXiv:1903.05631v2
fatcat:itqubnnqufamfkpjojs5dujzse
Dynamic Global-Local Spatial-Temporal Network for Traffic Speed Prediction
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
They all adopt the diffusion convolution to capture local spatial correlations and then integrate it with the dynamic global spatial correlations. ...
local and global information simultaneously from both temporal and spatial perspective. ...
He is currently pursuing the PH.D degree with the Hefei Institutes of Physical Science, Chinese Academy of Sciences, and also with the University of Science and Technology of China (USTC). ...
doi:10.1109/access.2020.3038380
fatcat:ziul4tawm5hite2c5imzgehmea
Defending Water Treatment Networks: Exploiting Spatio-temporal Effects for Cyber Attack Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
After preliminary exploring the sensing data of WTNs, we find that integrating spatio-temporal knowledge, representation learning, and detection algorithms can improve attack detection accuracy. ...
We then construct Spatio-Temporal Graphs (STGs), where a node is a sensor and an attribute is the temporal embedding vector of the sensor, to describe the state of the WTNs. ...
Next, we briefly introduce our structured spatio-temporal detection framework named STDO. Phase 1: Spatio-temporal representation learning. ...
arXiv:2008.12618v1
fatcat:fpdkkveauvcspmogn7rhrhirhi
Spatio-Temporal meets Wavelet: Disentangled Traffic Flow Forecasting via Efficient Spectral Graph Attention Network
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
the spatio-temporal dependencies under long- and short-term schemas of the low- and high-frequency components. ...
short-term thunderstorm and long-term daily trends) within a single method, which fail to accurately capture spatio-temporal dependencies under different schemas; ii) the under-exploration of the graph ...
The graph wavelet corresponds to graph Laplacian eigenvectors diffused away from a centered node with a scaling matrix on the graph and can reflect the localization property compared with eigenvectors. ...
arXiv:2112.02740v2
fatcat:xbaudqqkbzhz5jjiva3gmkx33y
A generic video coding framework based on anisotropic diffusion and spatio-temporal completion
2010
2010 IEEE International Conference on Acoustics, Speech and Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
This paper develops a complete framework for perceptual video coding with anisotropic diffusion-based abstraction and completion under the spatio-temporal variation regularity. ...
The restoration inference process as a learning equivalent optimization problem from a given set of sparse data, serves as non-parametric or exemplar-based sampling method by taking 3-D spatio-temporal ...
The restoration is considered as equivalent to a learning-based optimization problem from given set of sparse data, which will enforce global spatio-temporal consistency. 60632040, No. 60772099, No. 60928003 ...
doi:10.1109/icassp.2010.5495285
dblp:conf/icassp/YuanXZ10
fatcat:7gia72uypje3dfk7gcd3poktfu
Automated Dilated Spatio-Temporal Synchronous Graph Modeling for Traffic Prediction
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
However, these separated modules with complicated designs could restrict effectiveness and efficiency of spatio-temporal representation learning. ...
Furthermore, most previous works adopt the fixed graph construction methods to characterize the global spatio-temporal relations, which limits the learning capability of the model for different time periods ...
Network, which utilizes spatio-temporal fusion graph convolution and parallel TCNs for learning localized and global spatio-temporal dependencies respecively [26]. ...
arXiv:2207.10830v1
fatcat:r777j2mbzjc7zhwopzgysmsnwa
Action recognition via spatio-temporal local features: A comprehensive study
2016
Image and Vision Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Local methods based on spatio-temporal interest points (STIPs) have shown their effectiveness for human action recognition. ...
Recently, a large number of techniques based on local features including improved variants of the BoW model, sparse coding (SC), Fisher kernels (FK), vector of locally aggregated descriptors (VLAD) as ...
In order to capture the most informative spatio-temporal relationship between local descriptors, Kovashka and Grauman [40] proposed to learn a hierarchy of spatio-temporal neighborhood features. ...
doi:10.1016/j.imavis.2016.02.006
fatcat:yqk3jumipvaorfh2ozvzb326lu
« Previous
Showing results 1 — 15 out of 5,801 results