Filters








21,889 Hits in 5.5 sec

Abstraction of Graph Transformation Systems by Temporal Logic and Its Verification [chapter]

Mitsuharu Yamamoto, Yoshinori Tanabe, Koichi Takahashi, Masami Hagiya
2008 Lecture Notes in Computer Science  
Acknowledgments The authors are grateful to anonymous reviewers for their constructive comments.  ...  This research was also partially supported by the Ministry of Education, Science, Sports and Culture, Grant-in-Aid for Scientific Research on Priority Areas, 16016211, 2004.  ...  Graph transformation systems [11] , which can model many distributed and concurrent algorithms, are examples of such infinite systems.  ... 
doi:10.1007/978-3-540-69149-5_57 fatcat:hadfulpoaba4heq3bhfzgcqeou

TOWARDS LIMITING SEMANTIC DATA LOSS IN 4D URBAN DATA SEMANTIC GRAPH GENERATION

D. Vinasco-Alvarez, J. Samuel, S. Servigne, G. Gesquière
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
Secondly, this paper will demonstrate how semantic graphs based on these models can be implemented for spatial and temporal queries toward 4D semantic city model enrichment.  ...  Transformation tools can use this model to map datasets to interoperable semantic graph formats of 4D city models.  ...  ACKNOWLEDGMENTS The authors would like to thank University Lumière Lyon 2 for funding the PhD Thesis of Diego Vinasco-Alvarez. This work has been done within the LIRIS Vcity project 21 .  ... 
doi:10.5194/isprs-annals-viii-4-w2-2021-37-2021 fatcat:zb3gdqf2rfc4zbv7gjuucsf25u

HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition [article]

Ziyu Jia, Youfang Lin, Jing Wang, Zhiyang Feng, Xiangheng Xie, Caijie Chen
2021 arXiv   pre-print
Each stream is composed of the graph transformer network for modeling the heterogeneity, the graph convolutional network for modeling the correlation, and the gated recurrent unit for capturing the temporal  ...  However, it is challenging to make full use of the complementarity among spatial-spectral-temporal domain features for emotion recognition, as well as model the heterogeneity and correlation among multi-modal  ...  We are grateful for supporting from Swarma-Kaifeng Workshop which is sponsored by Swarma Club and Kaifeng Foundation.  ... 
arXiv:2108.03354v1 fatcat:o3esloogcfewddsmyzu2gv3tu4

Control flow coalescing on a hybrid dataflow/von Neumann GPGPU

Dani Voitsechov, Yoav Etsion
2015 Proceedings of the 48th International Symposium on Microarchitecture - MICRO-48  
graph instruction words (GIW) • GIWs concurrently execute for vectors of threads • von Neumann control flow dynamically schedules VGIWs on the CGRA • Threads are coalesced according to their control flow  ...  (and spatial) division of the HW between the BBs Underutilized due to spatial division of the HW between the BBs Fully utilized GPGPU SGMF VGIW Machine Model • Each thread may take a different  ... 
doi:10.1145/2830772.2830817 dblp:conf/micro/VoitsechovE15 fatcat:zkoeg77jjbfs3kdc22ni57jmlu

Automatic algorithm transformation for efficient multi-snapshot analytics on temporal graphs

Manuel Then, Timo Kersten, Stephan Günnemann, Alfons Kemper, Thomas Neumann
2017 Proceedings of the VLDB Endowment  
We present Single Algorithm Multiple Snapshots (SAMS), a novel approach to execute algorithms concurrently for multiple graph snapshots.  ...  For this purpose, algorithms must be executed for multiple graph snapshots.  ...  To model the graphs' temporal dimension, we store vertex and edge creation times directly within the CSR.  ... 
doi:10.14778/3090163.3090166 fatcat:oegznfd75va2pjad4dfedmbpxa

Long-Range Transformers for Dynamic Spatiotemporal Forecasting [article]

Jake Grigsby, Zhe Wang, Yanjun Qi
2022 arXiv   pre-print
State-of-the-art sequence-to-sequence models rely on neural attention between timesteps, which allows for temporal learning but fails to consider distinct spatial relationships between variables.  ...  However, these methods often rely on predefined graphs and perform separate spatial and temporal updates without establishing direct connections between each variable at every timestep.  ...  The code for the Spacetimeformer model was originally based on the Informer open-source release.  ... 
arXiv:2109.12218v2 fatcat:3h5jibzjzzgntegpygzh3makpm

Spatial and temporal refinement of typed graph transformation systems [chapter]

Martin Große-Rhode, Francesco Parisi-Presicce, Marta Simeoni
1998 Lecture Notes in Computer Science  
Graph transformation systems support the formal modeling of dynamic, concurrent, and distributed systems.  ...  In this paper we investigate two kinds of refinement relations for graph transformation systems in order to support the development of a module concept for graph transformation systems.  ...  The spatial (temporal) refinement category SR ≡ (resp. TR ≡ ) has graph transformation systems as objects and equivalence classes of spatial (temporal) refinements as morphism.  ... 
doi:10.1007/bfb0055805 fatcat:dddryscypja2bgilz4sf63ys2y

Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting

Mengzhang Li, Zhanxing Zhu
2021 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Existing frameworks usually utilize given spatial adjacency graph and sophisticated mechanisms for modeling spatial and temporal correlations.  ...  However, limited representations of given spatial graph structure with incomplete adjacent connections may restrict effective spatial-temporal dependencies learning of those models.  ...  Transformer models such as (Wang et al. 2020; Park et al. 2019 ) utilize spatial and temporal attention modules in transformer for spatial-temporal modeling.  ... 
doi:10.1609/aaai.v35i5.16542 fatcat:mdpj22qh5bd2zhq7yh5ojsrtte

OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement [article]

Fangyi Zhu, Jenq-Neng Hwang, Zhanyu Ma, Guang Chen, Jun Guo
2020 arXiv   pre-print
The temporal graph provides useful supplement over previous image-based approaches, allowing to reason the activities from the temporal evolution of visual features and the dynamic movement of spatial  ...  We introduce the video-based object-oriented video captioning network (OVC)-Net via temporal graph and detail enhancement to effectively analyze the activities along time and stably capture the vision-language  ...  In Fig. 4 , we show the process of building a temporal graph for an object. Actually, we build the temporal graph for each object in the video, thus we can describe all concurrent objects. B.  ... 
arXiv:2003.03715v5 fatcat:g5trretzdjauplie7estebze2a

DESIGN DATABASE MODELING FOR THE FUTURE CAD SYSTEMS

Deyi Xue, Haoguang Yang
2011 Proceedings of the Canadian Engineering Education Association (CEEA)  
for supporting various lifecycle aspects in concurrent design.  ...  To develop the future CAD systems with concurrent engineering functions, a new CAD model, called Concurrent Engineering-oriented Design Database Representation Model (CE-DDRM), is introduced in this research  ...  Sriram at the NIST for his encouragement, support, and discussion to the development of this concurrent engineering-oriented design database representation model.  ... 
doi:10.24908/pceea.v0i0.4042 fatcat:fjqjxipnerbg3kjp5smmrbyvji

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection [article]

Kyle Min, Sourya Roy, Subarna Tripathi, Tanaya Guha, Somdeb Majumdar
2022 arXiv   pre-print
In this paper, we present SPELL, a novel spatial-temporal graph learning framework that can solve complex tasks such as ASD.  ...  explicit spatial and temporal structure.  ...  This gives us three separate graphs where each of the graphs can model different spatial-temporal relationships between the nodes.  ... 
arXiv:2207.07783v2 fatcat:t3lq3s5jn5fh7e2jdfk4qqikna

Revisiting spatio-temporal layouts for compositional action recognition [article]

Gorjan Radevski, Marie-Francine Moens, Tinne Tuytelaars
2021 arXiv   pre-print
The main focus of this paper is compositional/few-shot action recognition, where we advocate the usage of multi-head attention (proven to be effective for spatial reasoning) over spatio-temporal layouts  ...  On the Something-Else and Action Genome datasets, we demonstrate (i) how to extend multi-head attention for spatio-temporal layout-based action recognition, (ii) how to improve the performance of appearance-based  ...  We also thank Dina Trajkovska for the help with the figures.  ... 
arXiv:2111.01936v1 fatcat:q3l3m7nj7jadflecmeulmwefcy

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs [article]

Shengyu Feng, Subarna Tripathi, Hesham Mostafa, Marcel Nassar, Somdeb Majumdar
2021 arXiv   pre-print
Structured video representation in the form of dynamic scene graphs is an effective tool for several video understanding tasks.  ...  Compared to the task of scene graph generation from images, dynamic scene graph generation is more challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions  ...  Another recent work, Spatial-Temporal Transformer (STTran) [6] grounds the model on the adjacent key frames.  ... 
arXiv:2112.09828v1 fatcat:mhyikupbf5gnfasfpfoosddrxm

Rapid dynamic speech imaging at 3 Tesla using combination of a custom vocal tract coil, variable density spirals and manifold regularization [article]

Rushdi Zahid Rusho, Abdul Haseeb Ahmed, Stanley Kruger, Wahidul Alam, David Meyer, David Howard, Ingo Titze, Mathews Jacob, Sajan Goud Lingala
2022 arXiv   pre-print
Results: We achieved a spatial resolution of 2.4mm2/pixel and a temporal resolution of 17.4 ms/frame for single slice imaging, and 52.2 ms/frame for concurrent 3-slice imaging.  ...  This was reflected by higher image quality scores in spatial and temporal blurring categories.  ...  Our scheme achieved a temporal resolution of ~17.4 ms/frame for single slice and ~52.2ms/frame for concurrent three slice imaging at a spatial resolution of 2.4 mm 2 /pixel.  ... 
arXiv:2209.02768v1 fatcat:p4w3o3jplnh2xgacvnx5duchgq

TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning [article]

Yang Liu, Keze Wang, Lingbo Liu, Haoyuan Lan, Liang Lin
2022 arXiv   pre-print
(TCGL), which jointly models the inter-snippet and intra-snippet temporal dependencies for temporal representation learning with a hybrid graph contrastive learning strategy.  ...  discrete cosine transform.  ...  Frequency Filtering Embedding (FFE) [82] used graph Fourier transform and frequency filtering as a graph Fourier domain operator for graph feature extraction.  ... 
arXiv:2112.03587v3 fatcat:fgrz462zsrdt5ooprppcks4yim
« Previous Showing results 1 — 15 out of 21,889 results