Filters








224,904 Hits in 4.3 sec

Temporal Network Sampling [article]

Nesreen K. Ahmed, Nick Duffield, Ryan A. Rossi
2021 arXiv   pre-print
We develop online, single-pass sampling algorithms and unbiased estimators for temporal network sampling.  ...  In this work, we propose a general framework for temporal network sampling with unbiased estimation.  ...  Temporal Network Sampling  ... 
arXiv:1910.08657v2 fatcat:dgk5tqlxvfhmpj5tnlwy4nrk5a

LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection [article]

Sanqing Qu, Guang Chen, Dan Xu, Jinhu Dong, Fan Lu, Alois Knoll
2020 arXiv   pre-print
Online action detection is a task with the aim of identifying ongoing actions from streaming videos without any side information or access to future frames.  ...  Specifically, in this paper, we propose a novel Learning Action Progression Network termed LAP-Net, which integrates an adaptive features sampling strategy.  ...  We can see that the introduction of our adaptive features sampling strategy can significantly boost the online action detection performance through the results. Study on Temporal Range Size.  ... 
arXiv:2011.07915v1 fatcat:jmb3g7oawnfl5ojqyv3oo42lhm

ECO: Efficient Convolutional Network for Online Video Understanding [chapter]

Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox
2018 Lecture Notes in Computer Science  
span several seconds. (2) While there are local methods with fast perframe processing, the processing of the whole video is not efficient and hampers fast video retrieval or online classification of long-term  ...  The architecture is based on merging long-term content already in the network rather than in a post-hoc fusion.  ...  Fig. 3 : 3 Scheme of our sampling strategy for online video understanding.  ... 
doi:10.1007/978-3-030-01216-8_43 fatcat:bjwjwxf6j5c2piomvho7y7hssa

Tutorial on graph stream analytics

András Benczúr, Ferenc Béres, Domokos Kelen, Róbert Pálovics
2021 Proceedings of the 15th ACM International Conference on Distributed and Event-based Systems  
First we introduce the data streaming computational model and give examples of the so-called temporal networks.  ...  In this short tutorial, we cover recent methods to analyze and model network data accessible as a stream of edges, such as interactions in a social network service, or any other graph database with real-time  ...  EXAMPLES OF TEMPORAL NETWORKS AND EDGE STREAMS Most of the networks in nature, society, and technology change over time.  ... 
doi:10.1145/3465480.3468293 fatcat:a2odkdlvhrhwbhohqlezvnogre

ECO: Efficient Convolutional Network for Online Video Understanding [article]

Mohammadreza Zolfaghari, Kamaljeet Singh, Thomas Brox
2018 arXiv   pre-print
span several seconds. (2) While there are local methods with fast per-frame processing, the processing of the whole video is not efficient and hampers fast video retrieval or online classification of  ...  The architecture is based on merging long-term content already in the network rather than in a post-hoc fusion.  ...  Fig. 3 : 3 Scheme of our sampling strategy for online video understanding.  ... 
arXiv:1804.09066v2 fatcat:phj7c67jrreybjjhqmnuno2cpy

Online Detection of Action Start in Untrimmed, Streaming Videos [article]

Zheng Shou, Junting Pan, Jonathan Chan, Kazuyuki Miyazawa, Hassan Mansour, Anthony Vetro, Xavier Giro-i-Nieto, Shih-Fu Chang
2018 arXiv   pre-print
background, (2) explicitly modeling the temporal consistency between data around action start and data succeeding action start, and (3) adaptive sampling strategy to handle the scarcity of training data  ...  We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos.  ...  Although these methods for temporal localization were originally designed for the offline setting, some of them can be adapted to conduct temporal localization in an online manner.  ... 
arXiv:1802.06822v3 fatcat:ob5gy45jjbgifgjgj35o4f5dt4

Spatio-Temporal Correlation Analysis of Online Monitoring Data for Anomaly Detection in Distribution Networks [article]

Xin Shi, Robert Qiu, Zenan Ling, Fan Yang, Xing He
2018 arXiv   pre-print
The online monitoring data in distribution networks contain rich information on the running states of the system.  ...  First, spatio-temporal matrix for each feeder in the distribution network is formulated and the spectrum of its covariance matrix is analyzed.  ...  of spatio-temporal correlations of the online monitoring data in real-time.  ... 
arXiv:1810.08962v1 fatcat:sbdlyejevraxjincms6ihouavm

Online Detection of Action Start in Untrimmed, Streaming Videos [chapter]

Zheng Shou, Junting Pan, Jonathan Chan, Kazuyuki Miyazawa, Hassan Mansour, Anthony Vetro, Xavier Giro-i-Nieto, Shih-Fu Chang
2018 Lecture Notes in Computer Science  
background, (2) explicitly modeling the temporal consistency between data around action start and data succeeding action start, and (3) adaptive sampling strategy to handle the scarcity of training data  ...  We aim to tackle a novel task in action detection -Online Detection of Action Start (ODAS) in untrimmed, streaming videos.  ...  Although these methods for temporal localization were originally designed for the offline setting, some of them can be adapted to conduct temporal localization in an online manner.  ... 
doi:10.1007/978-3-030-01219-9_33 fatcat:srxbb2ipvvcixoxftlpiuy4aly

Dynamic Node Embeddings from Edge Streams [article]

John Boaz Lee, Giang Nguyen, Ryan A. Rossi, Nesreen K. Ahmed, Eunyee Koh, Sungchul Kim
2020 arXiv   pre-print
As such CTDNEs naturally support online learning of the node embeddings in a streaming real-time fashion.  ...  approximating the temporal network as a sequence of static snapshot graphs.  ...  In the case of learning CTDNEs in an online fashion, we do not need to select the initial edge since we simply sample a number of temporal walks that end at the new edge.  ... 
arXiv:1904.06449v2 fatcat:nmfuo63f2zdbfkf6v7on235gsu

Node embeddings in dynamic graphs

Ferenc Béres, Domokos M. Kelen, Róbert Pálovics, András A. Benczúr
2019 Applied Network Science  
Most of the known techniques extract embeddings from static graph snapshots. By contrast, modeling the dynamics of the nodes in temporal networks requires evolving node representations.  ...  Recently, several representation learning methods have been proposed that are capable of embedding nodes in a vector space in a way that captures the network structure.  ...  Finally, in "Online link prediction" section we consider the online link prediction problem as another evaluation of our methods. Related works Temporal networks.  ... 
doi:10.1007/s41109-019-0169-5 fatcat:2bwsewieobbg7hkrd2qu3wmnmi

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds [article]

Siyuan Huang, Yichen Xie, Song-Chun Zhu, Yixin Zhu
2021 arXiv   pre-print
In this paper, we tackle this challenge by introducing a spatio-temporal representation learning (STRL) framework, capable of learning from unlabeled 3D point clouds in a self-supervised fashion.  ...  To corroborate the efficacy of STRL, we conduct extensive experiments on three types (synthetic, indoor, and outdoor) of datasets.  ...  Output: online encoder e θ . 8 for k " 1 to K do / * sample batches of temporal-correlated point clouds • Down-sampling.  ... 
arXiv:2109.00179v1 fatcat:pv7hktdu5bdfhootjdca3rheey

Dynamic Inference: A New Approach Toward Efficient Video Action Recognition [article]

Wenhao Wu, Dongliang He, Xiao Tan, Shifeng Chen, Yi Yang, Shilei Wen
2020 arXiv   pre-print
and video temporal relation modeling by introducing an online temporal shift module.  ...  The dynamic inference approach can be achieved from aspects of the network depth and the number of input video frames, or even in a joint input-wise and network depth-wise manner.  ...  Online temporal shift Temporal modeling by online temporal shift is also essential for the final performance.  ... 
arXiv:2002.03342v1 fatcat:7fu3u6hmirg4dp7jam2yfaznmm

Online Multi-Object Tracking with Dual Matching Attention Networks [article]

Ji Zhu, Hua Yang, Nian Liu, Minyoung Kim, Wenjun Zhang, Ming-Hsuan Yang
2019 arXiv   pre-print
levels of attention to different samples in the tracklet to suppress noisy observations.  ...  The spatial attention module generates dual attention maps which enable the network to focus on the matching patterns of the input image pair, while the temporal attention module adaptively allocates different  ...  Temporal Attention Network.  ... 
arXiv:1902.00749v1 fatcat:62swpawsxracde4sdsvur4ghki

Online Multi-Object Tracking with Dual Matching Attention Networks [chapter]

Ji Zhu, Hua Yang, Nian Liu, Minyoung Kim, Wenjun Zhang, Ming-Hsuan Yang
2018 Lecture Notes in Computer Science  
levels of attention to different samples in the tracklet to suppress noisy observations.  ...  The spatial attention module generates dual attention maps which enable the network to focus on the matching patterns of the input image pair, while the temporal attention module adaptively allocates different  ...  It consists of the Spatial Attention Network (SAN) and Temporal Attention Network (TAN).  ... 
doi:10.1007/978-3-030-01228-1_23 fatcat:s3tyz77aofcjhozgesqzhkjd4q

Shoreline: Data-Driven Threshold Estimation of Online Reserves of Cryptocurrency Trading Platforms (Student Abstract)

Xitong Zhang, He Zhu, Jiayu Zhou
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The most critical vulnerability of crypto-exchanges is from the so-called hot wallet, which is used to store a certain portion of the total asset online of an exchange and programmatically sign transactions  ...  In this paper, we propose Shoreline, a deep learning-based threshold estimation framework that estimates the optimal threshold of hot wallets from historical wallet activities and dynamic trading networks  ...  Acknowledgments This material is based upon work supported by the VeResearch research gift from VeChain Foundation, National Science Foundation under Grant IIS-1749940, IIS-1615597, and Office of Naval  ... 
doi:10.1609/aaai.v34i10.7265 fatcat:4jdwgl7o6zaedoaj4motjfq5ru
« Previous Showing results 1 — 15 out of 224,904 results