14,024 Hits in 4.3 sec

Socially-Aware Large-Scale Crowd Forecasting

Alexandre Alahi, Vignesh Ramanathan, Li Fei-Fei
2014 2014 IEEE Conference on Computer Vision and Pattern Recognition  
Given this dataset, we address the problem of forecasting pedestrians' destinations, a central problem in understanding large-scale crowd mobility.  ...  We propose a new descriptor coined as Social Affinity Maps (SAM) to link broken or unobserved trajectories of individuals in the crowd, while using the OD-prior in our framework.  ...  Experiments Large-scale evaluation The data collection campaign helps us conduct various experiments in real life setting with a large and dynamic crowd.  ... 
doi:10.1109/cvpr.2014.283 dblp:conf/cvpr/AlahiRF14 fatcat:nacdlyfdr5cgrio2drngyejr44

Sensing and Forecasting Crowd Distribution in Smart Cities: Potentials and Approaches

Alket Cecaj, Marco Lippi, Marco Mamei, Franco Zambonelli
2021 IoT  
and limitations; (iii) the data analysis techniques that can be effectively used to forecast crowd distribution.  ...  The objective of this survey is to overview: (i) the many potential application areas of crowd sensing and prediction; (ii) the technologies that can be exploited to sense crowd along with their potentials  ...  In fact, it allows for both real-time large scale crowd monitoring and crowd dynamics forecasting in the long term.  ... 
doi:10.3390/iot2010003 fatcat:3iidezw7xrezthunye5ljb7yri

Smartcrowd: Novel Approach to Big Crowd Management Using Mobile Cloud Computing

Mohammed Fazil Ali, Abul Bashar, Asadullah Shah
2015 2015 International Conference on Cloud Computing (ICCC)  
This paper presents a novel approach, SmartCrowd, utilizing the Mobile Cloud Computing(MCC) as a platform to find a solution to manage a large human crowd.  ...  The proposed solution caters to big crowd management on important  ...  Performance Cited 867 times 18 A conflict analysis framework for QoS-aware routing in contention-based wireless mesh networks with beamforming antennas Cited 5 times View at Publisher 19 A network-aware  ... 
doi:10.1109/cloudcomp.2015.7149656 fatcat:gwyh63bsnzcxblklvtm7lxhyb4

Social NCE: Contrastive Learning of Socially-aware Motion Representations [article]

Yuejiang Liu, Qi Yan, Alexandre Alahi
2021 arXiv   pre-print
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds.  ...  This issue largely arises from the non-i.i.d. nature of sequential prediction in conjunction with ill-distributed training data.  ...  awareness of forecasting models.  ... 
arXiv:2012.11717v3 fatcat:dcv4cxotlfb33e6vq2ntnocugu

Problems of Mega-events Engineering Risk Management in China

Wang Shangjun, Zhang Xinjian
2012 Systems Engineering Procedia  
in large-scale events.  ...  are primarily responsible for the safety of large-scale mass activities.  ... 
doi:10.1016/j.sepro.2012.01.007 fatcat:gm2a537tdjb6xamplckmdgsuhy

FuturICT: FET Flagship Pilot Project

Steven Bishop, Dirk Helbing, Paul Lukowicz, Rosaria Conte
2011 Procedia Computer Science  
This will produce an ambitious large-scale, science-driven, visionary research initiative to promote and develop future research outcomes in ICT.  ...  FuturICT will create the scientific methods and ICT platforms needed to address planetary-scale challenges and opportunities in the 21st century.  ...  The first is the gathering of large-scale data on information spread and social reactions that occur during the crisis.  ... 
doi:10.1016/j.procs.2011.12.014 fatcat:5odzqnhh5bhnnfkysbjwp2pcby

Enhancing Mobile App User Understanding and Marketing with Heterogeneous Crowdsourced Data: A Review

Bin Guo, Yi Ouyang, Tong Guo, Longbing Cao, Zhiwen Yu
2019 IEEE Access  
PERSONALIZED AND CONTEXT-AWARE APP ADAPTATION Large-scale app usage data has been leveraged for understanding app usage patterns.  ...  The work is useful for large-scale overviews of competitor apps and gathering information about the app market.  ... 
doi:10.1109/access.2019.2918325 fatcat:de763kc4qbdy5ijo55jxyhzgt4

Unsupervised camera localization in crowded spaces

Alexandre Alahi, Judson Wilson, Li Fei-Fei, Silvio Savarese
2017 2017 IEEE International Conference on Robotics and Automation (ICRA)  
Existing camera networks in public spaces such as train terminals or malls can help social robots to navigate crowded scenes.  ...  We first estimate the pairwise camera parameters by optimally matching single-view pedestrian tracks using social awareness. Then, we show the impact of jointly estimating the network parameters.  ...  In large-scale crowded environments such as train terminals, we cannot assume that a single person is moving around with homogeneous behavior.  ... 
doi:10.1109/icra.2017.7989311 dblp:conf/icra/AlahiWFS17 fatcat:ve6omcsg5rayxatwzbnrfb5bby

Social NCE: Contrastive Learning of Socially-aware Motion Representations

Yuejiang Liu, Qi Yan, Alexandre Alahi
2021 2021 IEEE/CVF International Conference on Computer Vision (ICCV)  
Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds.  ...  This issue largely arises from the non-i.i.d. nature of sequential prediction in conjunction with ill-distributed training data.  ...  awareness of forecasting models.  ... 
doi:10.1109/iccv48922.2021.01484 fatcat:v4gfmurvancvtabtu3njsayi4u

Over-crowdedness Alert! Forecasting the Future Crowd Distribution [article]

Yuzhen Niu, Weifeng Shi, Wenxi Liu, Shengfeng He, Jia Pan, Antoni B. Chan
2020 arXiv   pre-print
Studying this research problem will benefit applications concerned with forecasting crowd dynamics.  ...  Finally, we demonstrate that our framework is able to predict the crowd distribution for different crowd scenarios and we delve into applications including predicting future crowd count, forecasting high-density  ...  These methods can hardly be applied in situations to issue an alert for the potential danger of large-scale crowd in advance.  ... 
arXiv:2006.05127v1 fatcat:y6vdv7foo5bfbngo76iiqhlxkq

Mobile Crowd Sensing and Computing

Bin Guo, Zhu Wang, Zhiwen Yu, Yu Wang, Neil Y. Yen, Runhe Huang, Xingshe Zhou
2015 ACM Computing Surveys  
With the surging of smartphone sensing, wireless networking, and mobile social networking techniques, Mobile Crowd Sensing and Computing (MCSC) has become a promising paradigm for cross-space and largescale  ...  Further, it explores the complementary roles and presents the fusion/collaboration of machine and human intelligence in the crowd sensing and computing processes.  ...  Regarding the scale of crowd data contribution, it can be small or large, ranging from a group to a community to the urban scale.  ... 
doi:10.1145/2794400 fatcat:lol35ouj75eplapvdod5kyy2me

Improved Short Term Energy Load Forecasting Using Web-Based Social Networks

Mehmed Kantardzic, Haris Gavranovic, Nedim Gavranovic, Izudin Dzafic, Hanqing Hu
2015 Social Networking  
, and other social networks feeds, and variety of city or region websites.  ...  short term load forecasting process in a smart grid.  ...  In the cases of large human crowd, with longer term duration of an event, we may use these temporal diagrams for better prediction of event dynamics through the crowd size.  ... 
doi:10.4236/sn.2015.44014 fatcat:xtyco6dvrnakhckmeddaohb7ia

Group LSTM: Group Trajectory Prediction in Crowded Scenarios [chapter]

Niccoló Bisagno, Bo Zhang, Nicola Conci
2019 Lecture Notes in Computer Science  
Then, an improved social-LSTM is adopted for future path prediction.  ...  Motivated by this phenomenon, we propose a novel approach to predict future trajectories in crowded scenes, at the group level.  ...  [29] introduced a large scale dataset that contains various types of targets (pedestrians, bikers, skateboarders, cars, buses, and golf carts) using aerial cameras, in order to evaluate trajectory forecasting  ... 
doi:10.1007/978-3-030-11015-4_18 fatcat:5gytnb5kg5fd3cn3donmfjs5yq

Human Trajectory Forecasting in Crowds: A Deep Learning Perspective

Parth Kothari, Sven Kreiss, Alexandre Alahi
2021 IEEE transactions on intelligent transportation systems (Print)  
To objectively compare the performance of these interaction-based forecasting models, we develop a large scale interaction-centric benchmark TrajNet++, a significant yet missing component in the field  ...  However, social interactions in crowded environments are not only diverse but often subtle.  ...  driven by domain knowledge for capturing social interactions. 3) We present TrajNet++, a large scale interaction-centric trajectory forecasting benchmark with novel evaluation metrics that quantify the  ... 
doi:10.1109/tits.2021.3069362 fatcat:3s7bbcpa2nesnkx57b4h7wyaki

Learning to Predict Human Behavior in Crowded Scenes [chapter]

Alexandre Alahi, Vignesh Ramanathan, Kratarth Goel, Alexandre Robicquet, Amir A. Sadeghian, Li Fei-Fei, Silvio Savarese
2017 Group and Crowd Behavior for Computer Vision  
These capabilities are often referred to as Social Intelligence [8] . Any forecasting method needs to infer the same behaviors to develop socially-aware intelligent systems.  ...  More broadly, when humans walk in a crowded public space such as a train terminal, mall, or city centers, they obey a large number of (unwritten) common sense rules and comply with social conventions.  ... 
doi:10.1016/b978-0-12-809276-7.00011-4 fatcat:qwi75gx4yfcrvhnlybo256kcoq
« Previous Showing results 1 — 15 out of 14,024 results