Filters








8,609 Hits in 3.8 sec

Topic Detection and Tracking with Spatio-Temporal Evidence [chapter]

Juha Makkonen, Helena Ahonen-Myka, Marko Salmenkivi
2003 Lecture Notes in Computer Science  
Topic Detection and Tracking is an event-based information organization task where online news streams are monitored in order to spot new unreported events and link documents with previously detected events  ...  We present an approach that formalizes temporal expressions and augments spatial terms with ontological information and uses this data in the detection.  ...  Allan, Lavrenko and Jin reduced the topic detection to topic tracking, and showed that the performance of tracking is unacceptably low for efficient first story detection.  ... 
doi:10.1007/3-540-36618-0_18 fatcat:3fmulfkj7fh6tnsiq2wr7vmcba

Towards context-aware search and analysis on social media data

Leon R. A. Derczynski, Bin Yang, Christian S. Jensen
2013 Proceedings of the 16th International Conference on Extending Database Technology - EDBT '13  
search, local intent search, and spatio-temporal intent search.  ...  We view social media data as a constant stream of data points, each containing text with spatial and temporal contexts.  ...  Acknowledgments This work was supported by EU funding under grants 287863 (TrendMiner 6 ) and 264994 (Geocrowd 7 ). References  ... 
doi:10.1145/2452376.2452393 dblp:conf/edbt/Derczynski0J13 fatcat:iu6hi74k5bgx7epomdmy2z5vhy

Unusual event detection using sparse spatio-temporal features and bag of words model

Balakrishna Mandadi, Amit Sethi
2013 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)  
The videos are modeled using a bag of words model for documents, where the words are prototypical sparse spatio-temporal feature descriptors extracted along moving objects in the scene of observation.  ...  We present a system for unusual event detection in single fixed camera surveillance video.  ...  We provide results of using both optical flow features and spatio-temporal features.  ... 
doi:10.1109/iciip.2013.6707670 fatcat:s66ozjlegncwhexj6psxn2oxga

Data Security in Unattended Wireless Sensor Networks through Aggregate Signcryption

Faezeh Sadat Babamir
2012 KSII Transactions on Internet and Information Systems  
distribution of spatio-temporal interest points in the clips.  ...  To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the  ...  Spatiotemporal Interest Points Spatio-temporal Trajectory Features Trajectory extraction -In realistic video, reliable spatially salient point detection and tracking algorithms are very critical for  ... 
doi:10.3837/tiis.2012.10.011 fatcat:bigk5ykfk5h6njcsagmj2pxdki

Object temporal connotation

Cristina Becchio, Cesare Bertone
2003 Brain and Cognition  
Recent studies show that what connotes an object is first of all a certain spatio-temporal structure.  ...  We argue that time is an indispensable attribute for every type of object and briefly discuss the implication of this view with respect to a specific neuropsychological syndrome: unilateral spatial neglect  ...  Acknowledgments This research has been supported by Ministry of Education (Quantitative and qualitative instruments for the analysis of the relationship in psychotherapy; Protocol No. 2001115311).  ... 
doi:10.1016/s0278-2626(03)00057-5 pmid:12821101 fatcat:i5natpxmrbf23espmgilb57bgq

A perceptually based spatio-temporal computational framework for visual saliency estimation

Petros Koutras, Petros Maragos
2015 Signal processing. Image communication  
We also provide a new movie database with eye-tracking annotation.  ...  The proposed spatio-temporal computational framework incorporates many ideas based on psychological evidences and yields significant improvements on spatio-temporal saliency estimation.  ...  The authors wish to thank all the members of the NTUA CVSP Lab who participated in the eye-tracking annotation of the movie database.  ... 
doi:10.1016/j.image.2015.08.004 fatcat:kha3povnbna5lbecznl2syefqm

Extracting Large Scale Spatio-Temporal Descriptions from Social Media [article]

Carlo Bono, Barbara Pernici
2022 arXiv   pre-print
The critical aspects of this investigation, such as event sensing, multilingualism, selection of visual evidence, and geolocation, are currently being studied as a foundation for a unified spatio-temporal  ...  This knowledge can be used to complement and confirm other spatio-temporal descriptions of events, highlighting previously unseen or undervalued aspects.  ...  Acknowledgements This work was funded by the EU H2020 project Crowd4SDG "Citizen Science for Monitoring Climate Impacts and Achieving Climate Resilience", #872944.  ... 
arXiv:2206.13281v1 fatcat:y4uckhy3cfeczpjwwm6jkspngm

Recognizing Human Actions by Using Effective Codebooks and Tracking [chapter]

Lamberto Ballan, Lorenzo Seidenari, Giuseppe Serra, Marco Bertini, Alberto Del Bimbo
2013 Advanced Topics in Computer Vision  
We also show that a strong reduction of computation time can be obtained by applying codebook size reduction with Deep Belief Networks with little loss of accuracy.  ...  in which the same action is performed by different persons, speed and duration and points of view from which the event is observed.  ...  Fig. 3 3 Example of multiple person tracking, spatio-temporal interest point detection and their association to the tracks.  ... 
doi:10.1007/978-1-4471-5520-1_3 dblp:series/acvpr/BallanSS13 fatcat:jcneb56tarbhtb7zelmarkddqe

Graph-based Correlated Topic Model for Motion Patterns Analysis in Crowded Scenes from Tracklets

Manal Alghamdi, Yoshihiko Gotoh
2018 British Machine Vision Conference  
It extends the correlated topic model (CTM) in the text processing field, by integrating the spatio-temporal graph (STG) as a prior to capture the spatial and temporal coherence between tracklets during  ...  Secondly inter-correlation is derived between the tracklets by constructing a shortest path graph with k-nearest neighbourhood (kNN) from both the spatial and temporal domains.  ...  ., Station, as opposed to Al-Masjid), and thus full and complete tracklets could be generated with its object-tracking algorithm.  ... 
dblp:conf/bmvc/AlghamdiG18 fatcat:zonwmejegnal7hk7olp6beg7ye

A Literature Review on Video Analytics of Crowded Scenes [chapter]

Myo Thida, Yoke Leng Yong, Pau Climent-Pérez, How-lung Eng, Paolo Remagnino
2013 Intelligent Multimedia Surveillance  
We discuss the merits and weaknesses of various approaches for each topic and provide a recommendation on how existing methods can be improved.  ...  those of airport concourses, railway stations, shopping malls and the like.  ...  Spatio-Temporal Gradient Feature In addition to optical flow information, other features such as spatio-temporal gradient are also used to model the regular movement of a crowd [42, 50] .  ... 
doi:10.1007/978-3-642-41512-8_2 fatcat:m45yawffhzgypcn6nsjicrvhkm

Intelligent multi-camera video surveillance: A review

Xiaogang Wang
2013 Pattern Recognition Letters  
The covered topics include multi-camera calibration, computing the topology of camera networks, multi-camera tracking, object re-identification, multi-camera activity analysis and cooperative video surveillance  ...  both with active and static cameras.  ...  This spatio-temporal reasoning can solve a lot of ambiguity during multi-camera tracking.  ... 
doi:10.1016/j.patrec.2012.07.005 fatcat:vnbxmu55x5ditdmhjvsmloezr4

Scaling Video Analytics Systems to Large Camera Deployments [article]

Samvit Jain, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Joseph E. Gonzalez
2019 arXiv   pre-print
These spatio-temporal correlations can be harnessed to dramatically reduce the size of the inference search space, decreasing both workload and false positive rates in multi-camera video analytics.  ...  By discussing use-cases and technical challenges, we propose a roadmap for scaling video analytics to large camera networks, and outline a plan for its realization.  ...  Figure 3 shows the evident imbalance in the number of people detected on two cameras across a 500 second interval.  ... 
arXiv:1809.02318v4 fatcat:rt3vxm2gb5ggfa2txmk6oigo5q

A study in the cognition of individuals' identity: Solving the problem of singular cognition in object and agent tracking

Nicolas J. Bullot, Patrick Rysiew
2007 Consciousness and Cognition  
Introduction: referring to and tracking individuals Animals and humans must refer to and trace individuals, both in perceptual tracking and in other forms of cognitive tracking (e.g., indirect spatio-temporal  ...  Such individuals follow continuous spatio-temporal paths, have cohesive parts and possess causal powers.  ...  Organism tracking requires tracking spatio-temporal object-properties because organisms fulfill objecthood criteria First, organism tracking requires tracking spatio-temporal object-properties because  ... 
doi:10.1016/j.concog.2006.09.006 pmid:17126566 fatcat:ydve5xkxeng35fhmgkzfiridki

On Space-Time Interest Points

Ivan Laptev
2005 International Journal of Computer Vision  
To represent the detected events, we then compute local, spatio-temporal, scale-invariant N -jets and classify each event with respect to its jet descriptor.  ...  We estimate the spatio-temporal extents of the detected events by maximizing a normalized spatio-temporal Laplacian operator over spatial and temporal scales.  ...  From the temporal slices of space-time volumes shown here, it is evident that the detected events correspond to neighborhoods with high spatio-temporal variation in the image data or "space-time corners  ... 
doi:10.1007/s11263-005-1838-7 fatcat:44cbrcic6bbjfblwqxwidmispi

2D Human Pose Estimation in TV Shows [chapter]

Vittorio Ferrari, Manuel Marín-Jiménez, Andrew Zisserman
2009 Lecture Notes in Computer Science  
The method is fully automatic and self-initializing, and explains the spatio-temporal volume covered by a person moving in a shot by soft-labeling every pixel as belonging to a particular body part or  ...  Moreover, when video is available, we propose methods for exploiting the temporal continuity of both appearance and pose for improving the estimation based on individual frames.  ...  We are grateful for support from EU Project CLASS, the Swiss National Science Foundation, the Royal Academy of Engineering, Microsoft, and the Spanish Ministry of Education and Science (grant FPU AP2003  ... 
doi:10.1007/978-3-642-03061-1_7 fatcat:fyg6x4rlyndujmyti44iscfznq
« Previous Showing results 1 — 15 out of 8,609 results