Filters








11,671 Hits in 5.0 sec

A discriminative key pose sequence model for recognizing human interactions

Arash Vahdat, Bo Gao, Mani Ranjbar, Greg Mori
2011 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops)  
An activity is modeled with a sequence of key poses, important atomic-level actions performed by the actors.  ...  We start by describing a model of videos of a single person performing an activity. Given a set of such videos, we  ...  We search horizontally for a person nearest to the one performing the point activity and include him as the other part of the activity.  ... 
doi:10.1109/iccvw.2011.6130458 dblp:conf/iccvw/VahdatGRM11 fatcat:wjl4uyxkw5euvoxqifyrjprwy4

Not just the norm: Exemplar-based models also predict face aftereffects

David A. Ross, Mickael Deroche, Thomas J. Palmeri
2013 Psychonomic Bulletin & Review  
Here, we implemented and tested variations of norm and exemplar models.  ...  Face identity aftereffects have been taken as compelling evidence in favor of a norm-based account over an exemplar-based account.  ...  Acknowledgements This work was supported by the Temporal Dynamics of Learning Center, NSF grant SBE-0542013 and SMA-1041755, NIH core grant P30-EY008126, and the ESRC grant PTA-031-2006-00064.  ... 
doi:10.3758/s13423-013-0449-5 pmid:23690282 pmcid:PMC4151123 fatcat:qek77ibcd5hb7jmvzbpwy7yztq

A general method for human activity recognition in video

Neil Robertson, Ian Reid
2006 Computer Vision and Image Understanding  
Actions are described by a feature vector comprising both trajectory information (position and velocity), and a set of local motion descriptors.  ...  Action recognition is achieved via probabilistic search of image feature databases representing previously seen actions.  ...  The search time is improved by a factor of 20 and, since we sample many times, the search provides a set of particles which represents a distribution over the exemplar feature vectors into frames of the  ... 
doi:10.1016/j.cviu.2006.07.006 fatcat:cjcpy3lnzberjgiwqnnfpzgmhy

Diversified Trajectory Pattern Ranking in Geo-Tagged Social Media [chapter]

Zhijun Yin, Liangliang Cao, Jiawei Han, Jiebo Luo, Thomas Huang
2011 Proceedings of the 2011 SIAM International Conference on Data Mining  
We then use an exemplar-based algorithm to diversify the results in order to discover the representative trajectory patterns.  ...  The main objective is to reveal the collective wisdom recorded in the seemingly isolated photos and the individual travel sequences reflected by the geo-tagged photos.  ...  Suppose trajectory i is represented by an exemplar trajectory r(i), we can see that trajectory i becomes an exemplar if r(i) = i.  ... 
doi:10.1137/1.9781611972818.84 dblp:conf/sdm/YinCHLH11 fatcat:uvrn2e26jjdrbjo6vhdwthzsl4

Exemplar-based primitives for humanoid movement classification and control

E. Drumwright, O.C. Jenkins, M.J. Mataric
2004 IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004  
We present a unified methodology for humanoid robot control and activity classification using motor primitives [1], computationally efficient behaviors capable of perception and control.  ...  Alternatively, speed can be increased significantly at the expense of accuracy by reducing sampling and interval search granularities. B.  ...  In the offline procedure, the prediction from an activated primitive is used to incrementally update a synthesized motion trajectory.  ... 
doi:10.1109/robot.2004.1307142 dblp:conf/icra/DrumwrightJM04 fatcat:3oqwv5ofdral5fsu3lqmlci7ga

PERFORMANCE-DERIVED BEHAVIOR VOCABULARIES: DATA-DRIVEN ACQUISITION OF SKILLS FROM MOTION

ODEST CHADWICKE JENKINS, MAJA J. MATARIĆ
2004 International Journal of Humanoid Robotics  
First, we propose a representation for a skill-level interface as a "behavior vocabulary", a repertoire of modular exemplar-based memory models expressing kinematic motion.  ...  Results from evaluating an implementation of our methodology are presented along with the application of derived behavior vocabularies as predictors towards on-line humanoid trajectory formation and off-line  ...  Acknowledgements This research was supported by the DARPA MARS Grant DABT63-99-1-0015, DARPA MARS2020 Grant 5-39509-A, and ONR MURI Grant N00014-01-1-0354.  ... 
doi:10.1142/s0219843604000186 fatcat:polj3gxsjfdgppchd2ziuzxt2q

Resting State fMRI-Guided Fiber Clustering [chapter]

Bao Ge, Lei Guo, Jinglei Lv, Xintao Hu, Junwei Han, Tuo Zhang, Tianming Liu
2011 Lecture Notes in Computer Science  
Specifically, we represent the functional identity of a white matter fiber by two resting state fMRI (rsfMRI) time series extracted from the two gray matter voxels to which the fiber connects.  ...  proposed fiber clustering method can achieve meaningful bundles that are reasonably consistent across different brains, and part of the clustered bundles was validated via the benchmark data provided by  ...  (b) Joint visualization of 16 activated working memory ROIs (represented by green boxes) and clustered fiber bundles (represented by exemplars) for two subjects.  ... 
doi:10.1007/978-3-642-23629-7_19 fatcat:odcsbw56pjcdtojhfgjgvzd37a

Efficient Adversarial Attacks for Visual Object Tracking [article]

Siyuan Liang, Xingxing Wei, Siyuan Yao, Xiaochun Cao
2020 arXiv   pre-print
For targeted attack c), we attack both the exemplar image z and the specific search area (the blue part in c), which is determined by the specific trajectory.  ...  Due to incorrect activation of the response map, the search areas in adversarial examples will gradually shrink over time.  ... 
arXiv:2008.00217v1 fatcat:aspnhmvsdjg3pkxxftwt5oxsia

Feature Selection Using Enhanced Particle Swarm Optimisation for Classification Models

Hailun Xie, Li Zhang, Chee Peng Lim, Yonghong Yu, Han Liu
2021 Sensors  
The second proposed PSO model enhances the first one through four new strategies, i.e., an adaptive exemplar breeding mechanism incorporating multiple optimal signals, nonlinear function oriented search  ...  In comparison with a set of 15 classical and advanced search methods, the proposed models illustrate statistical superiority for discriminative feature selection for a total of 13 data sets.  ...  Funding: This research is funded by the RDF PhD Studentship at Northumbria University. Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable.  ... 
doi:10.3390/s21051816 pmid:33807806 pmcid:PMC7961412 fatcat:b3vhnu7qqnbnvayknlyg4t3uyy

An end-to-end system for content-based video retrieval using behavior, actions, and appearance with interactive query refinement

A. Hoogs, A. G. A. Perera, R. Collins, A. Basharat, K. Fieldhouse, C. Atkins, L. Sherrill, B. Boeckel, R. Blue, M. Woehlke, C. Greco, Z. Sun (+33 others)
2015 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)  
Queries can be posed as video exemplars, and the results can be refined through relevance feedback.  ...  Their behavior and appearance are characterized by action detectors and descriptors, which are indexed in an archive.  ...  Acknowledgement This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-08-C-0135.  ... 
doi:10.1109/avss.2015.7301807 dblp:conf/avss/HoogsPCBFASBBWG15 fatcat:54j5yknzsjgbjhsnbx7746jqp4

EXMOVES: Classifier-based Features for Scalable Action Recognition [article]

Du Tran, Lorenzo Torresani
2014 arXiv   pre-print
The entries in our descriptor are produced by evaluating a set of movement classifiers over spatial-temporal volumes of the input sequence.  ...  We show the generality of our approach by building our mid-level descriptors from two different low-level feature representations.  ...  This research was funded in part by NSF CA-REER award IIS-0952943 and NSF award CNS-1205521.  ... 
arXiv:1312.5785v3 fatcat:xgsncqmxdbhgbnkrazd5kvtphu

Modified Particle Swarm Optimization with Effective Guides

Aasam Abdul Karim, Nor Ashidi Mat Isa, Wei Hong Lim
2020 IEEE Access  
trajectory led by Global Exp P .  ...  order to adjust its search trajectory.  ...  Depending of the search performance of each MPSOEG particle, both of the global and local exemplars are switch alternately to guide its search process effectively.  ... 
doi:10.1109/access.2020.3030950 fatcat:revmfb5dtvf45oyjjxz2qwvcvm

Multi-class Semantic Video Segmentation with Exemplar-Based Object Reasoning

Buyu Liu, Xuming He, Stephen Gould
2015 2015 IEEE Winter Conference on Applications of Computer Vision  
We take an exemplar approach to object modeling by using a small set of object annotations and exploring the temporal consistency of object motion.  ...  The optimal semantic labeling is inferred by the MAP estimation of the model, which is solved by a single move-making based optimization procedure.  ...  Acknowledgments NICTA is funded by the Australian Government as represented by the Dept. of Communications and the ARC through the ICT Centre of Excellence program.  ... 
doi:10.1109/wacv.2015.140 dblp:conf/wacv/LiuHG15 fatcat:pumpr6xq3ndxrc4nx4rqmwf6pe

Behaviour understanding in video: a combined method

N. Robertson, I. Reid
2005 Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1  
Actions are described by a feature vector comprising both trajectory information (position and velocity), and a set of local motion descriptors.  ...  Action recognition is achieved via probabilistic search of image feature databases representing previously seen actions.  ...  ] method for generating a set of particles representing a distribution over trajectories, we structure the search over actions using a PCA decomposition of the database.  ... 
doi:10.1109/iccv.2005.47 dblp:conf/iccv/RobertsonR05 fatcat:g2hpqo55wjaozalwhmrldr2g6y

Behavior Recognition Using any Feature Space Representation of Motion Trajectories [chapter]

Shehzad Khalid
2012 Recent Developments in Video Surveillance  
The entry ℑ(a, b) in availability matrix stores the suitability of trajectory s b to be selected by trajectory s a as its exemplar. 3.  ...  s b to serve as an exemplar for trajectory s a while taking into account other potential exemplar for trajectory s a . 4.  ...  Is it possible to search those countless hours of videos for subjects or events of interest?  ... 
doi:10.5772/31910 fatcat:r4mb6s6v2zdrxk454vjrsposgu
« Previous Showing results 1 — 15 out of 11,671 results