450 Hits in 10.6 sec

Augmenting Bag-of-Words: Data-Driven Discovery of Temporal and Structural Information for Activity Recognition

Vinay Bettadapura, Grant Schindler, Thomas Ploetz, Irfan Essa
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We present data-driven techniques to augment Bag of Words (BoW) models, which allow for more robust modeling and recognition of complex long-term activities, especially when the structure and topology  ...  Our approach specifically addresses the limitations of standard BoW approaches, which fail to represent the underlying temporal and causal information that is inherent in activity streams.  ...  We thank Kitware, Disney Research and DARPA for providing the Ocean City, Soccer and WAAS datasets, respectively.  ... 
doi:10.1109/cvpr.2013.338 dblp:conf/cvpr/BettadapuraSPE13 fatcat:qi2pddgmhbefxkkc3rhqslt42e

Augmenting User Models with Real World Experiences to Enhance Personalization and Adaptation [chapter]

Fabian Abel, Vania Dimitrova, Eelco Herder, Geert-Jan Houben
2012 Lecture Notes in Computer Science  
The AUM workshop aims to create a forum for academic and industrial researchers and practitioners to discuss augmented user modeling from three angles: -Modeling: methods and techniques for analyzing digital  ...  Technological advancements, such as data/text mining, information extraction, opinion mining, social signal processing, interactive story telling, intelligent media annotation, semantic alignment, media  ...  We thank the members of the Program Committee of AUM 2011 for their support and reviews.  ... 
doi:10.1007/978-3-642-28509-7_4 fatcat:ogz2gojyszffvdtq6fy4itvite

A Hybrid Approach to Recognising Activities of Daily Living from Object Use in the Home Environment

Isibor Ihianle, Usman Naeem, Syed Islam, Abdel-Rahman Tawil
2018 Informatics  
A significant step in the recognition of activities is the accurate discovery of the object usage for specific routine activities.  ...  Current knowledge-driven and ontology-based techniques model object concepts from assumptions and everyday common knowledge of object use for routine activities.  ...  In the context of our activity-object use discovery process, the activity topic number and bag of sensor observations corresponds to the topic number and bag of words respectively of the LDA.  ... 
doi:10.3390/informatics5010006 fatcat:dp5mbujy4ja2vm3pvgea3sdhg4

Augmenting Transactive Memory Systems In Virtual Teams By Means Of Natural Language Processing And Machine Learning

Jamal Armel
2017 Zenodo  
TMS has been shown to be valuable for efforts to integrate and renovate knowledge assets of the organisation.  ...  this data into broad areas of expertise.  ...  The range and variety of the aspects I researched and the knowledge I have acquired through examining numerous theoretical and technical areas resulted in a truly challenging and stimulating research journey  ... 
doi:10.5281/zenodo.844844 fatcat:rma6cm6y6vai5dznmooj467rdq

Action Spotting and Recognition Based on a Spatiotemporal Orientation Analysis

K. G. Derpanis, M. Sizintsev, K. J. Cannons, R. P. Wildes
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper provides a unified framework for the interrelated topics of action spotting, the spatiotemporal detection and localization of human actions in video, and action recognition, the classification  ...  The general approach presented for action spotting and recognition is amenable to efficient implementation, which is deemed critical for many important applications.  ...  ACKNOWLEDGMENTS Portions of this research were funded by an NSERC Discovery Grant to R. Wildes. The authors thank H. Seo and P. Milanfar for providing their cropped KTH templates, and T.  ... 
doi:10.1109/tpami.2012.141 pmid:26353139 fatcat:7h5me2vj2rabxmszstrnrc7wx4

From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding

Weiyu Zhang, Menglong Zhu, Konstantinos G. Derpanis
2013 2013 IEEE International Conference on Computer Vision  
., position) across spacetime are used in a data-driven training process to discover patches that are highly clustered in the spacetime keypoint configuration space.  ...  Unlike previous action-related work, the discovery of patch classifiers is posed as a strongly-supervised process.  ...  A data-driven approach informed by rich training data (i.e., keypoints across spacetime) is used to identify the optimal operating points between these two extremes.  ... 
doi:10.1109/iccv.2013.280 dblp:conf/iccv/ZhangZD13 fatcat:onk6beoitjawpo2bfuoois2fyi

Web Analytics for Security Informatics

Kristin Glass, Richard Colbaugh
2011 2011 European Intelligence and Security Informatics Conference  
An enormous volume of security-relevant information is present on the Web, for instance in the content produced each day by millions of bloggers worldwide, but discovering and making sense of these data  ...  The proposed approach involves collecting and integrating three types of Web data -textual, relational, and temporal -to perform assessments and generate insights that would be difficult or impossible  ...  metadata, relational data, and temporal information.  ... 
doi:10.1109/eisic.2011.66 dblp:conf/eisic/GlassC11 fatcat:7gw736woknhhbgfvp42n7fg5me

High-level event recognition in unconstrained videos

Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, Mubarak Shah
2012 International Journal of Multimedia Information Retrieval  
While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features  ...  In this paper, we review current technologies for complex event recognition in unconstrained videos.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
doi:10.1007/s13735-012-0024-2 fatcat:mfzttic3svb4tho2xb6aczgp4y

Space-time tree ensemble for action recognition

Shugao Ma, Leonid Sigal, Stan Sclaroff
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We explore ensembles of hierarchical spatio-temporal trees, discovered directly from training data, to model these structures for action recognition.  ...  However, discovery of frequent and discriminative tree structures is challenging due to the exponential search space, particularly if one allows partial matching.  ...  This work was supported in part through US NSF grants #1029430 and #0910908.  ... 
doi:10.1109/cvpr.2015.7299137 dblp:conf/cvpr/MaSS15 fatcat:s46ndbp62vez7el2clvgzedqwu

Discovering meaning on the go in large heterogenous data

Harry Halpin, Fiona McNeill
2013 Artificial Intelligence Review  
Those creating the data will use their own terminology, structure and formats for the data, meaning that data from one source will be incompatible with data from another source.  ...  This o↵ers massive potential for interaction and mutual collaboration. But using this data often creates problems.  ...  bag-of-words and the bag-of-words for each of its own terms, thereby finding those most likely to match.  ... 
doi:10.1007/s10462-012-9377-4 fatcat:zy3swcqdrjbtrdqsjti4mogbmi

A Meaningful Information Extraction System for Interactive Analysis of Documents

Julien Maitre, Michel Menard, Guillaume Chiron, Alain Bouju, Nicolas Sidere
2019 2019 International Conference on Document Analysis and Recognition (ICDAR)  
For text analysis and extraction, topic models are based on the bag of words hypothesis. Different types of "bag of words" exist in the literature.  ...  Decision-making is constrained by temporal necessities and thus requires rapidly processing a large mass of information.  ... 
doi:10.1109/icdar.2019.00024 dblp:conf/icdar/MaitreMCBS19 fatcat:z6fkonijyvfmfnmbqdyrsruvy4

A Natural and Immersive Virtual Interface for the Surgical Safety Checklist Training

Andrea Ferracani, Daniele Pezzatini, Alberto Del Bimbo
2014 Proceedings of the 2014 ACM International Workshop on Serious Games - SeriousGames '14  
By leveraging big data from billions of search queries, billions of images on the web and from the social networks, and billions of user clicks, we have designed massive machine learning systems to continuously  ...  With the focus on natural language and entity understanding, for instance, we have improved Bing's ability to understand the user intent beyond queries and keywords.  ...  Kang, Yonghao He, Shiming Xiang, Chunhong Pan Bag-of-Words Based Deep Neural Network for Image Retrieval Yalong Bai, Wei Yu, Tianjun Xiao, Chang Xu, Kuiyuan Yang, Tiejun Zhao, Wei-Ying Ma Multi-modal  ... 
doi:10.1145/2656719.2656725 dblp:conf/mm/FerracaniPB14a fatcat:obsb2i4iybhu3dq77hujvjtbze

Geotagging in multimedia and computer vision—a survey

Jiebo Luo, Dhiraj Joshi, Jie Yu, Andrew Gallagher
2010 Multimedia tools and applications  
can benefit from the use of geographical information, and 3) The interplay between modalities and applications.  ...  In this paper, we survey geo-tagging related research within the context of multimedia and along three dimensions: 1) Modalities in which geographical information can be extracted, 2) Applications that  ...  Instead of using bag-of-words as in the previous work, it assumes a block of consecutive words, e.g. words in paragraphs and sentences, share the same location and topic assignment.  ... 
doi:10.1007/s11042-010-0623-y fatcat:esd7subpbjhntpes6quvngtwti

Exploiting multi-level parallelism for low-latency activity recognition in streaming video

Ming-yu Chen, Lily Mummert, Padmanabhan Pillai, Alexander Hauptmann, Rahul Sukthankar
2010 Proceedings of the first annual ACM SIGMM conference on Multimedia systems - MMSys '10  
We demonstrate the utility of our system on an activity recognition application that employs a robust new descriptor called MoSIFT, which explicitly augments appearance features with motion information  ...  We describe the implementation of the activity recognition application on Sprout, and show that it can accurately recognize actions at full frame rate (25 fps) and low latency on a challenging airport  ...  Prior work has shown that this kernel is well suited for bag-of-words representations [45] .  ... 
doi:10.1145/1730836.1730838 dblp:conf/mmsys/ChenMPHS10 fatcat:do5bppidmfbbneiwjvh3t2pnei

Natural Language Processing for Smart Healthcare [article]

Binggui Zhou, Guanghua Yang, Zheng Shi, Shaodan Ma
2022 arXiv   pre-print
We further discuss the limitations of current works and identify the directions for future works.  ...  In this work, we review existing studies that concern NLP for smart healthcare from the perspectives of technique and application.  ...  NLP techniques, especially information extraction, are also able to identify the relations between chemical structures and biological activity [195] and further help researchers search for potentially  ... 
arXiv:2110.15803v2 fatcat:3o6tx5wqezdb5mgyfub2jtuiqu
« Previous Showing results 1 — 15 out of 450 results