Filters








5,449 Hits in 5.1 sec

Dynamic extraction topic descriptors and discriminators

Ana Maguitman, David Leake, Thomas Reichherzer, Filippo Menczer
2004 Proceedings of the Thirteenth ACM conference on Information and knowledge management - CIKM '04  
topic descriptors and discriminators from a knowledge model, to characterize information needs for retrieval and filtering of relevant material.  ...  The paper develops a framework for understanding this interaction, and proposes and evaluates techniques for addressing the query formation and topic identification questions by dynamically extracting  ...  Acknowledgments We gratefully acknowledge the contributions of our collaborators Alberto Cañas and the IHMC CmapTools team. This research is supported in part by NASA under award No NCC 2-1216.  ... 
doi:10.1145/1031171.1031260 dblp:conf/cikm/MaguitmanLRM04 fatcat:irufwhf6xbc2xit5w3rthwruru

Learning Better Context Characterizations: An Intelligent Information Retrieval Approach [article]

Carlos M. Lorenzetti, Ana G. Maguitman
2010 arXiv   pre-print
The method starts with a small number of terms selected from a simple description of the topic under analysis and uses this description as the initial search context.  ...  Using these terms, a set of queries are built and submitted to a search engine. New documents and terms are used to refine the learned vocabulary.  ...  Our algorithm is based on the dynamic extraction of topic descriptors and discriminators, as first introduced in [14] .  ... 
arXiv:1004.3478v2 fatcat:tgtfqivuyban5ow5dfmnn3hzjm

Suggesting novel but related topics

Ana Maguitman, David Leake, Thomas Reichherzer
2005 Proceedings of the 10th international conference on Intelligent user interfaces - IUI '05  
The algorithm iteratively performs a cycle of topic formation, Web search for connected material, and context-based filtering.  ...  context.  ...  We gratefully acknowledge the contributions of our collaborators Alberto Cañas and the IHMC CmapTools team. This research is supported in part by NASA under award No NCC 2-1216.  ... 
doi:10.1145/1040830.1040876 dblp:conf/iui/MaguitmanLR05 fatcat:nuhkwqwu35faxf4iwzb5t6aihy

Discriminative Video Pattern Search for Efficient Action Detection

Junsong Yuan, Zicheng Liu, Ying Wu
2011 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Similar to the sliding window-based object detection, action detection finds the reoccurrences of such spatio-temporal patterns through pattern matching, by handling cluttered and dynamic backgrounds and  ...  It is also insensitive to dynamic and cluttered backgrounds and even to partial occlusions.  ...  In [29] , a motion-based representation called motion context is proposed for action recognition.  ... 
doi:10.1109/tpami.2011.38 pmid:21339530 fatcat:fl2mmgdg4vawlawcvx5zwk4rnm

Hypermedia exploration with interactive dynamic maps

Mountaz Zizi, Michel Beaudouin-Lafon
1995 International Journal of Human-Computer Studies  
The major contributions of this work include 1) automatic techniques for building maps directly from a web of documents, including extraction of semantic content and use of a spatial metaphor for generating  ...  Interactive Dynamic Maps (IDMs) help users interactively explore webs of hypermedia documents. IDMs provide automatically-generated abstract graphical views at different levels of granularity.  ...  We also thank O2 Technology for their support and Wendy Mackay for her help with earlier versions of this article.  ... 
doi:10.1006/ijhc.1995.1053 fatcat:j7aj5silfbez7jw6iylxa43sjm

Visual diversification of image search results

Reinier H. van Leuken, Lluis Garcia, Ximena Olivares, Roelof van Zwol
2009 Proceedings of the 18th international conference on World wide web - WWW '09  
Due to the reliance on the textual information associated with an image, image search engines on the Web lack the discriminative power to deliver visually diverse search results.  ...  The methods deploy lightweight clustering techniques in combination with a dynamic weighting function of the visual features, to best capture the discriminative aspects of the resulting set of images that  ...  ACKNOWLEDGMENTS The authors express their gratitude toward all the assessors that helped in the establishment of the ground truth.  ... 
doi:10.1145/1526709.1526756 dblp:conf/www/LeukenPOZ09 fatcat:h2b62otiunenvcpkfiypv2dmne

Human Action Segmentation and Recognition Using Discriminative Semi-Markov Models

Qinfeng Shi, Li Cheng, Li Wang, Alex Smola
2010 International Journal of Computer Vision  
In this paper, we propose a discriminative semi-Markov model approach, and define a set of features over boundary frames, segments, as well as neighboring segments.  ...  Moreover, the model is discriminatively learned from large margin principle, and is formulated as an optimization problem with exponentially many constraints.  ...  (2001) and Schuldt et al. (2004) for sharing the CMU MoBo and KTH datasets, respectively.  ... 
doi:10.1007/s11263-010-0384-0 fatcat:lv2ulbap4zbjnmtfkt42u3hhn4

Content-based image retrieval

Ritendra Datta, Jia Li, James Z. Wang
2005 Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval - MIR '05  
We conclude with a study on the trends in volume and impact of publications in the field with respect to venues/journals and sub-topics.  ...  The last decade has witnessed great interest in research on content-based image retrieval.  ...  These include histogram-based descriptors, dominant color descriptors, spatial color descriptors and texture descriptors suited for browsing and retrieval.  ... 
doi:10.1145/1101826.1101866 dblp:conf/mir/DattaLW05 fatcat:puk37fqtbng77dwtjd7sjyz2xi

Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook [article]

Sajid Javed, Martin Danelljan, Fahad Shahbaz Khan, Muhammad Haris Khan, Michael Felsberg, Jiri Matas
2021 arXiv   pre-print
Discriminative Correlation Filters (DCFs) and deep Siamese Networks (SNs) have emerged as dominating tracking paradigms, which have led to significant progress.  ...  We finish the survey by presenting recommendations and suggestions for distinguished open challenges based on our analysis.  ...  descriptor learning [49].  ... 
arXiv:2112.02838v1 fatcat:nsre4b5uafeopjb37go6c3obwu

Learning the semantics of multimedia queries and concepts from a small number of examples

Apostol (Paul) Natsev, Milind R. Naphade, Jelena TešiĆ
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
We evaluate this approach for rare concept and query topic modeling using the NIST TRECVID video corpus.  ...  In particular, we observe an improvement of 6% for rare concept detection and 17% for the search task.  ...  This material is based upon work funded in whole by the U. S. Government.  ... 
doi:10.1145/1101149.1101288 dblp:conf/mm/NatsevNT05 fatcat:2fkovjvzd5azjh764mv4fzlfpe

Hierarchical spatio-temporal context modeling for action recognition

Ju Sun, Xiao Wu, Shuicheng Yan, Loong-Fah Cheong, Tat-Seng Chua, Jintao Li
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
SIFT average descriptor), 2) intra-trajectory context (trajectory transition descriptor), and 3) inter-trajectory context (trajectory proximity descriptor).  ...  To obtain efficient and compact representations for the latter two levels, we encode the spatiotemporal context information into the transition matrix of a Markov process, and then extract its stationary  ...  Acknowledgment This research is supported in part by IDMPO Grant of R-705-000-018-279 Singapore, and in part as CSIDM Project No.  ... 
doi:10.1109/cvpr.2009.5206721 dblp:conf/cvpr/SunWYCCL09 fatcat:v6ww72arfjfdbokklaxe5qu5vq

Hierarchical spatio-temporal context modeling for action recognition

Ju Sun, Xiao Wu, Shuicheng Yan, Loong-Fah Cheong, Tat-Seng Chua, Jintao Li
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
SIFT average descriptor), 2) intra-trajectory context (trajectory transition descriptor), and 3) inter-trajectory context (trajectory proximity descriptor).  ...  To obtain efficient and compact representations for the latter two levels, we encode the spatiotemporal context information into the transition matrix of a Markov process, and then extract its stationary  ...  Acknowledgment This research is supported in part by IDMPO Grant of R-705-000-018-279 Singapore, and in part as CSIDM Project No.  ... 
doi:10.1109/cvprw.2009.5206721 fatcat:d2qg4be4czfwdbznw7x7oruwum

Retrieval of spatial–temporal motion topics from 3D skeleton data

Qianhui Men, Howard Leung
2019 The Visual Computer  
We propose a context-based motion document formation method to reflect geometric variations by calculating covariance descriptors among skeletal joint locations and joint relative distances, and temporal  ...  The similarity matching is based on motion-topic distributions from LDA with semantic meanings.  ...  Acknowledgements The work described in this paper was fully supported by Grants from City University of Hong Kong (Project No. 7004681 and 7004916).  ... 
doi:10.1007/s00371-019-01690-x fatcat:uavqoixxdjfjzcktafv65glmma

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  
This paper presents a hybrid framework for automatic consumption of sensor data and associating object usage to routine activities using Latent Dirichlet Allocation (LDA) topic modelling.  ...  Current knowledge-driven and ontology-based techniques model object concepts from assumptions and everyday common knowledge of object use for routine activities.  ...  Similar to other knowledge bases, it functions as a repository where information can be collected, organized, shared and searched.  ... 
doi:10.3390/informatics5010006 fatcat:dp5mbujy4ja2vm3pvgea3sdhg4

Neural network modeling of a dolphin's sonar discrimination capabilities

Whitlow W. L. Au, Lars N. Andersen, A. René Rasmussen, Herbert L. Roitblat, Paul E. Nachtigall
1995 Journal of the Acoustical Society of America  
The sound field scattered by a smooth thin elastic shell immersed in fluid arises largely from specular reflection and acoustic-membrane coupling, unless both source and observer are located near or on  ...  The algorithm of search is based on the traditional way to solve the problem without a computer.  ...  Search algorithms based on the optimal generators may find the deepest point in the valley several times faster than algorithms based on other generators.  ... 
doi:10.1121/1.413700 pmid:7608403 fatcat:m3nunzs4wfflhfl27n4shdn2n4
« Previous Showing results 1 — 15 out of 5,449 results