Filters








391 Hits in 5.1 sec

An Improved Approach for Estimating Social POI Boundaries With Textual Attributes on Social Media [article]

Cong Tran, Dung D. Vu, Won-Yong Shin
2020 arXiv   pre-print
It has been insufficiently explored how to perform density-based clustering by exploiting textual attributes on social media.  ...  We demonstrate the superiority of our algorithm over competing clustering methods including the original SoBEst.  ...  Spatio-textual similarity search. It is of importance to find spatially and textually closest objects to query objects.  ... 
arXiv:2012.09990v1 fatcat:67sl2pnff5g5bfekv36ctlzkma

An intelligent video categorization engine

G.Y. Hong, B. Fong, A.C.M. Fong
2005 Kybernetes  
Second, it allows unequal error protection for different video shots/segments during transmission to make better use of limited channel resources.  ...  Essentially, the SOM algorithm is a stochastic version of K-means clustering method (Balakrishnan, 1994) .  ...  experiments to produce a total of clusters close to 64. b is set to 1 for uncommitted F 2 node and 0.5 for committed F 2 node, since we use fast-commit slow-recode as our updating scheme K 34,6 Cluster-to-category  ... 
doi:10.1108/03684920510595490 fatcat:2jbxbctsrje35ididicbs3j5wy

A Multimodal Scheme for Program Segmentation and Representation in Broadcast Video Streams

Jinqiao Wang, Lingyu Duan, Qingshan Liu, Hanqing Lu, J.S. Jin
2008 IEEE transactions on multimedia  
For audio cues, a multiscale Kullback-Leibler (K-L) distance is proposed to locate audio scene changes (ASC), and accordingly ASC is aligned with video scene changes to represent candidate boundaries of  ...  The scheme aims to recover the temporal and structural characteristics of TV programs with visual, auditory, and textual information.  ...  [6] used spatio-temporal image slices of fixed length for clustering. Moreover, some advanced statistical models have been proposed to detect scenes. Zhang et al.  ... 
doi:10.1109/tmm.2008.917362 fatcat:olc7ct3eyrftviv4a6ervidxx4

Table of Contents

2021 2021 IEEE 37th International Conference on Data Engineering (ICDE)  
Johann Gamper (Free University of Bozen-Bolzano, Italy), and Minos Garofalakis (ATHENA Research Center & Technical University of Crete, Greece) LATEST: Learning-Assisted Selectivity Estimation Over Spatio-Textual  ...  , USA), Chuan Lei (IBM Research -Almaden, USA), Abdul Quamar (IBM Research -Almaden, USA), Vasilis Efthymiou (IBM Research -Almaden, USA), and Fatma Özcan (IBM Research -Almaden, USA) Fast Core-Based Top-k  ... 
doi:10.1109/icde51399.2021.00004 fatcat:six4wcvfsjd4bdphh5qfatdwru

Relevance ranking in georeferenced video search

Sakire Arslan Ay, Roger Zimmermann, Seon Ho Kim
2010 Multimedia Systems  
Such georeferenced media streams are useful in many applications and, very importantly, they can effectively be searched.  ...  In this study we investigate and present three ranking algorithms that use spatial and temporal video properties to effectively rank search results.  ...  It is also worth mentioning that multimedia applications often tolerate some minor errors.  ... 
doi:10.1007/s00530-009-0177-x fatcat:c6lw56lb3zaylkmndkrxl3ozry

Analysis of vector space model and spatiotemporal segmentation for video indexing and retrieval

Eric Galmar, Benoit Huet
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
In this paper, we propose to enhance these systems with the use of spatiotemporal regions.  ...  We analyse the properties of the VSM and show that shot description can be improved by considering spatio temporal representations.  ...  These terms are obtained by clustering region descriptors extracted over the whole database. K-means algorithm is used for clustering.  ... 
doi:10.1145/1282280.1282344 dblp:conf/civr/GalmarH07 fatcat:eon5iq3wwnb3neaslpgp3rw3be

YouTube Scale, Large Vocabulary Video Annotation [chapter]

Nicholas Morsillo, Gideon Mann, Christopher Pal
2010 Studies in Computational Intelligence  
While the idea of annotating static imagery with keywords is relatively well known, the idea of annotating videos with natural language keywords to enhance search is an important emerging problem with  ...  great potential to improve the quality of video search.  ...  A visual vocabulary is then built by K-means based clustering.  ... 
doi:10.1007/978-3-642-12900-1_14 fatcat:qqrwarq3b5gv7icnth6frlh754

Detecting Events in Online Social Networks: Definitions, Trends and Challenges [chapter]

Nikolaos Panagiotou, Ioannis Katakis, Dimitrios Gunopulos
2016 Lecture Notes in Computer Science  
Clustering can be performed on the textual features of users' messages (Topic Clustering) or on their spatio-temporal attributes (Spatio-Temporal clustering).  ...  Each cluster receives a score equal to the sum of its keywords' score. The top-k clusters according to their score are the candidate event Clusters.  ... 
doi:10.1007/978-3-319-41706-6_2 fatcat:4neqe4dxlvczndld3d2xkqtyxu

DeepTrust: A Reliable Financial Knowledge Retrieval Framework For Explaining Extreme Pricing Anomalies [article]

Pok Wah Chan
2022 arXiv   pre-print
queries with dynamic search conditions.  ...  The workflow starts with identifying anomalous asset price changes using machine learning models trained with historical pricing data, and retrieving correlated unstructured data from Twitter using enhanced  ...  Tekeuchi et al. proposed a spatio-temporal query expansion technique STT-PRF, by including spatial, temporal and textual information in each iteration of the PRF process [58] .  ... 
arXiv:2203.08144v1 fatcat:rusadj2rgrbplekl3bbpunbdwm

A Systematic Learning on Variety of Recommender Systems for Online Commodities

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
It develops dynamic recommendation method with respect to evolutionary clustering model. [28] also attempted to handle this situation that users' desires changes often by a time-aware spatio-textual RS  ...  It further evaluates the process using Movie Lens and collaborative filtering schemes. [31] Focused on movie recommender method named, k-means clustering based cuckoo search method to classify consumers  ... 
doi:10.35940/ijitee.h6969.0881019 fatcat:gapzmzcx2ngu7jjorwo7a56ffu

Program book

2010 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010)  
In this paper, we propose a series of join-based algorithms that combine the semantic pruning and the top-K processing to support top-K keyword search in XML databases.  ...  , skyline, k-dominance, top-k dominance, and k-frequency).  ...  when applied to social networks and searching for people, contacts or shared interests is very different from the search over documents studied in information retrieval.  ... 
doi:10.1109/icdew.2010.5452773 fatcat:oyq2tujbvjfpxjlyixux5q57vu

Extracting information from free text through unsupervised graph-based clustering: an application to patient incident records [article]

M. Tarik Altuncu, Eloise Sorin, Joshua D. Symons, Erik Mayer, Sophia N. Yaliraki, Francesca Toni, Mauricio Barahona
2019 arXiv   pre-print
Our unsupervised method extracts groups with high intrinsic textual consistency and compares well against categories hand-coded by healthcare personnel.  ...  We also show how to use our content-driven clusters to improve the supervised prediction of the degree of harm of the incident based on the text of the report.  ...  We performed a grid search to optimise the hyperparameters of our model (penalty = 10, tolerance for stopping criterion = 0.0001, linear kernel).  ... 
arXiv:1909.00183v1 fatcat:cncsptcjxjb43dd3i4vsthgwre

Moving Objects Analytics: Survey on Future Location & Trajectory Prediction Methods [article]

Harris Georgiou, Sophia Karagiorgou, Yannis Kontoulis, Nikos Pelekis, Petros Petrou, David Scarlatti, Yannis Theodoridis
2018 arXiv   pre-print
This source of information constitutes a rich input for data analytics processes, either offline (e.g. cluster analysis, hot motion discovery) or online (e.g. short-term forecasting of forthcoming positions  ...  (k-nn) variants that employ spatio-temporal index trees.  ...  queries that include predictive spatio-temporal range, aggregate (number of objects), and k-nn queries, as well as continuous queries.  ... 
arXiv:1807.04639v1 fatcat:lvje57kod5eldaplkl53wbwgti

29th International Conference on Data Engineering [book of abstracts]

2013 2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW)  
Given a set of spatio-textual objects, a query location and a set of keywords, the top k spatial keyword search retrieves the closest k objects each of which contains all keywords in the query.  ...  In addition, we show that the IL-Quadtree technique can also be applied to improve the performance of other spatial keyword queries such as the direction-aware top k spatial keyword search and the spatio-textual  ... 
doi:10.1109/icdew.2013.6547409 fatcat:wadzpuh3b5htli4mgb4jreoika

A Survey of Blocking and Filtering Techniques for Entity Resolution [article]

George Papadakis, Dimitrios Skoutas, Emmanouil Thanos, Themis Palpanas
2020 arXiv   pre-print
Finally, a transformation-based framework for top-k set similarity search is presented in [197] .  ...  This is then used to support both threshold-based and top-k string similarity search based on edit distance.  ... 
arXiv:1905.06167v4 fatcat:zoodv75tazg23cfnq4dwfgt6ge
« Previous Showing results 1 — 15 out of 391 results