A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Tracking Web Video Topics: Discovery, Visualization, and Monitoring
2011
IEEE transactions on circuits and systems for video technology (Print)
Despite the massive growth of web-shared videos in Internet, efficient organization and monitoring of videos remains a practical challenge. ...
Finally, giving the previously discovered topics, an incremental monitoring algorithm is proposed to track newly uploaded videos, while discovering new topics and giving recommendation to potentially hot ...
This paper addresses the discovery, monitoring and visualization of web video topics with various evolution trends. ...
doi:10.1109/tcsvt.2011.2148470
fatcat:uhcscretszg7zgl2pugtu57req
Tracking topic evolution via salient keyword matching with consideration of semantic broadness for Web video discovery
2017
Multimedia tools and applications
A method to track topic evolution via salient keyword matching with consideration of semantic broadness for Web video discovery is presented in this paper. ...
Consequently, it becomes feasible to track the evolution of topics over time for finding Web videos in which the users are interested. ...
Acknowledgements This work was partly supported by JSPS KAKENHI Grant Numbers JP16J02042 and JP17H01744. ...
doi:10.1007/s11042-017-5404-4
fatcat:bo2j6eprcfhcbdqkwfpl6s5lla
Trajectory-based visualization of web video topics
2010
Proceedings of the international conference on Multimedia - MM '10
The related issues include how to efficiently browse and track the evolution of topics and eventually locate the videos of interest. ...
While there have been research efforts in organizing largescale web videos into topics, efficient browsing of web video topics remains a challenging problem not yet addressed. ...
This paper presents a novel topic discovery and visualization system. ...
doi:10.1145/1873951.1874309
dblp:conf/mm/CaoNZZM10
fatcat:xxg2v3kwmjgpnnmqh4cgoozqvi
Becoming Social Media Savvy
2012
Topics in Clinical Nutrition
There are 3 basic types of learners: visual, auditory, and kinesthetic. 1 Visual learners learn by seeing and visualizing. ...
Tweets can be sent to students or clients about news articles, TV shows, books, videos, and Web sites. ...
doi:10.1097/tin.0b013e31824622a7
fatcat:32t3usvfyfbyrew26p2js527ru
Multimedia Resource Discovery
[chapter]
2011
Advanced Topics in Information Retrieval
Acknowledgements: The paradigms outlined in this chapter and their implementations ...
For example, words in the anchor text of a link to an image, a video clip or a music track, the file name of the object itself, meta-data stored within the files and other context information such as captions ...
In the multimedia context Section 4 argues that automated added services such as visual queries, relevance feedback and summaries can prove useful for resource discovery in multimedia digital libraries ...
doi:10.1007/978-3-642-20946-8_7
fatcat:fzndjjwksra6zhdaff6cq3voja
Towards Comprehensive Repositories of Opinions
2016
Proceedings of the 15th ACM Workshop on Hot Topics in Networks - HotNets '16
However, implicit inference of opinions is inherently uncertain and automated sharing of inferences raises significant privacy and security concerns. ...
Therefore, leveraging the trend that services are increasingly accessed from a clientside app rather than over the Web, we propose augmenting recommendation services to implicitly infer any user's opinions ...
All of us rely on recommendations from others for a variety of purposes such as knowledge discovery (e.g., web pages and books), entertainment (e.g., songs and movies), service provider selection (e.g. ...
doi:10.1145/3005745.3005765
dblp:conf/hotnets/ZhangNRM16
fatcat:dwoi36kcsvfevpyqgwtwmszuba
Topic Modeling with Wasserstein Autoencoders
[article]
2019
arXiv
pre-print
We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. ...
To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. ...
For the evaluation of topic quality, we monitor the NPMI and TU for all algorithms over a reasonable number of iterations (either when the topic quality begins to deteriorate or stops improving over a ...
arXiv:1907.12374v2
fatcat:gorwfy4lgnfejk54ifu3v2jsoa
On exploiting Data Visualization and IoT for Increasing Sustainability and Safety in a Smart Campus
2021
Journal on spesial topics in mobile networks and applications
AbstractIn a world that is getting increasingly digital and interconnected, and where more and more physical objects are integrated into the information network (Internet of Things, IoT), Data Visualization ...
In this paper, we present the design and implementation of a testbed where IoT and Data Visualization have been exploited to increase the sustainability and safety of the Cesena (Smart) Campus. ...
Acknowledgements We would like to express our sincere thanks and appreciation to Gianluca Grossi who prototyped the web-based application, and to Lorenzo Monti, who implemented and deployed the IoT infrastructure ...
doi:10.1007/s11036-021-01742-4
fatcat:pc7cha4ltjhrlhgibfk7l6rh54
Topic Modeling with Wasserstein Autoencoders
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. ...
To measure the diversity of the produced topics, we propose a simple topic uniqueness metric. ...
For the evaluation of topic quality, we monitor the NPMI and TU for all algorithms over a reasonable number of iterations (either when the topic quality begins to deteriorate or stops improving over a ...
doi:10.18653/v1/p19-1640
dblp:conf/acl/NanDNX19
fatcat:hqanr3yzmfbdvj32jrc5vbr6mu
Social media analytics – Challenges in topic discovery, data collection, and data preparation
2018
International Journal of Information Management
The social media analytics process involves four distinct steps, data discovery, collection, preparation, and analysis. ...
While there is a great deal of literature on the challenges and difficulties involving specific data analysis methods, there hardly exists research on the stages of data discovery, collection, and preparation ...
Through literature search, we identified solutions from sophisticated software architectures to visual analytics. Topic discovery and event detection are already well-established research fields. ...
doi:10.1016/j.ijinfomgt.2017.12.002
fatcat:uw4utzgpinf2rmqx2clnes346y
Sequential Pattern Mining Model to Identify the Most Important or Difficult Learning Topics via Mobile Technologies
2018
International Journal of Interactive Mobile Technologies
Based on this method, it is designed a model for understanding and learning the most difficult topics of students topics. ...
The paper mainly describes the model for understanding and learning the most difficult topics through the sequential pattern mining method. ...
Storing this data and track the logs of the student will lead to counting and ranking the most stop/replay/backward sequences containing the keyword topics. ...
doi:10.3991/ijim.v12i4.9223
fatcat:abxu3gexsnettlffw7nuuo5vgq
Exponential growth of hadal science: perspectives and future directions identified using topic modelling
2022
ICES Journal of Marine Science
We applied a topic modelling approach and fit a Latent Dirichlet Allocation model for 12 topics to 520 abstracts from peer-reviewed papers, reviews, and conference proceedings available on the Web of Science's ...
The model outputs were analysed with ecological modelling approaches to identify the main lines of research, track trends over time, and identify strengths and gaps. ...
Acknowledgements We are grateful to Louise Mair (Newcastle University, UK) for sharing her topic modelling code and knowledge and Danielle Robinson (Newcastle University) for coding support. ...
doi:10.1093/icesjms/fsac074
fatcat:kjcblav2i5h2vouq2n3nyaseeu
Emerging Research Topic Detection Using Filtered-LDA
2021
AI
The final stage of the filter uses multiple topic visualization formats to improve human interpretability of the filtered topics, and it presents the most-representative document for each topic. ...
The model acts as a filter that identifies old topics from a timestamped set of documents, removes all documents that focus on old topics, and keeps documents that discuss new topics. ...
Given that DTM limits its topic discovery to the prespecified number of topics, it keeps tracking these topics until the end of the time series. ...
doi:10.3390/ai2040035
fatcat:o3q4iigsqnab3m7dab7seyzeoa
Text Mining for Information Systems Researchers: An Annotated Topic Modeling Tutorial
2016
Communications of the Association for Information Systems
., text, audio, image, video)-much of it expressed in rich and ambiguous natural language. ...
In particular, we showcase how to use probabilistic topic modeling via Latent Dirichlet allocation, an unsupervised text-mining technique, with a LASSO multinomial logistic regression to explain user satisfaction ...
We observed the same problem for topic 41 ("heart", "rate", and "monitor" "heart_rate_monitor"; "blood" and "pressure" "blood_pressure"). 4. ...
doi:10.17705/1cais.03907
fatcat:4rfeitnzbbbndh5qqjdrai4xka
HierarchicalTopics: Visually Exploring Large Text Collections Using Topic Hierarchies
2013
IEEE Transactions on Visualization and Computer Graphics
To facilitate the representation and navigation of a large number of topics, we propose a visual analytics system -HierarchicalTopic (HT). ...
The dataset being visualized is the CNN news corpus. Topics are organized into 5 categories and annotations are attached to describe each news category. ...
ACKNOWLEDGMENTS This work was supported in part by grants from the National Science Foundation under award number SBE-0915528 and the Army Research Office under contract number W911NF-13-1-0083. ...
doi:10.1109/tvcg.2013.162
pmid:24051766
fatcat:5vr2wywvnzblxb2imiddrzkxri
« Previous
Showing results 1 — 15 out of 16,208 results