75 Hits in 6.1 sec

Semi-Automatic Tagging of Photo Albums via Exemplar Selection and Tag Inference

Dong Liu, Meng Wang, Xian-Sheng Hua, Hong-Jiang Zhang
2011 IEEE transactions on multimedia  
For a given album, it first selects a set of representative exemplars for manual tagging via a temporally consistent affinity propagation algorithm, and the tags of the rest of the photos are automatically  ...  In this paper, we propose a semi-automatic tagging scheme that aims to facilitate users in photo album tagging.  ...  Semi-Automatic Tagging of Photo Albums via Exemplar Selection and Tag Inference Dong Liu, Meng Wang, Member, IEEE, Xian-Sheng Hua, Member, IEEE, and Hong-Jiang Zhang, Fellow, IEEE Abstract-As one of the  ... 
doi:10.1109/tmm.2010.2087744 fatcat:r7j27dyijfavziquxtr53cw4py

Assistive tagging

Meng Wang, Bingbing Ni, Xian-Sheng Hua, Tat-Seng Chua
2012 ACM Computing Surveys  
We first introduce the status of automatic tagging and manual tagging and then state why assistive tagging can be a good solution.  ...  Along with the explosive growth of multimedia data, automatic multimedia tagging has attracted great interest of various research communities, such as computer vision, multimedia, and information retrieval  ...  Users manually tag the selected photos, and the tags of the rest of the photos are automatically inferred.  ... 
doi:10.1145/2333112.2333120 fatcat:cvlxcazimvdjxigdvchjinnewe

Automatic Face Understanding: Recognizing Families in Photos [article]

Joseph P Robinson
2021 arXiv   pre-print
Now, video dynamics, audio, and text captions can be used in the decision making of kinship recognition systems. We expect FIW will significantly impact research and reality.  ...  The locations of landmarks are determined from generated heatmaps from which predicted landmark locations get penalized without accounting for the spread: a high scatter corresponds to low confidence and  ...  Semi-Automatic Image Tagging & Data Exploration Automatic image tagging was recently done by first labeling a small amount of the data, and then using it as side information to help guide the clustering  ... 
arXiv:2102.08941v1 fatcat:eqje3jh23nb6do7crz7rw6342a

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods [article]

Aditya Mogadala and Marimuthu Kalimuthu and Dietrich Klakow
2020 arXiv   pre-print
This has created significant interest in the integration of vision and language. The tasks are designed such that they perfectly embrace the ideas of deep learning.  ...  and build new applications.  ...  We extend our special thanks to Matthew Kuhn and Stephanie Lund for painstakingly proofing the whole manuscript.  ... 
arXiv:1907.09358v2 fatcat:4fyf6kscy5dfbewll3zs7yzsuq

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods

Aditya Mogadala, Marimuthu Kalimuthu, Dietrich Klakow
2021 The Journal of Artificial Intelligence Research  
This has created significant interest in the integration of vision and language.  ...  This success can be partly attributed to the advancements made in the sub-fields of AI such as machine learning, computer vision, and natural language processing.  ...  We extend our special thanks to Matthew Kuhn and Stephanie Lund for painstakingly proofing the whole manuscript.  ... 
doi:10.1613/jair.1.11688 fatcat:kvfdrg3bwrh35fns4z67adqp6i

A novel approach for Multi-Tier security for XML based documents

Bimlendu Prasad Verma
2012 IOSR Journal of Computer Engineering  
However the data need to be secured in respect of confidentiality, integrity, authenticity and non-reproduction.  ...  Here we present an approach to achieve the Multi-Tier security that deals with providing integrity, non repudiation and different confidentiality levels for different users of the document.  ...  Ojha of Faculty of Engineering and Technology, Mewar University for encouraging and guiding us to write this paper. Acknowledgements  ... 
doi:10.9790/0661-0540104 fatcat:dlvsp3hzqjarpimzagisq7qrce

The YLI-MED Corpus: Characteristics, Procedures, and Plans [article]

Julia Bernd, Damian Borth, Benjamin Elizalde, Gerald Friedland, Heather Gallagher, Luke Gottlieb, Adam Janin, Sara Karabashlieva, Jocelyn Takahashi, Jennifer Won
2015 arXiv   pre-print
The YLI Multimedia Event Detection corpus is a public-domain index of videos with annotations and computed features, specialized for research in multimedia event detection (MED), i.e., automatically identifying  ...  The annotations also include degree of annotator agreement and average annotator confidence scores for the event categorization of each video.  ...  Any opinions, findings, and conclusions or recommendations are those of the authors and do not necessarily reflect the views of Cisco, LLNL, nor the NSF.  ... 
arXiv:1503.04250v1 fatcat:cterpksxandh3pmajoz7fa277m

Microlearning in health professions education

Jennie C. De Gagne, Amanda Woodward, Hyeyoung K. Park, Huilin Sun, Sandra S. Yamane
2018 The JBI Database of Systematic Reviews and Implementation Reports  
Theo Hug, Associate Professor and member of the successful faculty and institute of education at the LFUI and at the same time Head of the ARC Research Studio eLearning Environments.  ...  They are enhancing the Austrian innovative and competitive ability in the area of information and communication technology.  ...  We have also presented some particular requirements and in particular the definition of micro-content.  ... 
doi:10.11124/jbisrir-2017-003884 pmid:30489350 fatcat:hgqjcgrvlnhr5dnag37f5a7ffy

Using Lexical and Encyclopedic Knowledge [chapter]

Yannick Versley, Massimo Poesio, Simone Ponzetto
2016 Anaphora Resolution  
, is more complex and a larger variety of solutions can be found in practice.  ...  In contrast to hard criteria such as binding and agreement constraints, however, the question of semantic constraints and preferences and its operationalization in a system that performs anaphora resolution  ...  However, this situation is changing with encyclopedic knowledge that is either extracted automatically or semi-automatically from Wikipedia, or (in the case of FreeBase) curated manually.  ... 
doi:10.1007/978-3-662-47909-4_14 dblp:series/tanlp/VersleyPP16 fatcat:xjwq7ae47zhwribgolaj42xlae

A Comprehensive Performance Evaluation of Deformable Face Tracking "In-the-Wild"

Grigorios G. Chrysos, Epameinondas Antonakos, Patrick Snape, Akshay Asthana, Stefanos Zafeiriou
2017 International Journal of Computer Vision  
Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under  ...  In this paper, we perform the first, to the best of our knowledge, thorough evaluation of state-of-the-art deformable face tracking pipelines using the recently introduced 300 VW benchmark.  ...  The work of PS and EA was funded by the European Community Horizon 2020 [H2020/2014-2020] under Grant Agreement No. 688520 (TeSLA). The work of S.  ... 
doi:10.1007/s11263-017-0999-5 pmid:31983805 pmcid:PMC6953975 fatcat:edknqfajlfdvvmceaupqqosp6y

Facial expression recognition in the wild : from individual to group [article]

Abhinav Dhall, University, The Australian National, University, The Australian National
The database is constructed and labelled using a semi-automatic process based on closed caption subtitle based keyword search.  ...  conditions; 2) devising Head Pose Normalisation (HPN) methods which are independent of facial parts location; 3) creating automatic methods for the analysis of mood of group of people.  ...  The details of the mood inferring model, social features are discussed in detail. The group mood analysis is applied to two applications of 'event summarisation' and 'candid photo shot selection'.  ... 
doi:10.25911/5d4ea922db07c fatcat:g2yn7xzq5baxpfsuwdna574l2e

Surveillance Face Recognition Challenge [article]

Zhiyi Cheng and Xiatian Zhu and Shaogang Gong
2018 arXiv   pre-print
Significant progress in FR has been made due to the recent introduction of the larger scale FR challenges, particularly with constrained social media web images, e.g. high-resolution photos of celebrity  ...  faces taken by professional photo-journalists.  ...  Video Analytics Solutions for Public Safety (98111-571149), Vision Semantics Ltd, and SeeQuestor Ltd.  ... 
arXiv:1804.09691v6 fatcat:c2xlmiv2yvbwngrg43enlnfbqu

Natural-Born Cyborgs: Minds, Technologies, and the Future of Human Intelligence (review)

Mark Erickson
2004 Canadian journal of sociology  
, and semi-intelligent daily objects.  ...  The long-term memory of such associations is the system's main tool for selecting and filtering information from the databases to which it is linked, but it is a tool that is automatically and continuously  ... 
doi:10.1353/cjs.2004.0038 fatcat:w4y2rzpakbcgbivjhpsbizvmzu

Physicians' Progress Notes [chapter]

Jørgen Bansler, Erling Havn, Troels Mønsted, Kjeld Schmidt, Jesper Hastrup Svendsen
2013 ECSCW 2013: Proceedings of the 13th European Conference on Computer Supported Cooperative Work, 21-25 September 2013, Paphos, Cyprus  
These additional contributions will be published in the Volume 2 Proceedings, together with the expanded selection of demonstrations, videos, and work in progress.  ...  ECSCW 2013 received 82 competitive paper and note submissions. After extensive review, 15 were selected to form the core of the traditional single-track technical programme for the conference.  ...  Thanks to Tom Rodden for valuable comments on an earlier draft of this paper, and to Mike Fraser, Peter Tolmie, James Norris, and Holger Schnädelbach for useful feedback on this work.  ... 
doi:10.1007/978-1-4471-5346-7_7 dblp:conf/ecscw/BanslerHMSS13 fatcat:nnouibkakjalzkuugdozzgc5ii

Open Knowledge: Promises and Challenges [chapter]

Rufus Pollock, Jo Walsh
2012 The Digital Public Domain: Foundations for an Open Culture  
Figure 4 shows how the CC-licensed photo at photos/laughingsquid/2034629532 would be marked up using CC REL, including the machine tag upcoming:event that associates the photo with  ...  An extractor which looks for metadata specified in external files via <link> tags, however, would still retrieve them and see if they have been updated.  ...  CC recommends exposing a mechanism to extract the CC REL abstract model from the XML, so that CC tools need not know about every possible XML schema ahead of time.  ... 
doi:10.11647/obp.0019.07 fatcat:r3yre7bnmndbvbhggtzvdhdyaq
« Previous Showing results 1 — 15 out of 75 results