14 Hits in 4.5 sec

Kodak's consumer video benchmark data set

Alexander Loui, Jiebo Luo, Shih-Fu Chang, Dan Ellis, Wei Jiang, Lyndon Kennedy, Keansub Lee, Akira Yanagawa
2007 Proceedings of the international workshop on Workshop on multimedia information retrieval - MIR '07  
In this work we developed Kodak's consumer video benchmark data set, which includes (1) a significant number of videos from actual users, (2) a rich lexicon that accommodates consumers' needs, and (3)  ...  To the best of our knowledge, this is the first systematic work in the consumer domain aimed at the definition of a large lexicon, construction of a large benchmark data set, and annotation of videos in  ...  VIDEO DATA SETS AND KEYFRAMES Kodak's consumer video benchmark data set includes two video subsets from two different sources.  ... 
doi:10.1145/1290082.1290117 dblp:conf/mir/LouiLCEJKLY07 fatcat:r7ft2vjpovgtnpstet5osdgm4m

Laplacian adaptive context-based SVM for video concept detection

Wei Jiang, Alexander Loui
2011 Proceedings of the 3rd ACM SIGMM international workshop on Social media - WSM '11  
; the domain difference between newly acquired data and the original labeled training data is not negligible; and only very limited, or even no, partial annotations are available over newly acquired data  ...  the classifiers and concept relations according to the target data.  ...  These videos are annotated to 20 consumer concepts, among which 5 concepts are the same with the concepts annotated over Kodak's benchmark data.  ... 
doi:10.1145/2072609.2072615 fatcat:p4cwv6wnxfdz5ir3xgzvpnnsxi

Effective semantic classification of consumer events for automatic content management

Wei Jiang, Alexander C. Loui
2009 Proceedings of the first SIGMM workshop on Social media - WSM '09  
Such consumer events have the following characteristics: an event can contain both photos and videos; there usually exist noisy/erroneous images resulting from imperfect albuming; and event data taken  ...  An event is defined as a set of photos and/or videos that are taken within a common period of time, and have similar visual appearance.  ...  Specifically, a set of 21 SVM concept detection models [1] that are learn based on Kodak's consumer benchmark video set (5166 keyframes from 1358 consumer videos) [14] are applied to the consumer event  ... 
doi:10.1145/1631144.1631153 dblp:conf/mm/0001L09 fatcat:m62pp7ndhvcclivxqlqw2jik5u

Consumer video retargeting

Liang Shi, Jinqiao Wang, Lingyu Duan, Hanqing Lu
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
First, we parse consumer videos from low-level features to highlevel visual concepts, combining visual attention into a more accurate importance description.  ...  Extensive evaluations were done on two popular video genres, sports and advertisements.  ...  [18] come up with a systematic audio-visual lexicon for the Kodak's benchmark video data set, which involves concepts in several predefined categories including activity, occasion, people, object, scene  ... 
doi:10.1145/1631272.1631315 dblp:conf/mm/ShiWDL09 fatcat:ktbcscbvabhtvevdwgbrayktk4

Semantic Model Vectors for Complex Video Event Recognition

Michele Merler, Bert Huang, Lexing Xie, Gang Hua, Apostol Natsev
2012 IEEE transactions on multimedia  
concepts.  ...  Our study reveals that the proposed semantic model vectors representation outperforms-and is complementary to-other low-level visual descriptors for video event modeling.  ...  ACKNOWLEDGMENT The authors would like to thank the Associate Editor and the Reviewers for their insightful comments and suggestions, which contributed to improve and make this work complete.  ... 
doi:10.1109/tmm.2011.2168948 fatcat:ml6wb6yefjh3nlv46sibr6ccjm

Race and Computer Vision [chapter]

Alexander Monea
2019 The Democratization of Artificial Intelligence  
, 15.4M bounding boxes for 600 object classes, and 375k visual relationship annotations involving 57 classes" (Kuznetsova et a. 2018) .  ...  Consumer Reports (2010) similarly argued that this was merely a lighting issue and claimed to have 'debunked' the idea that Kinect is 'racist'.  ... 
doi:10.14361/9783839447192-012 fatcat:pcqu2weoargkjm4wg3k3wwx5eu

Erkennung visueller Konzepte in Bildern und Videos

Markus Mühling
Current approaches in the field of image and video retrieval focus on semantic concepts serving as an intermediate description to bridge the "semantic gap" between the data representation and the human  ...  A multi-modal video concept detection system is presented that relies on Bag-of-Words representations for visual and in particular for audio features.  ...  Experimental results are presented for Kodak's consumer video benchmark and Corel's stock photo dataset.  ... 
doi:10.17192/z2014.0483 fatcat:ol6cciz6gjczbltidl2pl26px4

A Historical Survey of Research Regarding Constructed-Response Formats [chapter]

Isaac I. Bejar
2017 Methodology of Educational Measurement and Assessment  
The second hurdle was broadening the conception of validity to encompass more than predictive considerations, a process that began with the introduction of construct validity by Cronbach and Meehl (1955  ...  This chapter chronicles ETS research and development contributions related to the use of constructed-response item formats. 1 The use of constructed responses in testing dates back to imperial China, where  ...  that much faster. 10 After she classified a few of the annotations, she formulated a coding scheme that could be used to systematically annotate the rest of essays.  ... 
doi:10.1007/978-3-319-58689-2_18 fatcat:zrqsycaplvfw3n6vilodtklf2y

IRRODL Volume 13, Number 4

Various Authors
2012 International Review of Research in Open and Distance Learning  
Currently the institutional LMS remains the "workhorse" of formal education delivery and support, but increasingly teachers and students are exploring public networks like Facebook and LinkedIn and private  ...  Editorial -Volume 13, Issue Number 4 IRRODL continues to grow and succeed, and we wish to thank those whose time, energy, and expertise have contributed to this success through reviewing one or more articles  ...  I also thank my friend and colleague, Dr. Wendy Nielsen, for her time and effort in editing. Acknowledgement The authors appreciatively acknowledge the financial support provided by a grant from  ... 
doi:10.19173/irrodl.v13i4.1392 fatcat:xochcjv4jrdmfoijbpigbm5kca

Race and Computer Vision

Alexander Monea, Mediarep.Org, Mediarep.Org, Andreas Sudmann
, 15.4M bounding boxes for 600 object classes, and 375k visual relationship annotations involving 57 classes" (Kuznetsova et a. 2018) .  ...  Consumer Reports (2010) similarly argued that this was merely a lighting issue and claimed to have 'debunked' the idea that Kinect is 'racist'.  ... 
doi:10.25969/mediarep/13540 fatcat:mrio7da4tzh4potywd5f4kc5qy

Dagstuhl Reports, Volume 4, Issue 11, November 2014, Complete Issue [article]

We work on the definition of a new approach to integrate HT data.  ...  Consumer behaviour, such as the shift from landline to mobile phones or from linear video to streaming video-on-demand, creates opportunities for existing and new entrants. What Kind of Internet?  ...  Given the description of the initial state, the goal state, and the set of possible actions, a planner uses heuristic search to look for a sequence of actions that transforms the initial state into the  ... 
doi:10.4230/dagrep.4.11 fatcat:zzps76cx7rfldla5z5dikvsqbe

Framing digital image credibility: image manipulation problems, perceptions and solutions [article]

Sabrina Caldwell, University, The Australian National, University, The Australian National
The data collected, and their analyses, demonstrate that humans are poor at identifying that an image has been manipulated.  ...  I discuss photo manipulation and consider how it has changed along with photography. I describe the relevant literature on the subject of image authentication and the use of eye gaze tracking [...]  ...  The data sets and results are listed in ( Greatest accuracy feature set for each set O,A-I bolded and greatest accuracy for each feature set italicized.)  ... 
doi:10.25911/5d70f0183ca9d fatcat:2jhxnhkgrfednh3hnxfng5stau

How can Photographic Practice Assist our Quest for Intimacy with an Ideal Other?

Stephen John Hobson, University, My, Marian Drew, George Petelin
One of the better definitions, by Thomas Moore, states, 'The word intimacy means 'profoundly interior.' It comes from the superlative form of the Latin word inter, meaning 'within.'  ...  and other people.  ...  Research Profile Stephen's career spans a breadth of respected working situations in the arts and photography. Stephen was the first director of Artspace Mackay in  ... 
doi:10.25904/1912/927 fatcat:vmkutzl3nfcvnk3ouwohyokbcu

Radiant Exposure: The Art And Spectacle Of The X-Rayed Body In American Visual Culture

Lita Tirak
I will historicize a variety of works produced between 1895 and the present, which consist of actual X-ray photographs and artistic simulations of their visual effects.  ...  As Americans have become more transparent under modern surveillance, the X-rayed body in art and visual culture has become entangled with ideas about identity and power.  ...  The video presented two spectacles of revelation.  ... 
doi:10.21220/s2js33 fatcat:lypzdwxq3vbdtjpoluv35jalfa