Filters








7 Hits in 6.3 sec

Video copy detection using multiple visual cues and MPEG-7 descriptors

Onur Küçüktunç, Muhammet Baştan, Uğur Güdükbay, Özgür Ulusoy
2010 Journal of Visual Communication and Image Representation  
We propose a video copy detection framework that detects copy segments by fusing the results of three different techniques: facial shot matching, activity subsequence matching, and non-facial shot matching  ...  The proposed framework is tested on the query and reference dataset of CBCD task of TRECVID 2008. Our results are compared with the results of top-8 most successful techniques submitted to this task.  ...  The Sound and Vision video used in this work is provided solely for research purposes through the TREC Video Information Retrieval Evaluation Project Collection.  ... 
doi:10.1016/j.jvcir.2010.07.001 fatcat:t47schbbsnd2zmnh34ym3ikefe

Balancing the power of multimedia information retrieval and usability in designing interactive tv

Hyowon Lee, Paul Ferguson, Cathal Gurrin, Alan F. Smeaton, Noel E. O'Connor, Heeseon Park
2008 Proceeding of the 1st international conference on Designing interactive user experiences for TV and video - uxtv '08  
A series of screen shots from the system we have actually developed and built illustrates how this is achieved.  ...  In this paper we describe a design strategy we developed as a result of our efforts in balancing the power of emerging multimedia information retrieval techniques and maintaining the simplicity of the  ...  TRECVid exercise has resulted in a variety of novel techniques and ways to enhance the accuracy of feature detections.  ... 
doi:10.1145/1453805.1453827 dblp:conf/uxtv/LeeFGSOP08 fatcat:lro6hwkslnfv5hm3ddv6zmwaka

Semantics and statistics for automated image annotation

Ainhoa Llorente Coto
2010
to achieve statistically significant results over the baseline.  ...  semantics of the words used in the annotation process, is able to improve the performance of probabilistic annotation systems.  ...  Alternatively, return the ID of the sought video and elapsed time to find it. Content-based Copy Detection This task was presented for the first time as a pilot task in the 2008 edition of TRECVID.  ... 
doi:10.21954/ou.ro.0000643f fatcat:xtz4bm6wqjgs5m4yvffj6th62m

Scalable Machine Learning for Visual Data

Xinnan Yu
2017
In the thesis, we propose innovative approaches to scale up machine learning to address challenges arising from both the scale of the data and the limitation of the supervision.  ...  Learning with high-dimensionality: The "large-scale" of visual data comes not only from the number of samples but also from the dimensionality of the features.  ...  The first three results are copied from [190] , on optimal sparsity (ϑ = 400). The first three results are copied from [190] . Encoding error is defined in (13.2) .  ... 
doi:10.7916/d8f47ndb fatcat:xde635kzfrdvdhvakf432yod54

Semantic Labeling for Image Classification

Dejan Depalov
2007 unpublished
The features of 10.  ...  Semantic Labeling for Image Classification Depalov Dejan The rapid growth of digital imaging technology and the accumulation of large collections of digital images has created the need for efficient and  ...  Manual indexing times for video are likely to be even longer. Both newspapers and stock shot agencies maintain archives of still photographs to illustrate articles or advertising copies.  ... 
doi:10.21985/n2z98b fatcat:3xr36dhkkrcp5hqigxmz3xzova

Expressing Needs of Digital Audio-Visual Applications in Different Communities of Practice for Long-Term Preservation [chapter]

Naresh Kumar, Vittore Casarosa
Advances in Library and Information Science  
To express the audio-visual needs formally it has mapped a knowledge schema.  ...  Lack of awareness about the preservation tools and applications is a big issue today.  ...  Ingest receives information from the producer, validates the received information by checking that it is uncorrupted and complete, We need to provide proofs and get approval for our investment We need  ... 
doi:10.4018/978-1-5225-1653-8.ch004 fatcat:6foblqnd2nahlnd2pi6xtqkkka

Exploiting Social Networks for Recommendation in Online Image Sharing Systems

Adam Rae
2012
I analyse such data by modelling the connections between users as multigraphs and exploiting the resultant topologies to produce features that can be used to train recommender systems based on machine  ...  systems that incorporate this information.  ...  Hu, Adam Rae, Jianhan Zhu, Dawei Song and Stefan Rüger As a result of our participation in the Visual Concept Detection Task at ImageCLEF 2008 in which I contributed to the execution of the experiments  ... 
doi:10.21954/ou.ro.00007e30 fatcat:36i6yfiyebaild242cyajki2hy