Search For:

Displaying 1-17 out of 17 total
Permutation-Based Low-Complexity Alternate Coding in Multi-View H.264/AVC
Found in: Multimedia and Expo, IEEE International Conference on
By Daniel Socek, Dubravko Culibrk, Hari Kalva, Oge Marques, Borko Furht
Issue Date:July 2006
pp. 2141-2144
Low bitrates enabled by the H.264/AVC standard come at the cost of significant decoding complexity. The problem is exacerbated when multi-view video coding (MVC), presently being standardized by the MPEG committee, is considered. Increasing the number of r...
 
Adaptive Visual Information Retrieval by Changing Visual Vocabulary Sizes in Context of User Intentions
Found in: Multimedia on the Web, Workshop on
By Marian Kogler,Mathias Lux,Oge Marques
Issue Date:September 2011
pp. 40-42
The overwhelming availability of visual content on the Internet poses a serious problem: although there are huge resources to tap, users often cannot find the content they actually want. The information need of a user is based on the user's intention or th...
 
Which Video Do You Want to Watch Now? Development of a Prototypical Intention-based Interface for Video Retrieval
Found in: Multimedia on the Web, Workshop on
By Christoph Lagger,Mathias Lux,Oge Marques
Issue Date:September 2011
pp. 45-48
Searching and retrieving videos in a meaningful way on the web is still an open problem. The integration of a user's context into search is one of the most promising approaches to enhance current search interfaces and algorithms. We performed two user stud...
 
Stereo depth with a Unified Architecture GPU
Found in: Computer Vision and Pattern Recognition Workshop
By Joel Gibson, Oge Marques
Issue Date:June 2008
pp. 1-6
This paper describes how the calculation of depth from stereo images was accelerated using a GPU. The Compute Unified Device Architecture (CUDA) from NVIDIA was employed in novel ways to compute depth using BT cost matching and the Semi-Global Matching alg...
 
A Forward-Looking User Interface for CBIR and CFIR Systems
Found in: Multimedia, International Symposium on
By Liam M. Mayron, Oge Marques, Gustavo B. Borba, Humberto R. Gamba, Vladimir Nedovic
Issue Date:December 2006
pp. 779-780
This demonstration highlights the benefits that image retrieval systems can enjoy by use of a thoughtful interface. We present a live demonstration of PRISM, a new Web-based application that, through a simple set of natural actions, allows the user the abi...
   
Challenges and Opportunities in Video Coding for 3D TV
Found in: Multimedia and Expo, IEEE International Conference on
By Hari Kalva, Lakis Christodoulou, Liam Mayron, Oge Marques, Borko Furht
Issue Date:July 2006
pp. 1689-1692
This paper explores the challenges opportunities in developing and deploying 3D TV services. The 3D TV services can be seen as a general case of the multi-view video that has been receiving significant attention lately. The keys to a successful 3D TV exper...
 
On the Potential of Incorporating Knowledge of Human Visual Attention into Cbir Systems
Found in: Multimedia and Expo, IEEE International Conference on
By Oge Marques, Liam Mayron, Gustavo Borba, Humberto Gamba
Issue Date:July 2006
pp. 773-776
Content-based image retrieval (CBIR) systems have been actively investigated over the past decade. Several existing CBIR prototypes claim to be designed based on perceptual characteristics of the human visual system, but even those who do are far from reco...
 
A Multimedia Traffic Classification Scheme for Intrusion Detection Systems
Found in: Information Technology and Applications, International Conference on
By Oge Marques, Pierre Baillargeon
Issue Date:July 2005
pp. 496-501
<p>Intrusion Detection Systems (IDS) have become widely used tools for ensuring system and network security. Among many other challenges, contemporary IDS have to cope with increasingly higher bandwidths, which sometimes force them to let some data g...
 
Crowdsourced object segmentation with a game
Found in: Proceedings of the 2nd ACM international workshop on Crowdsourcing for multimedia (CrowdMM '13)
By Amaia Salvador, Axel Carlier, Oge Marques, Vincent Charvillat, Xavier Giro-i-Nieto
Issue Date:October 2013
pp. 15-20
We introduce a new algorithm for image segmentation based on crowdsourcing through a game : Ask'nSeek. The game provides information on the objects of an image, under the form of clicks that are either on the object, or on the back-ground. These logs are t...
     
How well do you know Tom Hanks?: using a game to learn about face recognition
Found in: CHI '13 Extended Abstracts on Human Factors in Computing Systems (CHI EA '13)
By Justyn Snyder, Mathias Lux, Oge Marques
Issue Date:April 2013
pp. 337-342
Human face recognition abilities vastly outperform computer-vision algorithms working on comparable tasks, especially in the case of poor lighting, bad image quality, or partially hidden faces. In this paper, we describe a novel game with a purpose in whic...
     
Visual information retrieval using Java and LIRE
Found in: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '12)
By Mathias Lux, Oge Marques
Issue Date:August 2012
pp. 1193-1193
Visual information retrieval (VIR) is an active and vibrant research area, which attempts at providing means for organizing, indexing, annotating, and retrieving visual information (images and videos) form large, unstructured repositories. The goal of VIR ...
     
Event detection in video using motion analysis
Found in: Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams (ARTEMIS '10)
By Borko Furht, Hari Kalva, Oge Marques, Ricardo Castellanos
Issue Date:October 2010
pp. 57-62
Digital video is being used widely in a variety of applications such as entertainment, surveillance and security. Large amount of video in surveillance and security requires systems capable of processing video to automatically detect and recognize events t...
     
A classification scheme for user intentions in image search
Found in: Proceedings of the 28th of the international conference extended abstracts on Human factors in computing systems (CHI EA '10)
By Christoph Kofler, Mathias Lux, Oge Marques
Issue Date:April 2010
pp. 3913-3918
Searching for images on the web is still an open problem. While multiple approaches have been presented, there has been surprisingly little work on the actual goals and intentions of users. In this poster we present our classification scheme for user goals...
     
An exploratory study on joint analysis of visual classification in narrow domains and the discriminative power of tags
Found in: Proceeding of the 2nd ACM workshop on Multimedia semantics (MS '08)
By Mathias Lux, Oge Marques
Issue Date:October 2008
pp. 1-1
The popularity of social media sharing sites such as Flickr has driven a significant amount of research on the analysis of information contained in the tags used to annotate images. Many of such tags are not useful to describe the contents of an image and ...
     
Design and evaluation of a 3D video system based on H.264 view coding
Found in: Proceedings of the 2006 international workshop on Network and operating systems support for digital audio and video (NOSSDAV '06)
By Borko Furht, Hari Kalva, Lakis Christodoulou, Liam M. Mayron, Oge Marques
Issue Date:November 2006
pp. 1-1
Recent advances in video compression and 3D displays have necessitated a further understanding and development of 3D video coding algorithms. The emergence of low cost autostereoscopic displays is expected to drive the growth of 3DTV services. This paper d...
     
3D TV using MPEG-2 and H.264 view coding and autostereoscopic displays
Found in: Proceedings of the 14th annual ACM international conference on Multimedia (MULTIMEDIA '06)
By Borko Furht, Hari Kalva, Lakis Christodoulou, Liam M. Mayron, Oge Marques
Issue Date:October 2006
pp. 505-506
There is a renewed interest in the 3DTV research primarily due to the advances in low cost 3D display technologies. The two views required for 3DTV can be compressed using standard video compression techniques. MPEG-2 is widely used in digital TV applicati...
     
An unsupervised method for clustering images based on their salient regions of interest
Found in: Proceedings of the 14th annual ACM international conference on Multimedia (MULTIMEDIA '06)
By Gustavo B. Borba, Humberto R. Gamba, Liam M. Mayron, Oge Marques
Issue Date:October 2006
pp. 145-148
We have developed a biologically-motivated, unsupervised way of grouping together images whose salient regions of interest (ROIs) are perceptually similar regardless of the visual contents of other (less relevant) parts of the image. In the implemented mod...
     
 1