@comment{{This file has been generated by bib2bib 1.96}}
@comment{{Command line: ./bib2bib -ob msc.bib -c '$type = "MASTERSTHESIS"' -s year -r mediamill.bib}}
  author = {{Koen E. A. van de} Sande},
  title = {Coloring Concept Detection in Video using Interest Regions},
  month = {March},
  year = 2007,
  school = {University of Amsterdam},
  pdf = {},
  abstract = {
  		 Video concept detection aims to detect high-level semantic information present in video.
		 State-of-the-art systems are based on visual features and use machine learning to build
		 concept detectors from annotated examples. The choice of features and machine learning
		 algorithms is of great influence on the accuracy of the concept detector. So far, intensitybased
		 SIFT features based on interest regions have been applied with great success
		 in image retrieval. Features based on interest regions, also known as local features,
		 consist of an interest region detector and a region descriptor. In contrast to using
		 intensity information only, we will extend both interest region detection and region
		 description with color information in this thesis. We hypothesize that automated concept
		 detection using interest region features benefits from the addition of color information.
		 Our experiments, using the Mediamill Challenge benchmark, show that the combination
		 of intensity features with color features improves significantly over intensity features
  author = {{Ork de} Rooij},
  title = {Browsing News Video using Semantic Threads},
  month = {December},
  year = 2005,
  school = {University of Amsterdam},
  pdf = {},
  abstract = {
  		 This paper describes a novel approach for finding threads in video material using basic 
  		 clustering techniques by combining knowledge from the content-based retrieval in video 
  		 material domain and the topic detection and tracking domain. For this the notion of the 
  		 semantic thread as an ordered list of video shots about the same semantic subject is 
  		 proposed. A method for generating semantic threads from a large collection of video 
  		 material is presented. Several standard algorithms for creating clusters are compared and 
  		 a method for including both clusters and time to create threads is discussed. With these 
  		 threads an interface for searching through a large dataset of video material is proposed 
  		 and implemented. This interface is then evaluated with the TRECVID interactive retrieval 
  		 task, where it ranked among the best interactive retrieval systems currently available. 
  		 The interface proved to be very usefull for finding video material where the topic cannot 
  		 be easily found by using traditional keyword search. 
  author = {Bouke Huurnink},
  title = {{AutoSeek}: Towards a Fully Automated Video Search System},
  month = {October},
  year = 2005,
  school = {University of Amsterdam},
  pdf = {},
  abstract = {
  		 The astounding rate at which digital video is becoming available has stimulated 
  		 research into video retrieval systems that incorporate visual, auditory, and 
  		 spatio-temporal analysis. In the beginning, these multimodal systems required 
  		 intensive user interaction, but during the past few years automatic search systems 
  		 that need no interaction at all have emerged, requiring only a string of natural 
  		 language text and a number of multimodal examples as input. We apply ourselves 
  		 to this task of automatic search, and investigate the feasibility of automatic 
  		 search without multimodal examples. The result is AutoSeek, an automatic 
  		 multimodal search system that requires only text as input.  In our search 
  		 strategy we first extract semantic concepts from text and match them to semantic 
  		 concept indices using a large lexical database. Queries are then created for the 
  		 semantic concept indices as well as for indices that incorporate ASR text. 
  		 Finally, the result sets from the different indices are fused with a combination 
  		 strategy that was created using a set of development search statements.  We 
  		 subject our system to an external assessment in the form of the TRECVID 2005 
  		 automatic search task, and find that our system performs competitively when 
  		 compared to systems that also use multimodal examples,  ranking in the top 
  		 three systems for 25\% of the search tasks and scoring the fourth highest in 
  		 overall mean average precision. We conclude that automatic search without using 
  		 multimodal examples is a realistic task, and predict that performance will 
  		 improve further as semantic concept detectors increase in quantity and quality.
  author = {Cees G. M. Snoek},
  title = {Camera Distance Classification: Indexing Video Shots based on Visual Features},
  month = {October},
  year = {2000},
  school = {University of Amsterdam},
  pdf = {},
  abstract = {
  		 In this thesis we describe a method that automatically indexes shots from 
  		 cinematographic video data based on the camera distance used. The proposed 
  		 method can be used for automatic analysis and interpretation of the meaning 
  		 of the shot within a video stream, as an assistance tool for video librarians, 
  		 and as indexing mechanism to be used within a video database system. Three 
  		 types of camera distance, originating from the art of filming, are distinguished. 
  		 Based on extracted and evaluated visual features an integrated classification 
  		 method is proposed and evaluated. It was found that, although discriminative 
  		 power of some features was limited, classification of cinematographic video 
  		 based on visual features is possible in the majority of shots.
  note = {Awarded by the NGI as best computer science masters thesis for the state of North-Holland in 2001.}