2006
DOI: 10.1007/11788034_1
|View full text |Cite
|
Sign up to set email alerts
|

Interactive Experiments in Object-Based Retrieval

Abstract: Abstract. Object-based retrieval is a modality for video retrieval based on segmenting objects from video and allowing end-users to use these objects as part of querying. In this paper we describe an empirical TRECVid-like evaluation of object-based search, and compare it with a standard image-based search into an interactive experiment with 24 search topics and 16 users each performing 12 search tasks on 50 hours of rushes video. This experiment attempts to measure the impact of object-based search on a corpu… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2006
2006
2010
2010

Publication Types

Select...
4
3

Relationship

4
3

Authors

Journals

citations
Cited by 14 publications
(8 citation statements)
references
References 11 publications
(11 reference statements)
0
8
0
Order By: Relevance
“…In [16] the authors demonstrate object-based video retrieval on a single movie Groundhog Day, where shots are retrieved based on objects appearing within the film, other common objects specified by example images and different visual aspects of the same object. In [17] the authors demonstrate shot retrieval based on segmented query objects matching segmented movie objects using colour, shape and/or texture. Shot retrieval based on the whole frame is also supported.…”
Section: Object-based Video Retrievalmentioning
confidence: 99%
“…In [16] the authors demonstrate object-based video retrieval on a single movie Groundhog Day, where shots are retrieved based on objects appearing within the film, other common objects specified by example images and different visual aspects of the same object. In [17] the authors demonstrate shot retrieval based on segmented query objects matching segmented movie objects using colour, shape and/or texture. Shot retrieval based on the whole frame is also supported.…”
Section: Object-based Video Retrievalmentioning
confidence: 99%
“…Another retrieval system based on a visual-query is described in [4], where the query is initialised by the user by one or more images which can come from outside the system (e.g., from Google Image search). The user can then select objects inside the image, or specify which is the feature (colour or texture) or visual-characteristic that makes it a good query image.…”
Section: A Rushes Retrieval and Browsingmentioning
confidence: 99%
“…In the most of the cases two interface conditions are compared to test which one works best. There is no constraint to reality: the system can effectively retrieve (Sav et al 2006) or be just a simulation (Dumais et al 2001); the user interface can support the accomplishment of a task (McDonald and Tait 2003) or just collect user's answers (e.g. relevance judgement) (Oard et al 2004).…”
Section: Operational Vs Hypothesis-basedmentioning
confidence: 99%