Indexing, browsing, and searching of digital video

Smeaton, Alan F.

doi:10.1002/aris.1440380109

Cited by 29 publications

(24 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The two most common media types for sub-object retrieval are video and text. Smeaton (2004) has elegantly summarized the retrieval of video components including interactive video browsing and retrieval, so in this section I concentrate on retrieval of document components.…”

Section: Part-of-retrievalmentioning

confidence: 99%

Interactive information retrieval

Ruthven

2008

Annual Review Info Sci & Tec

View full text Add to dashboard Cite

Section: Part-of-retrievalmentioning

confidence: 99%

Interactive information retrieval

Ruthven

2008

Annual Review Info Sci & Tec

View full text Add to dashboard Cite

“…. The danger of choosing from the start or end of a shot is the increased likelihood of picking up artifacts from the previous shot if there has been a gradual rather than a hard shot transition..." [16]. Therefore we investigated if linearly weighting images towards the middle as being better candidates for a keyframe proved beneficial.…”

Section: Increase Emphasis On Images Towards Middle Of Eventmentioning

confidence: 99%

Investigating keyframe selection methods in the novel domain of passively captured visual lifelogs

Doherty

Byrne

Smeaton

et al. 2008

Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval

Self Cite

View full text Add to dashboard Cite

The SenseCam is a passive capture wearable camera, worn around the neck, and when worn continuously it takes an average of 1,900 images per day. It can be used to create a personal lifelog or visual recording of the wearer's life which can be helpful as an aid to human memory. For such a large amount of visual information to be useful, it needs to be structured into "events", which can be achieved through automatic segmentation. An important component of this structuring process is the selection of keyframes to represent individual events. This work investigates a variety of techniques for the selection of a single representative keyframe image from each event, in order to provide the user with an instant visual summary of that event. In our experiments we use a large test set of 2,232 lifelog events collected by 5 users over a time period of one month each. We propose a novel keyframe selection technique which seeks to select the image with the highest "quality" as the keyframe. The inclusion of "quality" approaches in keyframe selection is demonstrated to be useful owing to the high variability in image visual quality within passively captured image collections.

show abstract

“…However, when presented with a large archive of content, a user will, in many cases, be unsure of what programme they are looking for, for example, a video archive that contains all recordings of a late night chat show, how can a user, without knowing the date of broadcast, find the interview with Madonna where she throws a glass of water in the host's face ? In this case there is a need for video searching through the actual video content, using some keywords from the dialogue between Madonna and the chat show host [24] or if CCTV video, using some representation of the object corresponding to the CCTV suspect [14].…”

Section: Managing Video Archivesmentioning

confidence: 99%