Dialogue Sequence Detection in Movies

Lehane, Bart; O’Connor, Noel E.; Murphy, Noel

doi:10.1007/11526346_32

Cited by 20 publications

(30 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The event segmentation and classification technique used here is described in detail and evaluated in [29,30,12]. It exploits a number of observations about film creation principles.…”

Section: Figure 2: Overall Approachmentioning

confidence: 99%

See 1 more Smart Citation

Associating characters with events in films

Salway¹,

Lehane

O’Connor

2007

Proceedings of the 6th ACM International Conference on Image and Video Retrieval

Self Cite

View full text Add to dashboard Cite

The work presented here combines the analysis of a film's audiovisual features with the analysis of an accompanying audio description. Specifically, we describe a technique for semantic-based indexing of feature films that associates character names with meaningful events. The technique fuses the results of event detection based on audiovisual features with the inferred on-screen presence of characters, based on an analysis of an audio description script. In an evaluation with 215 events from 11 films, the technique performed the character detection task with P recision = 93% and Recall = 71%. We then go on to show how novel access modes to film content are enabled by our analysis. The specific examples illustrated include video retrieval via a combination of event-type and character name and our first steps towards visualization of narrative and character interplay based on characters occurrence and co-occurrence in events.

show abstract

“…The event segmentation and classification technique used here is described in detail and evaluated in [29,30,12]. It exploits a number of observations about film creation principles.…”

Section: Figure 2: Overall Approachmentioning

confidence: 99%

“…Once the shot boundaries are known, the editing pace can be inferred. Two motion features are extracted per shot, MPEG-7 motion intensity [33] and a measure of camera motion [29]. A support vector machine based classifier is used to classify audio into one of: speech, music, silence and other audio.…”

Section: Figure 2: Overall Approachmentioning

confidence: 99%

Associating characters with events in films

Salway¹,

Lehane

O’Connor

2007

Proceedings of the 6th ACM International Conference on Image and Video Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a starting point, four low-level audio features are extracted, namely the High Zero Crossing Rate Ratio, the Silence Ratio, the Short Term Energy, and the Short-Term Energy Variation. The effectiveness of these low-level features in helping to distinguish between speech and music has previously been demonstrated [11,18]. In order to classify each one second window of audio, a set of support vector machines (SVMs) are used, one for each audio category.…”

Section: Audio-visual Analysis Techniques Usedmentioning

confidence: 99%

“…The values obtained from processing each one second window are then up-sampled in order to compute the proportion of each audio category for each shot. At the end of this process, for each shot of a movie, there is a value for the percentage of speech, music, silence, quiet music, speech with background music and other audio present (further details of the audio classification process are provided in [18]). …”

Section: Audio-visual Analysis Techniques Usedmentioning

confidence: 99%

“…[23] detects violent events in a movie by searching for visual cues such as flames or blood pixels, or audio cues such as explosions or screaming. Previous work by some of the authors focused on completely summarising a movie by detecting all of the relevant events [18,17]. Three event classes were chosen (exciting, dialogue and musical) that typically encapsulate all relevant portions of a movie.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Automatically selecting shots for action movie trailers

Smeaton

Lehane

O’Connor

et al. 2006

Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval

Self Cite

View full text Add to dashboard Cite

Movie trailers, or previews, are an important method of advertising movies. They are extensively shown before movies in cinemas, as well as on television and increasingly, over the Internet. Making a trailer is a creative process, in which a number of shots from a movie are selected in order to entice a viewer in to paying to see the full movie. Thus, the creation of these trailers is an integral part in the promotion of a movie. Action movies in particular rely on trailers as a form of advertising as it is possible to show short, exciting portions of an action movie, which are likely to appeal to the target audience. This paper presents an approach which automatically selects shots from action movies in order to assist in the creation of trailers. A set of audiovisual features are extracted that aim to model the characteristics of shots typically present in trailers, and a support vector machine is utilised in order to select the relevant shots. The approach taken is not particularly novel but the results show that the process may be used in order to ease the trailer creation process or to facilitate the creation of variable length, or personalised trailers.

show abstract

References

2011

Multimedia Semantics

View full text Add to dashboard Cite

Dialogue Sequence Detection in Movies

Cited by 20 publications

References 8 publications

Associating characters with events in films

Associating characters with events in films

Automatically selecting shots for action movie trailers

References

Contact Info

Product

Resources

About