A distance measure for repeated takes of one scene

Bailer, Werner; Lee, Felix; Thallinger, Georg

doi:10.1007/s00371-008-0280-6

Cited by 12 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This experiment uses the results of the algorithms described in [3]. The algorithms are two variants of the longest common subsequence (LCSS) based algorithm presented in that paper, and an algorithm based on dynamic time warping (DTW) used for comparison.…”

Section: Correlation On Repeated Take Detection Algorithm Outputsmentioning

confidence: 99%

“…All results are based on a ground truth temporal segmentation in order to support algorithms that need same the segmentation of ground truth and result set. The data consists of the outputs of the three algorithms on six videos from the TRECVID 2007 rushes test set (MRS07063, MRS025913, MRS044731, MRS144760, MRS157475, MS216210) and the ground truth created by the authors of [3].…”

Section: Correlation On Repeated Take Detection Algorithm Outputsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating detection of near duplicate video segments

Bailer

2010

Proceedings of the ACM International Conference on Image and Video Retrieval

Self Cite

View full text Add to dashboard Cite

The automatic detection of near duplicate video segments, such as multiple takes of a scene or different news video clips showing the same event, has received growing research interest in recent years. However, there is no agreed way of evaluating near duplicate detection algorithms. This makes it very hard to compare the performance of different algorithms, even if they are applied to the same data set. In this paper we have implemented several evaluation measures found in literature and we apply them to real algorithm outputs and a simulated result data set. We then calculate the correlation between the results obtained with the different measures in order to investigate whether they can be compared or not. The results show that the correlation between the measures is some cases quite low, and some measures are especially sensitive to certain types of deviations from the ground truth. However, a group of precision/recall type measures and two others are clearly correlated, though with moderate correlation coefficients. We also analyze the correlation between these measures and the subjective human judgment of the number of repeated segments in summary videos.

show abstract

Section: Correlation On Repeated Take Detection Algorithm Outputsmentioning

confidence: 99%

Section: Correlation On Repeated Take Detection Algorithm Outputsmentioning

confidence: 99%

Evaluating detection of near duplicate video segments

Bailer

2010

Proceedings of the ACM International Conference on Image and Video Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…We use the approach proposed in [25] to identify repeated takes of the same scene. This algorithm uses a variant of the Longest Common Subsequence (LCSS) measure on a sequence of visual activity samples and color and texture features of regularly samples key frames to identify takes of the same scene.…”

Section: Global Color Similaritymentioning

confidence: 99%

“…In addition, key frames need to be extracted synchronously from all views. If necessary, the clips from different views can be automatically temporally aligned, using the method for repeated take detection [25] with a different parameterization.…”

Section: Multiple Viewsmentioning

confidence: 99%

A Video Browsing Tool for Content Management in Postproduction

Bailer

Weiss

Kienast

et al. 2010

International Journal of Digital Multimedia Broadcasting

Self Cite

View full text Add to dashboard Cite

We propose an interactive video browsing tool for supporting content management and selection in postproduction. The approach is based on a process model for multimedia content abstraction. A software framework based on this process model and desktop and Web-based client applications are presented. For evaluation, we apply two TRECVID style fact finding approaches (retrieval and question answering tasks) and a user survey to the evaluation of the video browsing tool. We analyze the correlation between the results of the different methods, whether different aspects can be evaluated independently with the survey, and if a learning effect can be measured with the different methods, and we also compare the full-featured desktop and the limited Web-based user interface. The results show that the retrieval task correlates better with the user experience according to the survey. The survey rather measures the general user experience while different aspects of the usability cannot be analyzed independently.

show abstract

“…Bailer et al [1] proposed a distance measure based on Longest Common Subsequence (LCSS) to determine the similarity of segments in the video. These similar segments were then grouped into one cluster if they belong to one scene.…”

Section: Introductionmentioning

confidence: 99%

Improving Retake Detection by Adding Motion Feature

Hoang

Satoh

et al. 2011

Image Analysis and Processing – ICIAP 2011

View full text Add to dashboard Cite

Retake detection is useful for many applications of video summarization. It is a challenging task since different takes of the same scene are usually of different lengths; or have been recorded under different environment conditions. A general approach to solve this problem is to decompose the input video sequence into sub-sequences and then group these sub-sequences into clusters. By combining with temporal information, the clustering result is used to find take and scene boundaries. One of the most difficult steps in this approach is to cluster sub-sequences. Most of previous approaches only use one keyframe for representing one sub-sequence and extract features such as color and texture from this keyframe for clustering. We propose another approach to improve the performance by combining the motion feature extracted from each sub-sequence and the features extracted from each representing keyframe. Experiments evaluated on the standard benchmark dataset of TRECVID BBC Rushes 2007 show the effectiveness of the proposed method.

show abstract

A distance measure for repeated takes of one scene

Cited by 12 publications

References 17 publications

Evaluating detection of near duplicate video segments

Evaluating detection of near duplicate video segments

A Video Browsing Tool for Content Management in Postproduction

Improving Retake Detection by Adding Motion Feature

Contact Info

Product

Resources

About