Shot boundary detection The shot boundary detection system in 2007 is basically the same as that of last year. We make three major modifications in the system of this year. First, CUT detector and GT detector use block based RGB color histogram with the different parameters instead of the same ones

High level feature extraction ID MAP Training set Testing set Brief description run1 0.116 LIG & CAS 1frame/shot & 3frame/shot baseline+keypoint run2 0.123 LIG & CAS 3frame/shot baseline run3 0.057

This paper provides an overview of a pilot evaluation of video summaries using rushes from several BBC dramatic series. It was carried out under the auspices of TRECVID. Twenty-two research teams submitted video summaries of up to 4 % duration, of 42 individual rushes video les aimed at compressing

(s) TRECVID 2007 2SB Task Details Groups may submit up to 10 runs Comparison to human-annotated reference (thanks to Jonathan Lasko, again, but last time) Groups were again asked to provide some standard information on the processing complexity of each run: Total runtime in seconds Total decode time

1.1 How to Retrieve Video Content? 217 1.2 Human-Driven Labeling 219 1.3 Machine-Driven Labeling 219

This paper presents our approaches and results of the four TRECVID 2008 tasks we participated in: high-level feature extraction, automatic video search, video copy detection, and rushes summarization. In high-level feature extraction, we jointly submitted our results with Columbia University

Abstract not found

This paper presents a video summarization technique for rushes that employs high-level feature fusion to identify segments for inclusion. It aims to capture distinct video events using a variety of features: k-means based weighting, speech, camera motion, significant differences in HSV colorspace, and a dynamic time warping (DTW) based feature that suppresses repeated scenes. The feature functions are used to drive a weighted k-means based clustering to identify visually distinct, important segments that constitute the final summary. The optimal weights corresponding to the individual features are obtained using a gradient descent algorithm that maximizes the recall of ground truth events from representative training videos. Analysis reveals a lengthy computation time but high quality results (60 % average recall over 42 test videos) as based on manually-judged inclusion of distinct shots. The summaries were judged relatively easy to view and had an average amount of redundancy.

detection:an experimental perspective