TVS '07: Proceedings of the international workshop on TRECVID video summarization
ACM2007 Proceeding
Publisher:
  • Association for Computing Machinery
  • New York
  • NY
  • United States
Conference:
MM07: The 15th ACM International Conference on Multimedia 2007 Augsburg Bavaria Germany September, 2007
ISBN:
978-1-59593-780-3
Sponsors:

Bibliometrics

Abstract

It is our great pleasure to welcome you to the first TRECVID Video Summarization workshop, held in conjunction with ACM Multimedia 2007. Although this is the first TRECVID summarization workshop, it is only the next in an annual series of TRECVID evaluation workshops going back to 2001. TRECVID is an annual event whereby the effectiveness of tasks relative to content-based video management is benchmarked in an open, metrics-based forum. TRECVID attracts over 60 research groups from across the world each year in an activity in which those groups can assess the relative effectiveness of their techniques against the best in the world. TRECVID has been instrumental in helping to push back the boundaries in tasks like shot boundary detection, video search and automatic concept/feature detection and has been a catalyst in helping the research community to achieve improvements in each of these in recent years.

This year is the first year that TRECVID has addressed the task of automatic video summarization and in this workshop we shall see the results of 22 research groups from 14 countries as they address the challenge of automatically summarizing raw, unprocessed rushes video down to at most 4% of the original content duration. This is also the first year that TRECVID has held one of its workshops outside the closed confines of the NIST campus in Gaithersburg, USA. We are delighted that doing this gives us the opportunity to showcase our collective activities to a wider audience, not just our own participants, and we believe that collocating with the ACM Multimedia conference is an ideal forum for this. We thank the ACM Multimedia workshop chairs for affording us this opportunity.

The TRECVID summarization workshop is not like any other workshop in that many or most of the workshop participants will have worked to complete a shared task, namely the automatic summarization of a collection of input videos. This means that we expect to have a highly interactive, highly involved workshop with much offline discussion and idea brainstorming. We are looking forward to it.

ARTICLE
The trecvid 2007 BBC rushes summarization evaluation pilot

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 ...

ARTICLE
Video summarization at Brno University of Technology
September 2007, pp 16–19https://doi.org/10.1145/1290031.1290033

This paper describes the video summarization system built for the TRECVID 2007 evaluation by the Brno team. Motivations for the system design and its overall structure are described followed by more detailed description of the critical parts of the ...

ARTICLE
Clever clustering vs. simple speed-up for summarizing rushes
September 2007, pp 20–24https://doi.org/10.1145/1290031.1290034

This paper discusses in detail our approaches for producing the submitted summaries to TRECVID, including the two baseline methods. The cluster method performed well in terms of coverage, and adequately in terms of user satisfaction, but did take longer ...

ARTICLE
Rushes video summarization by object and event understanding
September 2007, pp 25–29https://doi.org/10.1145/1290031.1290035

This paper explores a variety of visual and audio analysis techniques in selecting the most representative video clips for rushes summarization at TRECVID 2007. These techniques include object detection, camera motion estimation, keypoint matching and ...

ARTICLE
Generating comprehensible summaries of rushes sequences based on robust feature matching
September 2007, pp 30–34https://doi.org/10.1145/1290031.1290036

This paper describes our first attempt at tackling a pilot task in Trecvid: video summarization of rushes data [3]. Our method is based on the tight clustering produced via SIFT matching. In this first attempt, we try to examine how our approach ...

ARTICLE
A user-centered approach to rushes summarisation via highlight-detected keyframes
September 2007, pp 35–39https://doi.org/10.1145/1290031.1290037

We present our keyframe-based summary approach for BBC Rushes video as part of the TRECVid Summarisation benchmark evaluation carried out in 2007. We outline our approach to summarisation that uses video processing for feature extraction and is informed ...

ARTICLE
Video summarization preserving dynamic content
September 2007, pp 40–44https://doi.org/10.1145/1290031.1290038

This paper describes a system for selecting excerpts from unedited video and presenting the excerpts in a short summary video for efficiently understanding the video contents. Color and motion features are used to divide the video into segments where ...

ARTICLE
Rushes summarization with self-organizing maps
September 2007, pp 45–49https://doi.org/10.1145/1290031.1290039

In this paper, we describe our approach for video summarization that was applied to the BBC rushes material as part of the TRECVID 2007 evaluations. The method consists of initial shot boundary detection followed by shot similarity assessment and ...

ARTICLE
The Hong Kong Polytechnic University at TRECVID 2007 BBC rushes summarization
September 2007, pp 50–54https://doi.org/10.1145/1290031.1290040

In this paper, we propose the framework and methodology for BBC rushes summarization task of TRECVID 2007. We divide the entire task into three sub-tasks: shot segmentation; noise shot detection and removal; video summarization. We first segment the ...

ARTICLE
Split-screen dynamically accelerated video summaries
September 2007, pp 55–59https://doi.org/10.1145/1290031.1290041

In this paper, we describe our approach to the TRECVID 2007 BBC Rushes Summarization task. Our processing is composed of several steps. First the video is segmented into shots. Then, one-second video segments are clustered into similarity classes. The ...

ARTICLE
Skimming rushes video using retake detection
September 2007, pp 60–64https://doi.org/10.1145/1290031.1290042

In audiovisual post-production users are confronted with large amounts of redundant unedited raw material, called rushes. Viewing and organizing this material is a crucial but time consuming task. This paper describes an approach for creating skimmed ...

ARTICLE
Video rushes summarization by adaptive acceleration and stacking of shots
September 2007, pp 65–69https://doi.org/10.1145/1290031.1290043

When witnessing the great increase of video data available, it becomes clear that summarization is one of the great challenges ahead. One particular problem is the summarization of video rushes.

In this paper we present a straightforward approach that ...

ARTICLE
National institute of informatics, japan at TRECVID 2007: BBC rushes summarization
September 2007, pp 70–73https://doi.org/10.1145/1290031.1290044

In this paper, we present a method for BBC rushes summarization. In the proposed method, first the input video is decomposed into fragments by comparing consecutive frames. Next, these fragments are grouped by a clustering method. Using the clustering ...

ARTICLE
NTU TRECVID-2007 fast rushes summarization system
September 2007, pp 74–78https://doi.org/10.1145/1290031.1290045

Rushes are the raw materials used to produce a video. They often contain redundant and repetitive contents. Rushes summarization aims to provide a quick overview for a rushes video. As part of TRECVID 2007, NIST initiates a rushes summarization task. ...

ARTICLE
THU-ICRC at rush summarization of TRECVID 2007
September 2007, pp 79–83https://doi.org/10.1145/1290031.1290046

In this paper, we describe the THU-ICRC system for the rush summarization task of TRECVID07. Our main objective is to abstract a minimal length rush video by removing useless (or low-quality) and redundant frames and reserving important objects and ...

ARTICLE
Feature fusion and redundancy pruning for rush video summarization
September 2007, pp 84–88https://doi.org/10.1145/1290031.1290047

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 ...

ARTICLE
Attention-based video summarisation in rushes collection
September 2007, pp 89–93https://doi.org/10.1145/1290031.1290048

This paper presents the framework of a general video summarisation system on the rushes collection, which formalises the summarisation process as an 0-1 Knapsack optimisation problem. Three stages are included, namely content analysis, content selection ...

ARTICLE
On-line video skimming based on histogram similarity
September 2007, pp 94–98https://doi.org/10.1145/1290031.1290049

This paper describes the method proposed for the TRECVID 2007 BBC rushes summarization task. Such method has been developed starting from an on-line summary generation approach which provides a fast way to generate a base summary that can be later ...

Contributors

  • Paul Over
    National Institute of Standards and Technology
  • Alan F Smeaton
    Dublin City University

Acceptance Rates

TVS '07 Paper Acceptance Rate 18 of 18 submissions, 100%
Overall Acceptance Rate 44 of 70 submissions, 63%
YearSubmittedAcceptedRate
TVS '08522650%
TVS '071818100%
Overall704463%

Comments

About Cookies On This Site

We use cookies to ensure that we give you the best experience on our website.

Learn more

Got it!