&lt;title&gt;Echocardiogram video summarization&lt;/title&gt;

Ebadollahi, Shahram; Chang, Shih-Fu; Wu, Henry; Takoma, Shin

doi:10.1117/12.428229

Cited by 15 publications

(13 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Summarizing an ECG, and video in general as seen in the work of [9], involves extracting the most interesting video frames, which are called key frames, which enable the user to easily navigate through the ECGs and view their essential parts. For [59] summarizing an ECG involves two things: parsing the ECG and selecting the key frames. The aim of the parser is to temporally segment the sequences of the video into smaller units, which are called shots.…”

Section: Multimedia Summarizationmentioning

confidence: 99%

“…[60], follow a similar approach to [59] in order to parse the video stream into physical units. Then video group detection, scene detection and clustering strategies are used to mine the video content structure.…”

Section: Multimedia Summarizationmentioning

confidence: 99%

“…This is achieved by connecting the system of [57] with DEFINDER, a text mining tool for extracting definitions of terms from medical articles (see [58]). [59] and [60] present systems performing summarization of documents which have multimedia content, echocardiograms and medical videos respectively.…”

Section: Abstractive Multi-document Summarizationmentioning

confidence: 99%

See 2 more Smart Citations

Summarization from medical documents: a survey

Afantenos

Karkaletsis

Stamatopoulos

2005

Artificial Intelligence in Medicine

155

View full text Add to dashboard Cite

Objective: The aim of this paper is to survey the recent work in medical documents summarization. Background: During the last decade, documents summarization got increasing attention by the AI research community. More recently it also attracted the interest of the medical research community as well, due to the enormous growth of information that is available to the physicians and researchers in medicine, through the large and growing number of published journals, conference proceedings, medical sites and portals on the World Wide Web, electronic medical records, etc. Methodology: This survey gives first a general background on documents summarization, presenting the factors that summarization depends upon, discussing evaluation issues and describing briefly the various types of summarization techniques. It then examines the characteristics of the medical domain through the different types of medical documents. Finally, it presents and discusses the summarization techniques used so far in the medical domain, referring to the corresponding systems and their characteristics. Discussion and Conclusions: The paper discusses thoroughly the promising paths for future research in medical documents summarization. It mainly focuses on the issue of scaling to large collections of documents in various languages and from different media, on personalization issues, on portability to new sub-domains, and on the integration of summarization technology in practical applications.

show abstract

Section: Multimedia Summarizationmentioning

confidence: 99%

Section: Multimedia Summarizationmentioning

confidence: 99%

See 1 more Smart Citation

Summarization from medical documents: a survey

Afantenos

Karkaletsis

Stamatopoulos

2005

Artificial Intelligence in Medicine

155

View full text Add to dashboard Cite

show abstract

“…In the digital echocardiography video project, 2 we developed techniques to detect and recognize constituent views in each video, extract clinically important frames, and generate time-compressed clinical summaries (we show the system architecture in Figure B, next page). Such tools facilitate many exciting applications.…”

Section: Medical Video Indexing and Summarizingmentioning

confidence: 99%

The holy grail of content-based media analysis

Chang

2002

IEEE Multimedia

View full text Add to dashboard Cite

T ools and systems for content-based access to multimedia and-image, video, audio, graphics, text, and any number of combinations-has increased in the last decade. We've seen a common theme of developing automatic analysis techniques for deriving metadata (data describing information in the content at both syntactic and semantic levels). Such metadata facilitates developing innovative tools and systems for multimedia information retrieval, summarization, delivery, and manipulation. Many interesting demonstrations of potential applications and services have emerged-finding images visually similar to a chosen picture (or sketch); summarizing videos with thumbnails of keyframes; finding video clips of a specific event, story, or person; and producing a two-minute skim of an hour-long program. (Audio-visual skims are condensed media clips that summarize information in the content.)There's much excitement and buzz created by these fancy applications. But people are always asking, What will be engineering's Holy Grail for content-based media analysis in practical applications? My response is that the answer is complex. It's less about a specific algorithm or service than a rigorous methodology to formulate and evaluate content-based analysis research. Content chainTo evaluate content-based research methodologies, we must first consider who the intended users are and whether alternative solutions exist. Hence, it's important to consider each solution within the context of the content chain, the process starting with acquisition, followed by production, processing, and finally consumption. chain and is produced by specific production sources and methods, associated with multiple media modalities (audio, images, video, graphics, text, and so forth), and intended for specific user groups. It's important to remember that most often users don't deal with raw content just coming off the sensing devices-many content processing stages have already occurred. Figure 1 also highlights important principles critical for effective content analysis:❚ understanding production models, ❚ fusing multimedia data, and ❚ exploring perceptual viewer models. Areas of researchBy content-based media analysis, I refer to research in the following areas:❚ Reverse engineering of the media capturing and editing processes. Works in this area attempt to reverse engineer the capturing and editing processes, and recover the constituent content components such as shots, scenes, and structural elements (dialogues, anchors, and so forth) in the video. By breaking videos into atomic entities at different levels, we can develop intuitive and efficient access tools.❚ Extracting and matching objects. Similar to breaking documents into words or phrases, we can decompose images and videos into objects, from which we can derive comprehensive attributes. Much work has been pursued to define adequate features and criteria for matching audio-visual content based on audio-visual properties and spatiotemporal relationships. ❚ Meaning decoding and automatic annotation...

show abstract

“…• A pictorial summary [3,[7][8][9][10][11][12][13]18,19,25,30,31] is a collection of still images (possibly varying in size) arranged in time. The use of compact images provides the user with an overview of the video directly and efficiently; however, the motion and audio information of the video is lost.…”

mentioning

confidence: 99%

Exploring video content structure for hierarchical summarization

Zhu

Fan

et al. 2004

Multimedia Systems

View full text Add to dashboard Cite

In this paper, we propose a hierarchical video summarization strategy that explores video content structure to provide the users with a scalable, multilevel video summary. First, video-shot-segmentation and keyframe-extraction algorithms are applied to parse video sequences into physical shots and discrete keyframes. Next, an affinity (self-correlation) matrix is constructed to merge visually similar shots into clusters (supergroups). Since video shots with high similarities do not necessarily imply that they belong to the same story unit, temporal information is adopted by merging temporally adjacent shots (within a specified distance) from the supergroup into each video group. A video-scene-detection algorithm is thus proposed to merge temporally or spatially correlated video groups into scenario units. This is followed by a scene-clustering algorithm that eliminates visual redundancy among the units.A hierarchical video content structure with increasing granularity is constructed from the clustered scenes, video scenes, and video groups to keyframes. Finally, we introduce a hierarchical video summarization scheme by executing various approaches at different levels of the video content hierarchy to statically or dynamically construct the video summary. Extensive experiments based on real-world videos have been performed to validate the effectiveness of the proposed approach.

show abstract

<title>Echocardiogram video summarization</title>

Cited by 15 publications

References 8 publications

Summarization from medical documents: a survey

Summarization from medical documents: a survey

The holy grail of content-based media analysis

Exploring video content structure for hierarchical summarization

Contact Info

Product

Resources

About