Instantly indexed multimedia databases of real world events

Pingali, Gopal; Opalach, Agata; Jean, Yves D.; Carlbom, Ingrid

doi:10.1109/tmm.2002.1017739

Cited by 29 publications

(15 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Event-centric applications like [18,19,20] show different types of media assets as different facets of the events they document. From the authors' point of view, there is no other intuitive way to index multimedia assets from multiple users.…”

Section: Unified Indexingmentioning

confidence: 99%

“…The event model E [1] introduced by Westermann and Jain has been developed based on an analysis and abstraction of events in various domains such as research publications [21], personal media [24], meetings [19], enterprise collaboration [25], and sports [18]. It provides a generic structure for the definition of events and is extensible to the requirements of events in the most different concrete applications and domains.…”

Section: Generic Event Model Ementioning

confidence: 99%

See 1 more Smart Citation

<title>Event-centric media management</title>

2008

View full text Add to dashboard Cite

The management of the vast amount of media assets captured at every day events such as meetings, birthday parties, vacation, and conferences has become an increasingly challenging problem. Today, most media management applications are media-centric. This means, they put the captured media assets into the center of the management. However, in recent years it has been proposed that events are a much better abstraction of human experience and thus provide a more appropriate means for managing media assets. Consequently, approaches that include events into their media management solution have been explored. However, they typically consider events only as some more metadata that can be extracted from the media assets. In addition, today's applications and approaches concentrate on particular problems such as event detection, tagging, sharing, classification, or clustering and are often focused on a single media type. In this paper, we argue for the benefits of an event-centric media management (EMMa) approach that looks at the problem of media management holistically. Based on a generic event model, we specify a media event model for the EMMa approach. The single phases and processes of the EMMa approach are defined in a general process chain for an event-centric media management, the EMMa cycle. This cycle follows the event concept throughout all phases and processes of the chain and puts the concept of events in the center of the media management. Based on the media event model and EMMa cycle, we design a component-based architecture for the EMMa approach and conduct an implementation of the approach.

show abstract

Section: Unified Indexingmentioning

confidence: 99%

Section: Generic Event Model Ementioning

confidence: 99%

<title>Event-centric media management</title>

2008

View full text Add to dashboard Cite

show abstract

“…Pingali et al [15] proposed an approach to construct the instant semantics for tennis video. The developed system (Lucent Vision) can instantly construct the semantics for tennis video.…”

Section: Related Workmentioning

confidence: 99%

“…In summary, most of published papers worked on the recorded video to acquire semantics except that one paper was for acquiring the instant semantics of tennis video [15] and the other acquired live highlights using audio/video cues [18]. In this paper we aim to instantly acquire semantics and provide semanticsbased services of live soccer video.…”

Section: Related Workmentioning

confidence: 99%

An instant semantics acquisition system of live soccer video with application to live event alert and on-the-fly language selection

Yan

et al. 2008

Proceedings of the 2008 International Conference on Content-Based Image and Video Retrieval

View full text Add to dashboard Cite

Automatic indexing of recorded sports video is a hard problem, even more so for live sports video, though a lot of advances have been achieved in the recent years. This paper presents a semiautomatic instant semantics generation system of live soccer video and its two applications: live event alert and instant semantics embedding. A key technical challenge of building the proposed system is how to acquire the desired semantics in a very short time lag. To confront this challenge, we develop a threechannel approach to accurately and quickly acquire semantics. The three channels are (1) developing the tool for inputting gamelog, (2) signal communication for getting commands of referee and director, and (3) video analysis for finding event boundary. The proposed system requires only a very small amount of manual work to operate gamelog acquisition tool using an icon-based interface for entering event log. Experimental results show that our system can quickly obtain the semantics of live soccer video, alert live events with a very small latency, and embed semantics into broadcasting video with a short time lag.

show abstract

“…Previous research has been conducted on trying to enrich users' interest, engagement, and experience of media in different ways [6,8,21,22]. However, few have focused on sport events and the approach to give the viewer an alternative view or option of whom to follow in these events has not been utilized.…”

Section: Related Workmentioning

confidence: 99%