Event-based media processing and analysis: A survey of the literature

Abstract

Research on event-based processing and analysis of media is receiving an increasing attention from the scientific community due to its relevance for an abundance of applications, from consumer video management and video surveillance to lifelogging and social media. Events have the ability to semantically encode relationships of different informational modalities, such as visual-audio-text, time, involved agents and objects, with the spatio-temporal component of events being a key feature for contextual analysis. This unveils an enormous potential for exploiting new information sources and opening new research directions. In this paper, we survey the existing literature in this field. We extensively review the employed conceptualization of the notion of event in multimedia, the techniques for event representation and modeling, the feature representation and event inference approaches for the problems of event detection in audio, visual, and textual content. Furthermore, we review some key event-based multimedia applications, and various benchmarking activities that provide solid frameworks for measuring the performance of different event processing and analysis systems. We provide an in-depth discussion of the insights obtained from reviewing the literature and identify future directions and challenges.Keywords: Event-based media processing and analysis, event conceptualization, event representation and modeling, multimedia event detection, event-based applications and benchmarking, survey of the literature

Detection and Resolution of Rumours in Social Media

“…They then use the set of keywords associated with an event to track new incoming tweets. Similar approaches to event tracking have been introduced by others, such as using a bipartite graph for topical word selection (Long et al 2011), using text classification techniques to determine whether incoming data is related to a previously identified event or to a new one (Reuter and Cimiano 2012), and using similarity metrics (Tzelepis et al 2016). However, these approaches have not been directly applied to rumours and hence their applicability needs to be further studied with a suitable rumour dataset.…”

The JORD System

“…In recent years, social networks, such as Twitter and Flickr, have emerged as important sources of information that report events in real-time, and provide a much broader story [13,4]. With respect to Twitter, for example, the majority of the users use Twitter for breaking news, and thereby become a part of the process by commenting, posting and sharing information at the moment when an event occurs [1].…”

Improving video event retrieval by user feedback

“…Examples of static features are SIFT [31], SURF [1] and LBP [37] features. Currently, one of the layers of a pre-trained deep neural network is used as the static feature vector [53]. The static features can be represented in a Bag of Words approach [23] and be aggregated over the video using an average or max pooling strategy [53].…”