Survey on modeling and indexing events in multimedia

Scherp, Ansgar; Mezaris, Vasileios

doi:10.1007/s11042-013-1427-7

Cited by 45 publications

(17 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides copy-move forgery detection, our method can also be applied to solve other problems in computer vision, such as video event detection [13] and multimedia indexing [23]. For example, when the targets of interest are small objects with non-textured appearances, our method can be applied to efficiently locate these small smooth regions and construct corresponding features.…”

Section: Discussionmentioning

confidence: 99%

Feature point-based copy-move forgery detection: covering the non-textured areas

Han

Niu

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Detection of copy-move forgery has recently attracted much attention. During the past decade, two categories of methods, namely block-based and feature point-based methods, gradually developed. Compared with block-based methods, feature point-based methods exhibit remarkable performance with respect to robustness and computational cost. However, the feature point-based methods are still incomplete especially in terms of forgeries involving small smooth regions. In this paper, we solve this problem by cautiously supplementing redundant feature points and feature fusion. We propose two-stage feature detection to obtain better feature coverage and enhance the matching performance by combining the MROGH and HH descriptor. We evaluated our method on two representative datasets. We use precision, recall and F 1 score to quantitatively evaluate the performance. Experimental results confirm the efficacy of our work.

show abstract

Section: Discussionmentioning

confidence: 99%

Feature point-based copy-move forgery detection: covering the non-textured areas

Han

Niu

2014

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…They can be classified in two groups: event clustering approaches [5][6][7][8][9][10][11] and event hybrid approaches [12,14,17,21,27,28]. Extracting events from multimedia in terms of photographs or images is much more difficult when compared to text for essentially two reasons: i) Event detection from images requires aggregation of heterogeneous metadata [29]; ii) Linking multimedia data to event model aspects is far more challenging then textual data [30]. In fact, many aspects of an event should be taken into consideration, as described in the multimedia event model presented in [13], such as time, space, actors, granularities, sub-events, etc.…”

Section: B Event Detection From Multimediamentioning

confidence: 99%

Foto2Events: From Photos to Event Discovery and Linking in Online Social Networks

Raad

Chbeir

2014

2014 IEEE Fourth International Conference on Big Data and Cloud Computing

View full text Add to dashboard Cite

Online social networking has become the predominant activity in the digital world thanks to multimedia data (mainly photos) sharing (e.g., photos now represent 93% of the top posts on Facebook). Discovering events where users are involved using their own posts and those shared by their friends would be of great importance. In this paper, we address this issue by providing an original approach able to detect, enrich and also link user's events using photos shared within his online social networks. Using metadata, our approach provides a multidimensional gathering of similar photos using their temporal, geographical, and social facets. To validate our approach, we implemented a prototype called Foto2Events and conducted a set of experiments on real and generated data. Results show that our approach works well for various metadata distributions.

show abstract

“…In addition, the modeling process must consider which sensor data models it, and how to model the interaction between events. Three different aspects of interaction have been identified in the literature, as summarized in [150]: 1) mereological referring to the part-of relation between events [130] that means that an event can be composed of different sub-events, 2) causality, referring to the fact that events can be classified in cause events or effect events [94,151], 3) correlation, referring to the relationship between two or more events having common cause [157].…”

Section: Tasksmentioning

confidence: 99%

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Ruocco

2014

SIGIR Forum

View full text Add to dashboard Cite

The proliferation of Web-and social media-based photo-sharing applications have not only opened many possibilities but also resulted in new needs and challenges. They have resulted in a large amount of personal photos being available for public access. One of the most interesting characteristics of these data is that they are surrounded by 1) textual annotations, also called tags, which are intended to describe and categorize, by collective user efforts, the uploaded resources 2) temporal information referring to when a pictures has been taken and often by 3) a locational information describing where the picture has been taken. Despite the recent developments and technological advances in Web-based media-sharing applications, the continuously increasing amount of available information has made the access to the photos a demanding task. In general, we can address this challenge by allowing photo collections to be organized and browsed through the concept of events. We also believe most users are familiar with searching photo collections using events as starting points.Aiming at supporting the detection and search of event-related photos, this thesis proposes a novel framework for extracting pictures related to real-life events from a collection of Web-images by leveraging on their temporal geographical and textual annotations and comparing the proposed approach with existing related state-ofthe-art approaches. Second, a set of geographical features is proposed describing the characteristics of the geographical profile of query terms deriving concepts from exploratory analysis. Third, the thesis provides two different tag-based search framework to improve the effectiveness of searching images related to events. The first framework is based on temporal and geographical proximity of query terms to the temporal neighbors of a given timestamped query, while the second framework is based on a novel machine-learning based query expansion method combining the heterogeneous textual, temporal and geographical similarity between query terms and candidate expansion terms for the selection of the expansion terms given a free text textual query.All the proposed methods have been evaluated by performing extensive experiments on real data gathered from media-sharing applications on the Web. Where possible, comparison with related techniques has been performed to reinforce the validity of the presented approaches. The proposed methods have shown promising results in both the extraction and clustering of event-related images and searching eventrelated pictures by using metrics from the state of the art.i ii Preface

show abstract

Survey on modeling and indexing events in multimedia

Cited by 45 publications

References 67 publications

Feature point-based copy-move forgery detection: covering the non-textured areas

Feature point-based copy-move forgery detection: covering the non-textured areas

Foto2Events: From Photos to Event Discovery and Linking in Online Social Networks

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Contact Info

Product

Resources

About