Managing Event Information: Modeling, Retrieval, and Applications

Gupta, Amarnath; Jain, Ramesh

doi:10.2200/s00374ed1v01y201107dtm019

Cited by 12 publications

(12 citation statements)

References 100 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our ontologies extend the E* model [8] to specify relationships between events and entities. Specifically, we utilize the relationships "subevent-of", which specifies event containment.…”

Section: Event Modelmentioning

confidence: 99%

“…The symbols ⊏ L and ⊏ T indicate spatial and temporal containment [8]. In later sections, we refer to the location and time of the event, L E and T E as E.occurs-at and E.occurs-during respectively.…”

Section: Event Modelmentioning

confidence: 99%

“…Their modeling framework allows representation of static and dynamic associations, which is very critical in modeling real world relationships. For our work, we rely on primitives like the one mentioned in this framework as well as event relations described in [8]. These event semantics (subevent-of and partitcipation relation described in Section 2) provides an additional dimension of reasoning than the works described here.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Discovering Context for Real-World Events

Satish¹,

Jain²,

Gupta³

2018

MUC

Self Cite

View full text Add to dashboard Cite

ABSTRACT. Specifying the search space is an important step in designing multimedia annotation systems. With the large amount of data available from sensors and web services, context-aware approaches for pruning search spaces are becoming increasingly common. In these approaches, the search space is limited by the contextual information obtained from a fixed set of sources. For example, a system for tagging faces in photos might rely on a static list of candidates obtained from the photo owner's Facebook profile. These contextual sources can become extremely large, which leads to lower accuracy in the annotation problem. We present Context Discovery Algorithm, a technique to progressively discover the most relevant search space from a dynamic set of context sources. This allows us to reap the benefits of context, while keeping the size of the search space within limits. As a concrete application for our approach, we present a simple photo management application, which tags faces of people in a user's personal photos. We empirically study the role of our framework in the face tagging application to tag photos taken at real-world events, such as conferences, weddings or social gatherings. Our results show that the availability of event context, and its dynamic discovery, can produce 97.5% smaller search spaces with at least 93% correct tags. RÉSUMÉ. Spécifier un espace de recherche représente une étape importante dans la conception de systèmes d'annotation multi-média. Avec une grande quantité de données provenant de capteurs et de services Web, les approches sensible au contexte deviennent de plus en plus usuelles pour élaguer les espaces de recherche. Dans ces approches, l'espace de recherche est limité par les informations contextuelles qui sont obtenues à partir d'un ensemble donné de sources. Par exemple, un système pour marquer les visages dans des photos pourrait reposer sur une liste statique de candidats obtenus à partir de photos de personnes sur leur profil FaceBook. Ces sources contextuelles peuvent devenir très volumineuses, ce qui peut conduire à une précision plus faible dans le problème des annotations. Nous présentons un nouvel algorithme de découverte du contexte, une technique pour découvrir progressivement l'espace de recherche le plus pertinent pour un ensemble dynamique de sources contextuelles. Ceci nous permet de recueillir les bénéfices du contexte tout en gardant la taille de l'espace de recherche à une taille raisonnable. Comme concrète application de notre approche, nous présentons une application simple de management de photos, où les visages de personnes sont marqués à partir de photos privées d'un utilisateur. Nous étudions empiriquement le rôle de notre cadre de travail dans l'application de marquage de visages pour marquer des photos prises lors d'événements sociaux comme des conférences, des mariages ou de rassemblements sociaux. Nos résultats montrent que la disponibilité du contexte des événements et sa découverte dynamique peut produire des espaces de recherche plus petits de 97...

show abstract

“…Our ontologies extend the E* model [8] to specify relationships between events and entities. Specifically, we utilize the relationships "subevent-of", which specifies event containment.…”

Section: Event Modelmentioning

confidence: 99%

Section: Event Modelmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Discovering Context for Real-World Events

Satish¹,

Jain²,

Gupta³

2018

MUC

Self Cite

View full text Add to dashboard Cite

show abstract

“…Events are typically modeled as data tuples consisting of attributes, values and timestamps, such as the 3-tuple by Voisard and Ziekow [21], the 2-tuple by Zhou et al [24] or XML schema [3]. The E* event model [9] is useful for modeling multimedia events. A probabilistic event model for processing uncertain events is proposed by Wasserkrug et al [22].…”

Section: Related Workmentioning

confidence: 99%

The process-oriented event model (PoEM)

Patri

Sorathia²,

Panangadan

et al. 2014

Proceedings of the 8th ACM International Conference on Distributed Event-Based Systems

View full text Add to dashboard Cite

The paper presents a comprehensive theoretical framework for modeling events and semantics of event processing at a level of abstraction that captures the different processes in industrial applications but is not limited to a specific application domain. The model, called Process-oriented Event Model (PoEM), provides a formal approach to model realworld entities and their interrelationships, and specifies the process of moving from data streams to event detection to event-based goal planning. The model links event detection to states, actions, and roles, enabling event notification, filtering, context awareness and escalation. PoEM defines event and non-event concepts and combines information from them to build an event processing workflow. Usage of the PoEM model is illustrated in case studies from the oil and gas industry and maritime piracy events.

show abstract

“…CueNet models an input photograph as a photo-captureevent [3] in an event graph [1]. This event graph containing the photo event, and its associated owner, is then used (a) Picatrix -Our event based photo browsing interface.…”

Section: Progressive Discoverymentioning

confidence: 99%

Visualizing progressive discovery

Satish

Jain

Gupta

2013

Proceedings of the 3rd ACM Conference on International Conference on Multimedia Retrieval

Self Cite

View full text Add to dashboard Cite

Computational problems are increasingly relying on contextaware approaches for tractable solutions. Usually, these approaches statically link additional sources of information to those already present in the problem space. We have been building CueNet, a context discovery framework, which will dynamically discover the most relevant context for a given application problem. In this demonstration, we will show how the identities of people in personal photos can be discovered through contextual information. We present Picatrix: an event based photo browsing web interface. Users can select a photo, and see a live visualization of how our context discovery algorithm, seeded with the initial information, discovers context from different data sources, and uses it to tag the faces in the given photo.

show abstract

Managing Event Information: Modeling, Retrieval, and Applications

Cited by 12 publications

References 100 publications

Discovering Context for Real-World Events

Discovering Context for Real-World Events

The process-oriented event model (PoEM)

Visualizing progressive discovery

Contact Info

Product

Resources

About