Using contextual spaces for image re-ranking and rank aggregation

Pedronette, Daniel Carlos Guimarães; Torres, Ricardo da Silva; Calumby, Rodrigo Tripodi

doi:10.1007/s11042-012-1115-z

Cited by 14 publications

(22 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The potential of this framework is that each module can be improved separately, leading to better results. For example, our text module can use more sophisticated text processing/analysis, or the fusion module can apply more elaborated approaches (e.g., [5,15,16]). …”

Section: Discussionmentioning

confidence: 99%

“…Score-based rank aggregation approaches has been used in the multimodal image retrieval context [16] and also used for associating photos to georeferenced textual documents [2]. In this paper, we aim at using a score-based rank aggregation approach for combining features of di↵erent modalities.…”

Section: Related Workmentioning

confidence: 99%

“…The goal of the data fusion module is to combine the scores produced by features of di↵erent modalities in order to produce a more e↵ective score. We use a rank aggregation method based on a multiplication approach, initially proposed for multimodal image retrieval [16].…”

Section: Information Fusionmentioning

confidence: 99%

See 2 more Smart Citations

Multimedia multimodal geocoding

Pedronette

Almeida

et al. 2012

Proceedings of the 20th International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

This work is developed in the context of the placing task of the MediaEval 2011 initiative. The objective is to geocode (or geotag) a set of videos, i.e., automatically assign geographical coordinates to them. This paper presents an architecture for multimodal geocoding that exploits both visual and textual descriptions associated with videos. This work also describes our e↵orts regarding the implementation of this architecture to demonstrate its applicability. Conducted experiments show how our multimodal approach enhances the results compared to relying on a single modality.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multimedia multimodal geocoding

Pedronette

Almeida

et al. 2012

Proceedings of the 20th International Conference on Advances in Geographic Information Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…), and the need to annotate the existing images with the keywords that can apply to them. Among the proposals based on visual examples, which are content-based image retrieval techniques (based on the analysis of different types of visual or textual features [20,21,22]), we can distinguish several approaches:…”

Section: Related Workmentioning

confidence: 99%

Real-time selection of video streams for live TV broadcasting based on Query-by-Example using a 3D model

Yus

Ilarri

Mena

2013

Multimed Tools Appl

View full text Add to dashboard Cite

The emergence of low-cost cameras with nearly professional features in the consumer market represents a new important source of video information. For example, using an increasing number of these cameras in live TV broadcastings enables obtaining varied contents without affecting the production costs. However, searching for interesting shots (e.g., a certain view of a specific car in a race) among many video sources in real-time can be difficult for a Technical Director (TD). So, TDs require a mechanism to easily and precisely represent the kind of shot they want to obtain abstracting them from the need to be aware of all the views provided by the cameras.In this paper we present our proposal to help a TD to visually define, using an interface for the definition of 3D scenes, an interesting sample view of one or more objects in the scenario. We recreate the views of the cameras in a 3D engine and apply 3D geometric computations on their virtual view, instead of analyzing the real images they provide, to enable an efficient and precise realtime selection. Specifically, our system computes a similarity measure to rank the candidate cameras. Moreover, we present a prototype of the system and an experimental evaluation that shows the interest of our proposal.

show abstract

“…Dessa forma, se o conjunto inicial de resultados apresenta imagens relevantes, a tendênciaé que o usuário possa fornecer informação de qualidade para o sistema e, assim, os resultados ao longo das iterações subsequentes sejam mais satisfatórios [Calumby et al 2017]. Por outro lado, abordagens tradicionais de recuperação de imagens produzem resultados baseados no cômputo de similaridade apenas entre pares de imagens, deixando de explorar a informação existente nas relações entre elas [Pedronette et al 2014]. Alternativamente,é possível combinar técnicas de re-ranqueamento com a realimentação de relevância, a fim de propagar as melhorias na eficácia dos rankings iniciais ao longo das iterações de feedback.…”

Section: Introductionunclassified

Refinamento do Conjunto Inicial de Resultados baseado em Contexto para Recuperação Interativa de Imagens

Filho¹,

Calumby

2019

Anais Do XXXIV Simpósio Brasileiro De Banco De Dados (SBBD 2019)

Self Cite

View full text Add to dashboard Cite

Este trabalho propõe a exploração de informações contextuais para refinamento do conjunto inicial de resultados em sistemas de recuperação interativa de imagens. Este método baseado em contexto difere das abordagens tradicionais, pois considera a rica informação presente nas relações entre múltiplas imagens, ao invés de realizar o cômputo de similaridade apenas entre pares de imagens. Neste trabalho, realizou-se uma avaliação experimental da eficácia desta técnica em diferentes cenários de busca na Web. Os resultados mostraram que o método avaliado foi capaz aprimorar significativamente a eficácia da recuperação, especialmente quanto aplicado em conjunto com medidas de similaridade de maior poder distintivo.

show abstract

Using contextual spaces for image re-ranking and rank aggregation

Cited by 14 publications

References 32 publications

Multimedia multimodal geocoding

Multimedia multimodal geocoding

Real-time selection of video streams for live TV broadcasting based on Query-by-Example using a 3D model

Refinamento do Conjunto Inicial de Resultados baseado em Contexto para Recuperação Interativa de Imagens

Contact Info

Product

Resources

About