An Overview of Semantics Processing in Content-Based 3D Model Retrieval

Gao, Boyong; Zheng, Hao; Zhang, Sanyuan

doi:10.1109/aici.2009.482

Cited by 10 publications

(8 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A survey of three typical semantics processing techniques (relevance feedback, machine learning, and ontology) is presented in [71]. Typical semantics based 3D retrieval approaches include relevance feed back [72], semantic labeling [73], neural networks [74], supervised [75 78] or semi supervised [79 81] learning, boosting [82], proto types [83], autotagging [84], spectral clustering [85], manifold ranking [86], semantic tree [87], feature dimension reduction [88], semantic subspaces [89], class distances [54], semantics annotation of 3D models [90], semantic correspondences [91], and sparse structure regularized ranking [92].…”

Section: Semantics Based 3d Model Retrieval Techniquesmentioning

confidence: 99%

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

et al. 2015

Computer Vision and Image Understanding

120

View full text Add to dashboard Cite

a b s t r a c tLarge scale 3D shape retrieval has become an important research direction in content based 3D shape retrieval. To promote this research area, two Shape Retrieval Contest (SHREC) tracks on large scale com prehensive and sketch based 3D model retrieval have been organized by us in 2014. Both tracks were based on a unified large scale benchmark that supports multimodal queries (3D models and sketches). This benchmark contains 13680 sketches and 8987 3D models, divided into 171 distinct classes. It was compiled to be a superset of existing benchmarks and presents a new challenge to retrieval methods as it comprises generic models as well as domain specific model types. Twelve and six distinct 3D shape retrieval methods have competed with each other in these two contests, respectively. To measure and compare the performance of the participating and other promising Query by Model or Query by Sketch 3D shape retrieval methods and to solicit state of the art approaches, we perform a more comprehensive comparison of twenty six (eighteen originally participating algorithms and eight additional state of the art or new) retrieval methods by evaluating them on the common benchmark. The benchmark, results, and evaluation tools are publicly available at our websites

show abstract

Section: Semantics Based 3d Model Retrieval Techniquesmentioning

confidence: 99%

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

et al. 2015

Computer Vision and Image Understanding

120

View full text Add to dashboard Cite

show abstract

“…Em outros overviews relacionados ao assunto, como em [Yubin et al 2007], [Qin et al 2008] e [Gao et al 2009] a abordagem dada era focada em extratores e não houve uma metodologia para a revisão. Na presente RS pretendemos analisar, além dos descritores, outros pontos presentes no processo de recuperação por conteúdo, e também, atualizar a literatura sobre novas técnicas existentes.…”

Section: Introductionunclassified

O estado da arte em Recuperaçãoo de modelos tridimensionais por conteúdo através de uma Revisão Sistemática

Bergamasco¹,

Nunes²

2012

Anais Do VIII Simpósio Brasileiro De Sistemas De Informação (SBSI 2012)

View full text Add to dashboard Cite

O avanço da tecnologia possibilita a construção de Sistemas de Informação mais complexos. Uma das abordagens que tem sido desenvolvida nesse sentido e o uso de ambientes tridimensionais. Devido ao grande vo-lume de dados nas bases de imagens é necessária a implementção de métodos eficientes para efetuar a busca desses modelos. Uma das tecnicas existentes é a recuperação baseada por conteúdo, que possui diversos algoritmos para extração de características e usa funções de similaridade para comparar objetos diferentes. Este artigo apresenta resultados de uma Revisao Sistemática realizada sobre este tema, a fim de analisar as técnicas, extratores, funções de similaridade e banco de dados usados.

show abstract

“…Notably, the main interest of such methods is related to the possibility of matching 3D models with 2D objects identified (e.g., with the help of some segmentation techniques) in still images or videos. In particular, such an approach might bring interesting and original solutions to the well-known problem of semantic gap 23,24 , which can be synthesized as follows. Given an object or a set of objects detected with the help of computer vision techniques from still images or videos, how can we interpret its meaning?…”

Section: Introductionmentioning

confidence: 99%

“…Existing approaches make intensively use of machine learning techniques 24 , in order to bridge the gap between rough pixels and semantically meaningful interpretations of the image content. In this context, 3D modelling offers an interesting and complementary axis of research.…”

Section: Introductionmentioning

confidence: 99%

An overview of view-based 2D/3D indexing methods

2010

View full text Add to dashboard Cite

This paper proposes a comprehensive overview of state of the art 2D/3D, view-based indexing methods. The principle of 2D/3D indexing methods consists of describing 3D models by means of a set of 2D shape descriptors, associated with a set of corresponding 2D views (under the assumption of a given projection model). Notably, such an approach makes it possible to identify 3D objects of interest from 2D images/videos. An experimental evaluation is also proposed, in order to examine the influence of the number of views and of the associated viewing angle selection strategies on the retrieval results. Experiments concern both 3D model retrieval and image recognition from a single view. Results obtained show promising performances, with recognition rates from a single view higher then 66%, which opens interesting perspectives in terms of semantic metadata extraction from still images/videos.

show abstract

An Overview of Semantics Processing in Content-Based 3D Model Retrieval

Cited by 10 publications

References 42 publications

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

A comparison of 3D shape retrieval methods based on a large-scale benchmark supporting multimodal queries

O estado da arte em Recuperaçãoo de modelos tridimensionais por conteúdo através de uma Revisão Sistemática

An overview of view-based 2D/3D indexing methods

Contact Info

Product

Resources

About