Describing images via linguistic features and hierarchical segmentation

Castillo-Ortega, Rita; Chamorro-Martı́nez, J.; Marín, Nicolás; Sánchez, Daniel; Soto-Hidalgo, J. M.

doi:10.1109/fuzzy.2010.5584443

Cited by 17 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in D2T systems which generate texts from time series data, language tends to be simpler [8] and relevant information such as events can be clearly identified through the use of temporal expressions. In others, such as the aforementioned geographical NLG systems or visual systems in general [39], this complexity will be higher (see Fig. 13 b)).…”

Section: ) Referring Expression Generationmentioning

confidence: 99%

Fuzzy sets across the natural language generation pipeline

2016

View full text Add to dashboard Cite

We explore the implications of using fuzzy techniques (mainly those commonly used in the linguistic description/summarization of data discipline) from a natural language generation perspective. For this, we provide an extensive discussion of some general convergence points and an exploration of the relationship between the different tasks involved in the standard NLG system pipeline architecture and the most common fuzzy approaches used in linguistic summarization/description of data, such as fuzzy quantified statements, evaluation criteria or aggregation operators. Each individual discussion is illustrated with a related use case. Recent work made in the context of cross-fertilization of both research fields is also referenced.

show abstract

Section: ) Referring Expression Generationmentioning

confidence: 99%

Fuzzy sets across the natural language generation pipeline

2016

View full text Add to dashboard Cite

show abstract

“…Concepts related to low-level features like colour, texture, and shape are among the most employed in linguistic description [16], and are usually affected by fuzziness. Colour terms used as adjectives like red, vivid yellow, etc.…”

Section: Fuzzy Concepts In Visual Scenesmentioning

confidence: 99%

“…Not only properties, but regions themselves can be fuzzy as well, as they are usually defined in terms of their correspondence to properties [16]. In this sense, a fuzzy region is defined as a fuzzy subset of pixels in the image.…”

Section: Fuzzy Concepts In Visual Scenesmentioning

confidence: 99%

“…These concepts, which are themselves fuzzy even for crisp regions, have been an object of study with fuzzy techniques [22,16,23]. It is easy to see examples of concepts that are fulfilled only to some degree by objects in the image depicted in Figure 1(a), such as round shape, above (spatial relationship), in the middle (location), etc.…”

Section: Fuzzy Concepts In Visual Scenesmentioning

confidence: 99%

See 1 more Smart Citation

The Role of Graduality for Referring Expression Generation in Visual Scenes

Gatt

Marín

Portet

et al. 2016

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Referring Expression Generation (reg) algorithms, a core component of systems that generate text from non-linguistic data, seek to identify domain objects using natural language descriptions. While reg has often been applied to visual domains, very few approaches deal with the problem of fuzziness and gradation. This paper discusses these problems and how they can be accommodated to achieve a more realistic view of the task of referring to objects in visual scenes.

show abstract

“…As future work, we shall use the relations introduced here in many applications, in particular for developing image retrieval systems working with linguistic queries and flexible queries to image databases, as well as for identifying visual concepts and the automatic generation of linguistic descriptions of images on the basis of color information [20]. We will also employ these techniques for color image segmentation [21], [22].…”

Section: Definition 411mentioning

confidence: 99%

On some fuzzy relations for color information

Sánchez

Soto-Hidalgo

Chamorro-Martı́nez

et al. 2011

2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)

Self Cite

View full text Add to dashboard Cite

Abstract-In this paper we introduce several fuzzy resemblance relations between different combinations of crisp and fuzzy colors. As a starting point, we discuss about fuzzy colors and fuzzy color spaces as a way to represent color information, providing examples of conjunctive and disjunctive use of fuzzy colors for this purpose. Then we determine different types of relations measuring the degree of matching between color information of different kinds, using well known results from fuzzy sets and possibility theories. We study the particular case in which the user considers there is no resemblance between the fuzzy colors comprising the fuzzy color space under consideration. The proposal is based on definitions of fuzzy color and fuzzy color space provided by the authors in previous works.

show abstract

Describing images via linguistic features and hierarchical segmentation

Cited by 17 publications

References 35 publications

Fuzzy sets across the natural language generation pipeline

Fuzzy sets across the natural language generation pipeline

The Role of Graduality for Referring Expression Generation in Visual Scenes

On some fuzzy relations for color information

Contact Info

Product

Resources

About