Using Visual Context and Region Semantics for High-Level Concept Detection

Mylonas, Ph.; Spyrou, Evaggelos; Avrithis, Yannis; Kollias, Stefanos

doi:10.1109/tmm.2008.2009681

Cited by 33 publications

(17 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…And patch can also represent rich information in an expanded area, so using it can also implement some semantic-concerned task, such as image inpainting [20] and image synthesis [21]. For visual concept application, the representation form [22], topological relations among regions [23], template of an object [24] is very important. All above works were a good start on concept acquisition, explicit representation and top-down effect of visual concept.…”

Section: How To Fulfill a More Detailed Definition Of An Object?mentioning

confidence: 99%

A Bio-Inspired Integration Method for Object Semantic Representation

Wei

2016

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

We have two motivations. Firstly, semantic gap is a tough problem puzzling almost all sub-fields of Artificial Intelligence. We think semantic gap is the conflict between the abstractness of high-level symbolic definition and the details, diversities of low-level stimulus. Secondly, in object recognition, a pre-defined prototype of object is crucial and indispensable for bi-directional perception processing. On the one hand this prototype was learned from perceptional experience, and on the other hand it should be able to guide future downward processing. Human can do this very well, so physiological mechanism is simulated here. We utilize a mechanism of classical and non-classical receptive field (nCRF) to design a hierarchical model and form a multi-layer prototype of an object. This also is a realistic definition of concept, and a representation of denoting semantic. We regard this model as the most fundamental infrastructure that can ground semantics. Here a AND-OR tree is constructed to record prototypes of a concept, in which either raw data at low-level or symbol at high-level is feasible, and explicit production rules are also available. For the sake of pixel processing, knowledge should be represented in a data form; for the sake of scene reasoning, knowledge should be represented in a symbolic form. The physiological mechanism happens to be the bridge that can join them together seamlessly. This provides a possibility for finding a solution to semantic gap problem, and prevents discontinuity in low-order structures.

show abstract

Section: How To Fulfill a More Detailed Definition Of An Object?mentioning

confidence: 99%

A Bio-Inspired Integration Method for Object Semantic Representation

Wei

2016

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

show abstract

“…An image can be derived from the meaning of its constituent named patches. So, a semantic vocabulary is obtained by manually assigning the meaningful labels to image patches [35,38].…”

Section: Related Work and Backgroundmentioning

confidence: 99%

“…In [33], Mylonas et al have proposed Fuzzy topological relations defined by domain expert in order to model real-life information such as "Part", "Specialization", "Example", "Instrument", "Location", "Patient" and "Property". However, in [35], the authors defined other relationships incorporating fuzziness in their definition. They utilized a set of relations derived from MPEG-7 such as "Similar", "Accompanier", "Part", "Component", "Specialization", "Generalization", "Example", "Location" and "Property".…”

Section: Related Work and Backgroundmentioning

confidence: 99%

A generic framework for semantic video indexing based on visual concepts/contexts detection

Elleuch

Ammar

Alimi

2014

Multimed Tools Appl

View full text Add to dashboard Cite

Providing a semantic access to video data requires the development of concept detectors. However, semantic concepts detection is a hard task due to the large intra-class and the small inter-class variability of content. Moreover, semantic concepts co-occur together in various contexts and their occurrence may vary from one to another. Thus, it is interesting to exploit this knowledge in order to achieve satisfactory performances. In this paper we present a generic semantic video indexing scheme, called SVI_REGIMVid. It is based on three levels of analysis. The first level (level1) focuses on low-level processing such as video shot boundary/ key-frame detection, annotation tools, key-points detection and visual features extraction tools. The second level (level2) aims to build the semantic models for supervised learning of concepts/contexts. The third level (level3) enriches the semantic interpretation of concepts/ contexts by exploiting fuzzy knowledge. The obtained experimental results are promising for a semantic concept/context detection process.

show abstract

“…In this Section we will use and extend the ideas presented in [10] and [11], in order to describe the visual content of a given image I i using a model vector m i . This vector will capture the relation of a given image with the region types of the visual vocabulary.…”

Section: Construction Of Model Vectorsmentioning

confidence: 99%

Using a region and visual word approach towards semantic image retrieval

Kalantidis

Spyrou

Mylonas

et al. 2010

2010 Fifth International Workshop Semantic Media Adaptation and Personalization

Self Cite

View full text Add to dashboard Cite

This paper presents a region-based approach towards semantic image retrieval. Combining segmentation and the popular Bag-of-Words model, a visual vocabulary of the most common "region types" is first constructed using the database images. The visual words are consistent image regions, extracted through a k-means clustering process. The regions are described with color and texture features, and a "model vector" is then formed to capture the association of a given image to the visual words. Opposite to other methods, we do not form the model vector based on all region types, but rather to a smaller subset. We show that the presented approach can be efficiently applied to image retrieval when the goal is to retrieve semantically similar rather than visually similar images. We show that our method outperforms the commonly used Bag-of-Words model based on local SIFT descriptors.

show abstract

Using Visual Context and Region Semantics for High-Level Concept Detection

Cited by 33 publications

References 61 publications

A Bio-Inspired Integration Method for Object Semantic Representation

A Bio-Inspired Integration Method for Object Semantic Representation

A generic framework for semantic video indexing based on visual concepts/contexts detection

Using a region and visual word approach towards semantic image retrieval

Contact Info

Product

Resources

About