Visual Language Model for Scene Recognition

Pham, Trong-Ton; Maisonnasse, Loïc; Mulhem, Philippe; Gaussier, Éric

doi:10.1142/9789814277563_0008

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have applied a visual language modeling framework for the Robotvision task. This generative model is quite standard in the Information Retrieval field, and already lead to good results for visual scene recognition [10]. Before explaining in detail the language modeling approach, we fix some elements related to the feature extractions of images.…”

Section: Image Representationmentioning

confidence: 99%

“…In the case of [4], the kernel used only considers the three closest regions to a given region. In [10], we have presented the image as a probabilistic graph which allows capturing the visual complexity of an image. Images are represented by a set of weighted concepts, connected through a set of directed associations.…”

Section: Visual Language Modelingmentioning

confidence: 99%

“…Language models for text retrieval where proposed ten years ago, and behave very well when all the data cannot be directly extracted from the corpus. We have already proposed such application for image retrieval in [10], achieving very good results. We decided to focus on this challenging task represented by the Robotvision task in CLEF 2009.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MRIM-LIG at ImageCLEF 2009: Robotvision, Image Annotation and Retrieval Tasks

Pham

Maisonnasse

Mulhem

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper describes mainly the experiments that have been conducted by the MRIM group at the LIG in Grenoble for the the ImageCLEF 2009 campaign, focusing on the work done for the Robotvision task. The proposal for this task is to study the behaviour of a generative approach inspired by the language model of information retrieval. To fit with the specificity of the Robotvision task, we added post-processing in a way to tackle with the fact that images do belong only to several classes (rooms) and that image are not independent from each others (i.e., the robot cannot in one second be in three different rooms). The results obtained still need improvement, but the use of such language model in the case of Robotvision is showed. Some results related to the Image Retrieval task and the Image annotation task are also presented.

show abstract

Section: Image Representationmentioning

confidence: 99%

Section: Visual Language Modelingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MRIM-LIG at ImageCLEF 2009: Robotvision, Image Annotation and Retrieval Tasks

Pham

Maisonnasse

Mulhem

et al. 2010

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Indeed, these three phrases are clearly distinct from each other. They can be associated with the three layers of a classical paradigm in machine vision of Marr as introduced in chapter 2: the processing layer (1), the mapping layer (2), the high-level interpretation layer (3). Our contributions are mainly related to the graph modeling and graph retrieval problem.…”

mentioning

confidence: 99%

Modèle de graphe et modèle de langue pour la reconnaissance de scènes visuelles

Pham¹,

Maisonnasse²,

Mulhem³

et al. 2010

Document numérique

Self Cite

View full text Add to dashboard Cite

Content-based image indexing and retrieval (CBIR) system needs to consider several types of visual features and spatial information among them (i.e., different point of views) for better image representation. This thesis presents a novel approach that exploits an extension of the language modeling approach from information retrieval to the problem of graph-based image retrieval. Such versatile graph model is needed to represent the multiple points of views of images. This graph-based framework is composed of three main stages:Image processing stage aims at extracting image regions from the image. It also consists of computing the numerical feature vectors associated with image regions.Graph modeling stage consists of two main steps. First, extracted image regions that are visually similar will be grouped into clusters using an unsupervised learning algorithm. Each cluster is then associated with a visual concept. The second step generates the spatial relations between the visual concepts. Each image is represented by a visual graph captured from a set of visual concepts and a set of spatial relations among them.Graph retrieval stage is to retrieve images relevant to a new image query. Query graphs are generated following the graph modeling stage. Inspired by the language model for text retrieval, we extend this framework for matching the query graph with the document graphs from the database. Images are then ranked based on the relevance values of the corresponding image graphs.Two instances of the visual graph model have been applied to the problem of scene recognition and robot localization. We performed the experiments on two image collections: one contained 3,849 touristic images and another composed of 3,633 images captured by a mobile robot. The achieved results show that using visual graph model outperforms the standard language model and the Support Vector Machine method by more than 10% in accuracy.

show abstract

Geographic Scene Understanding of High-Spatial-Resolution Remote Sensing Images: Methodological Trends and Current Challenges

Liu

Huang

2022

Applied Sciences

View full text Add to dashboard Cite

As one of the primary means of Earth observation, high-spatial-resolution remote sensing images can describe the geometry, texture and structure of objects in detail. It has become a research hotspot to recognize the semantic information of objects, analyze the semantic relationship between objects and then understand the more abstract geographic scenes in high-spatial-resolution remote sensing images. Based on the basic connotation of geographic scene understanding of high-spatial-resolution remote sensing images, this paper firstly summarizes the keystones in geographic scene understanding, such as various semantic hierarchies, complex spatial structures and limited labeled samples. Then, the achievements in the processing strategies and techniques of geographic scene understanding in recent years are reviewed from three layers: visual semantics, object semantics and concept semantics. On this basis, the new challenges in the research of geographic scene understanding of high-spatial-resolution remote sensing images are analyzed, and future research prospects have been proposed.

show abstract

Visual Language Model for Scene Recognition

Cited by 3 publications

References 14 publications

MRIM-LIG at ImageCLEF 2009: Robotvision, Image Annotation and Retrieval Tasks

MRIM-LIG at ImageCLEF 2009: Robotvision, Image Annotation and Retrieval Tasks

Modèle de graphe et modèle de langue pour la reconnaissance de scènes visuelles

Geographic Scene Understanding of High-Spatial-Resolution Remote Sensing Images: Methodological Trends and Current Challenges

Contact Info

Product

Resources

About