Semantic Image Segmentation and Object Labeling

Athanasiadis, Thanos; Mylonas, Phivos; Avrithis, Yannis; Kollias, Stefanos

doi:10.1109/tcsvt.2007.890636

Cited by 95 publications

(49 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Semantic video classification is one promising solution to bridge the semantic gap [1,2,4,5,12,14,33,41,42,44,51,52], but its performance largely depends on two inter-related issues: (1) suitable algorithms for video content representation and feature extraction; (2) effective algorithms for video classifier training.…”

Section: Bridging Semantic Gapmentioning

confidence: 99%

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Luo

Fan

Satoh

et al. 2008

Signal Processing: Image Communication

View full text Add to dashboard Cite

In this paper, we have developed a novel scheme to achieve more effective analysis, retrieval and exploration of large-scale news video collections by performing multi-modal video content analysis and synchronization. First, automatic keyword extraction is performed on news closed captions and audio channels to detect the most interesting news topics (i.e., keywords for news topic interpretation), and the associations among these news topics (i.e., contextual relationships among the news topics) are further determined according to their co-occurrence probabilities. Second, visual semantic items, such as human faces, text captions, video concepts, are extracted automatically by using our semantic video analysis techniques. The news topics are automatically synchronized with the most relevant visual semantic items. In addition, an interestingness weight is assigned for each news topic to characterize its importance. Finally, a novel hyperbolic visualization scheme is incorporated to visualize large-scale news topics according to their associations and interestingness. With a better global overview of large-scale news video collections, users can specify their queries more precisely and explore large-scale news video collections interactively. Our experiments on large-scale news video collections have provided very positive results.

show abstract

Section: Bridging Semantic Gapmentioning

confidence: 99%

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Luo

Fan

Satoh

et al. 2008

Signal Processing: Image Communication

View full text Add to dashboard Cite

show abstract

“…A mapping between the keywords and the visual blobs is performed using a method based on Expectation Maximization. The rest of the literature [15,26,32,12,2] noticeably differs from the original work by Duygulu et al in the sense that the models built try to exploit the maximum of information that can be extracted from the image: not only low level features (color, texture, etc. ), but also local contextual relationships between pixels or image segments, location and even global relevance estimates.…”

mentioning

confidence: 99%

“…Galleguillos et al [12] have shown that introducing contextual information about the co-occurrences and the relative location of image regions with local appearance-based features improves the global labellin. Athanasiadis et al [2] define a framework for simultaneous image segmentation and object labellin operating at the semantic level. They represent the contextual information as an ontological taxonomy of the set of possible semantic labels and employ fuzzy algebra to adjust the labelling of the regions given by region growing segmentation algorithms.…”

mentioning

confidence: 99%

Segmentation-based multi-class semantic object detection

Vieux

Benois-Pineau

Domenger

et al. 2010

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we study the problem of the detection of semantic objects from known categories in images. Unlike existing techniques which operate at the pixel or at a patch level for recognition, we propose to rely on the categorization of image segments. Recent work has highlighted that image segments provide a sound support for visual object class recognition. In this work, we use image segments as primitives to extract robust features and train detection models for a predefined set of categories. Several segmentation algorithms are benchmarked and their performances for segment recognition are compared. We then propose two methods for enhancing the segments classification, one based on the fusion of the classification results obtained with the different segmentations, the other one based on the optimization of the global labelling by correcting local ambiguities between neighbor segments. We use as a benchmark the Microsoft MSRC-21 image database and show that our method competes with the current state-of-the-art.

show abstract

“…with E f,b defined similarly to E f,a , with z a replaced by z b in (2). It can be shown [8] that (4) takes the form of…”

Section: The Semantically Adaptable Classifiermentioning

confidence: 99%

“…This variation follows in principle the algorithmic definition of the traditional RSST, though a few adjustments were considered necessary and were added. S-RSST aims to improve the usual oversegmentation results by incorporating region labeling in the segmentation process [2]. The modification of the traditional algorithm to S-RSST lies on the definition of the two criteria: (a) The dissimilarity criterion between two adjacent regions a and b (vertices v a and v b in the graph), based on which the graph's edges are sorted and (b) the termination criterion.…”

Section: Semantically Adaptive Image Segmentationmentioning

confidence: 99%

Semantic Adaptation of Neural Network Classifiers in Image Segmentation

Simou

Athanasiadis

Kollias

et al.

Artificial Neural Networks - ICANN 2008

Self Cite

View full text Add to dashboard Cite

Abstract. Semantic analysis of multimedia content is an on going research area that has gained a lot of attention over the last few years. Additionally, machine learning techniques are widely used for multimedia analysis with great success. This work presents a combined approach to semantic adaptation of neural network classifiers in multimedia framework. It is based on a fuzzy reasoning engine which is able to evaluate the outputs and the confidence levels of the neural network classifier, using a knowledge base. Improved image segmentation results are obtained, which are used for adaptation of the network classifier, further increasing its ability to provide accurate classification of the specific content.

show abstract

Semantic Image Segmentation and Object Labeling

Cited by 95 publications

References 25 publications

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Integrating multi-modal content analysis and hyperbolic visualization for large-scale news video retrieval and exploration

Segmentation-based multi-class semantic object detection

Semantic Adaptation of Neural Network Classifiers in Image Segmentation

Contact Info

Product

Resources

About