A Semantic Typicality Measure for Natural Scene Categorization

By Julia Vogel, Bernt Schiele. 2004

130 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

SUN database: Large-scale scene recognition from abbey to zoo (2010, background): “There are a few exceptions to this trend – In [31], each image is graded according to different scene categories.”
SUN Database: Exploring a Large Collection of Scene Categories (2014, background): “However, the dominant view in the literature is that one image depicts one scene category (with some exceptions (Vogel and Schiele 2004; Boutell et al. 2004).”
A Big Data Analytics Method for Tourist Behaviour Analysis (2017, unknown): “Our representative photos identification is carried out in two steps: Visual Content Representation and Kernel Density Estimation Visual Content Representation: Feature descriptors for local regions are used as powerful cues in automatic natural scene recognition [70] and are robust to occlusions an”
What, where and who? Classifying events by scene and object recognition (2007, background): “A number of previous works have offered ways of recognizing scene categories [16, 22, 6].”
Salient object detection: A survey (2014, background): “n [1], ﬁxation prediction [2], [3], object importance [4]–[6], memorability [7], scene clutter [8], video interestingness [9]–[12], surprise [13], image quality assessment [14]–[16], scene typicality [17], [18], aesthetic [11] and attributes [19]. Given space limitations, this paper cannot fully exp”
Feature Learning for Image Classification Via Multiobjective Genetic Programming (2014, methodology): “In addition, the methods in [25] and [26] have also applied global features to different tasks of image classification.”
SIFT and color feature fusion using localized maximum-margin learning for scene classification (2011, background): “In recent years, local feature based methods [9-13] become more popular because of its robustness to occlusions, geometric deformation and illumination variations.”
A Bayesian hierarchical model for learning natural scene categories (2005, methodology): “It is also worth noting that 4 (coast, forest, open country and mountain) of the categories are similar to the 4 of the 6 categories reported in [17].”
Simultaneous image classification and annotation (2009, unknown): “Much previous work has explored the use of global image features for scene (or event) classification [21, 27, 26, 28, 17], and both discriminative and generative techniques have been applied to this problem.”