A Statistical Model for General Contextual Object Recognition

By Peter Carbonetto, Nando de Freitas, Kobus Barnard. European Conference on Computer Vision, 2004

310 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7925221db50d93142cb5e5a4e31d6b72b2c5af8b

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Geometric context from a single image (2005, background): “Other researchers have exploited local contextual information using random field frameworks [16, 2, 11] and other representations (e.”
Objects in Context (2007, background): “Classes (i, ii, iv, and v) have been addressed fairly well in the models proposed by the computer vision community [2] [5] [23].”
Beyond Actions: Discriminative Models for Contextual Group Activities (2010, unknown): “Some work clearly demonstrates that contextual information could improve the performance of weak local detectors [19, 39, 30, 5, 45, 51].”
Learning Spatial Context: Using Stuff to Find Things (2008, methodology): “Another approach to modeling spatial relationships is to use a Markov Random Field (MRF) or variant (CRF,DRF) [14, 15] to encode the preferences for certain spatial relationships.”
Object categorization using co-occurrence, location and appearance (2008, methodology): “Most recent methods incorporate co-ocurrence of high level features to enforce contextual constraints [4, 18]; information from an external knowledge base may be used instead of learned cooccurences [18].”
80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition (2008, methodology): “[8] learn models using both textual and visual cues.”
Towards total scene understanding: Classification, annotation and segmentation in an automatic framework (2009, methodology): “Our work is also related to a family of models called ‘pictures and words’ models for images and annotations [1, 6, 5, 3]4 None of these models are capable of simultaneously performing image classification, annotation and segmentation.”
An empirical study of context in object detection (2009, methodology): “The classic trick of increasing the size of a scanning-window detector to include surrounding pixels [5, 41] is one simple application, as are more involved MRF/CRF-based methods, such as [4, 20, 35].”
Contextualizing Object Detection and Classification (2015, background): “Index Terms— Object classiﬁcation, object detection, context modeling Ç 1 I NTRODUCTION R ECOGNIZING objects in an image requires combining many different signals from the raw image data.”
The Visual Extent of an Object (2011, methodology): “These include Local Pixel Context (Carbonetto et al. 2004; Dalal and Triggs 2005; Fulkerson et al. 2009; Gould et al. 2009; Shotton et al. 2009), 2D scene gist context (Oliva and Torralba 2001), 3D geometric context (Hoiem et al. 2008; Nedovi´c and Smeulders 2010), and semantic context (Malisiewicz…”
Supervised Learning of Semantic Classes for Image Annotation and Retrieval (2007, methodology): “More recently, there has been an effort to solve the problem in greater generality by resorting to unsupervised learning [3], [4], [8], [12], [13], [15], [21], [31].”
Why Can't I Dance in the Mall? Learning to Mitigate Scene Bias in Action Recognition (2019, background): “Leveraging scene context is useful for object detection [40, 7, 11, 13], semantic segmentation [35, 39, 40, 69], predicting invisible things [32], and action recognition without looking at the human [23, 54].”
Spatial Memory for Context Reasoning in Object Detection (2017, background): “Context helps image understanding! Apart from strong psychological evidence [4, 37, 64, 65] that context is vital for humans to recognize objects, many empirical studies in the computer vision community [10, 11, 16, 22, 23, 43, 60, 62, 73, 82, 83] have also suggested that recognition algorithms can ”
Context based object categorization: A critical survey (2010, unknown): “Region level interactions have been extensively investigated in the area of context-based object categorization tasks [6,7,15,16,19,20,26,30,37] since regions follow plausible geometrical configurations.”
UvA-DARE ( Digital Academic Repository ) The visual extent of an object : suppose we know the object locations (2011, methodology): “These include Local Pixel Context (Carbonetto et al. 2004; Dalal and Triggs 2005; Fulkerson et al. 2009; Gould et al. 2009; Shotton et al. 2009), 2D scene gist context (Oliva and Torralba 2001), 3D geometric context (Hoiem et al. 2008; Nedović and Smeulders 2010), and semantic context (Malisiewicz…”
Detection Evolution with Multi-order Contextual Co-occurrence (2013, background): “High level image contexts such as semantic context [4], image statistics [27], and 3D geometric context [15], are used as well as low level image contexts, including local pixel context [5] and shape context [23].”