A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes

By Christian Wojek, Bernt Schiele. 2008

141 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Pixelwise Instance Segmentation with a Dynamically Instantiated Network (2017, methodology): “This detection potential is similar to the one previously proposed by [25], [41], [45] and [48], but formulated for the differentiable mean field inference algorithm.”
Higher Order Conditional Random Fields in Deep Neural Networks (2015, methodology): “Numerous improvements to this model were subsequently proposed including: densely connected pairwise potentials facilitating interactions between all pairs of image pixels [24], formulating higher order potentials defined over cliques larger than two nodes [21,27] in order to capture more context, m”
Information Fusion on Oversegmented Images: An Application for Urban Scene Understanding (2013, methodology): “We used the Walsh-Hadamard transform to encode the texture as proposed in [10], and a bag-of-words [11] approach to learn models.”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, background): “Recent work has shown that with modern computer vision tools, visual environment modeling for robot navigation is becoming possible (Wojek and Schiele 2008; Ess et al. 2009a).”
Multimodal information fusion for urban scene understanding (2016, methodology): “We used the Walsh–Hadamard transform to encode the texture, as proposed by Wojek and Schiele [34].”
3D Traffic Scene Understanding From Movable Platforms (2014, methodology): “Following [61], we divide the last image of each sequence into patches of size ns ×ns pixels and classify them into the categories road, background and sky.”
A new performance measure and evaluation benchmark for road detection algorithms (2013, background): “Consequently, many approaches put higher emphasis on appearance cues such as the color and texture of the road area [5], [6], [7], [8], [9], [10], [11], [12].”
What, Where and How Many? Combining Object Detectors and CRFs (2010, methodology): “To our knowledge, the only other existing approaches that attempt to jointly estimate segmentation and detection in one optimization framework are the works of [6,18].”
Region-based Segmentation and Object Detection (2009, unknown): “However, these models either us a different representation for object and non-object regions [23] or rely on a pixel-level represe ntation [16].”
Stixmantics: A Medium-Level Model for Real-Time Semantic Scene Understanding (2014, methodology): “(semantic) segmentation approaches, such as [6,20,28,37,44] among many others, operate in a bottom-up fashion and usually do not recover an object-level scene description.”
Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation (2012, methodology): “A more holistic approach to combine detection and segmentation was proposed in [6, 25], defining the joint inference within a CRF framework.”
Resolving Language and Vision Ambiguities Together: Joint Segmentation & Prepositional Attachment Resolution in Captioned Scenes (2016, background): “Recent works have looked at both joint [10, 11, 16, 21, 29, 36, 42, 43, 53, 59, 63, 65] and sequential/cascaded [12, 25, 26, 28, 38, 41] reasoning over different perception modules (e.”
D Traffic Scene Understanding from Movable Platforms (2013, methodology): “Following [61], we IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE This article has been accepted for publication in a future issue of this journal, but has not been fully edited.”
Multi-view traffic sign detection, recognition, and 3D localisation (2011, unknown): “In a similar vein, Wojek and Schiele [20] went further in coupling object detection and scene labeling approaches.”
Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017, background): “In particular, Wojek & Schiele (2008b) show that AdaBoost and linear SVM perform roughly the same if enough features are given.”
Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks (2019, methodology): “As an energy-minimization model, conditional random ﬁeld (CRF) is often used for solving multiple association tasks, and is widely applied in trafﬁc scene understanding [4].”
Learning Where to Classify in Multi-view Semantic Segmentation (2014, background): “Others focused on better graphical models [19, 20] or including detectors [7, 21].”
Hough Regions for Joining Instance Localization and Segmentation (2012, background): “Wojek and Schiele [13] couple scene and detector information, but due to the inherent complexity the problem is not solvable in an exact manner.”