A Boundary-Fragment-Model for Object Detection

By Andreas Opelt, Axel Pinz, Andrew Zisserman. European Conference on Computer Vision, 2006

395 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1ca9da67e2c427e59a5a54c9b31157e6b8b4843e

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

Citations in the corpus

A Review of Computer Vision Techniques for the Analysis of Urban Traffic (2011, methodology): “The last section considers tracking, which can equally be applied after both classification methods.”
Crisp Boundary Detection Using Pointwise Mutual Information (2014, methodology): “Object boundary cues have been used to aid in segmentation [1,2,3], object detection and recognition [4,5], and recovery of intrinsic scene properties such as shape, reflectance, and illumination [6].”
Look at Boundary: A Boundary-Aware Face Alignment Algorithm (2018, methodology): “It has been proved efﬁcient in vision tasks as segmentation [32, 27, 22] and object detection [36, 50, 37].”
Shape discovery from unlabeled image collections (2009, methodology): “Methods using Houghstyle voting with patches [16] or discriminative edge fragments [21] can backproject segmentation boundaries learned from labeled training examples to predict new objects’ outlines.”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, background): “bag of words [28], edge fragments [26], multiscale-oriented filters [24]).”
Feature representation for statistical-learning-based object detection: A review (2015, background): “There are other category-specific geometrical primitives for shape representation, referred as contour fragment [59][95] and boundary fragment [57].”
Recognition using regions (2009, background): “Here, we are working in a long-standing tradition in computer vision [8, 3, 21, 20, 27, 24].”
A survey on face detection in the wild: Past, present and future (2015, neutral): “Forinstance,in[94]multi- pleboundaryfragmentstoweakclassifierswerecomposedandformedastrong"boundary-fragment-model"detector usingboosting.”
50 Years of object recognition: Directions forward (2013, background): “[238] present a boundary fragment model approach for object localization in images.”
Person Re-identification by Descriptive and Discriminative Classification (2011, background): “, Haar-like [21], Edge Orientation Histograms [12], or boundary fragments [15] have been introduced for the application with boosting for feature selection.”
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection (2011, methodology): “Indeed, object class detectors based on ISM’s idea have become increasingly popular (Liebelt et al. 2008; Opelt et al. 2006; Maji and Malik 2009; Gall and Lempitsky 2009; Chum and Zisserman 2007).”
Incremental learning of object detectors using a visual shape alphabet (2006, methodology): “Our object model is similar to those of [ 13 , 14, 15] and is briefly reviewed in section 2.”
Deepstrip: High-Resolution Boundary Refinement (2020, background): “Boundary detection is a well-studied problem and fundamental for human recognition [28, 9].”
Evolutionary Hough Games for coherent object detection (2012, neutral): “For example, some methods use interest points [3], dense sampling [4], boundary fragments [6] or edge groups [7].”
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection (2014, methodology): “Contour detection is typically considered a low-level problem, and used to aid higher-level tasks such as object detection [2, 3, 27, 21].”
Finding People in Images and Videos (2006, methodology): “Some well known approach to object detection are described in Papageorgiou and Poggio [2000], Mohan et al.”
Object detection using a max-margin Hough transform (2009, methodology): “Combined with verification step, this approach has been used successfully for detection of objects [18, 22 ].”
Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection (2013, background): “While numerous detection approaches [5, 11, 7] utilize such features directly, other papers learn edge-based features [27, 38, 21] or class-speciﬁc edges [23, 18] using object level supervision.”