Object Detection by Contour Segment Networks

By Vittorio Ferrari, Tinne Tuytelaars, Luc Van Gool. European Conference on Computer Vision, 2006

344 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/339c13bfe3371a71ab486381721dbb689ff415ab

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

Matching Local Self-Similarities across Images and Videos (2007, background): “, [6]) or proximity of corresponding extracted edges (e.”
Shape discovery from unlabeled image collections (2009, methodology): “Spectral clustering from the initial affinities provides candidate object clusters.”
Active skeleton for non-rigid object detection (2009, methodology): “Recent approaches in the literature can be roughly divided into: (1) image appearance-based [9, 31]; (2) shape-driven [5, 16, 23, 4]; (3) and mixture of shape and appearance models [22, 32, 33].”
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs (2016, background): “Object proposal results on ETHZ Shape Classes [12].”
Boundary Detection Benchmarking: Beyond F-Measures (2013, background): “Many other works such as [21, 10, 3] also included pB (or gPB) boundary intensity in their feature design.”
Fast directional chamfer matching (2010, methodology): “In [10], a contour segment network framework is described where shape matching is formulated as finding paths on the network similar to model outlines.”
Recent advances and trends in visual tracking: A review (2011, background): “Ferrari et al. [18] used the network of contour segments to represent the shape of an object in order to detect object in cluttered images.”
Discriminatively Trained Sparse Code Gradients for Contour Detection (2012, background): “Contours and segmentations have also seen extensive uses in shape matching and object recognition [8] [9].”
A stochastic graph grammar for compositional object representation and recognition (2009, methodology): “However in contrast to the outlined-templates used in [28], we use templates that have flexible topologies and are full of intra-contour structures.”
Large scale mining and retrieval of visual data in a multimodal context (2008, methodology): “, 2006] are used as negative test set (as done for object detection from hand-drawings by [Ferrari et al., 2006]).”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, neutral): “For example the ETHZ dataset [25] contains 5 different classes (namely ‘logo’, ‘bottle’, ‘giraffe’, ‘mug’ and ‘swan’), which are characterized by specific shapes.”
Hierarchical Matching of Deformable Shapes (2007, methodology): “To test our matching algorithm on cluttered images, we ran experiments on a set of 80 images of swans and bottles from the ETHZ dataset [11].”
Recognition using regions (2009, background): “[12]) consists of ﬁve distinctive shape categories (ap-plelogos, bottles, giraffes, mugs and swans) in a total of 255 images.”
Feature representation for statistical-learning-based object detection: A review (2015, background): “The shape features such as shape context [47], kAS [94][52] and shape tokens [97] are all based on geometric measurement.”