Multiscale Categorical Object Recognition Using Contour Fragments

By Jamie Shotton, Andrew Blake, Roberto Cipolla. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

399 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/bc61994bf24fe751c786ea49c3d7645cdfc4732c

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

Image colorization using similar images (2012, background): “We note that these matchings are found based solely on image features and thus could be unreliable at image regions where features cannot be reliably extracted [16] (e.g. at regions corresponding to object boundaries).”
Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection (2019, background): “Edge detection is a recurrent task required for several classical computer vision processes (e.g., segmentation [39], image recognition [38, 30]), or even in the modern tasks such as image-to-image translation [41], photo sketching [18] and so on.”
Human detection from images and videos: A survey (2016, methodology): “Note that the method in [143] can be considered as a special case of the proposed method (marked as (4.”
Multiple Viewpoint Recognition and Localization (2010, neutral): “For a particular window in the image, the edges are compared to a scaled version of the boundary contour using a version of oriented chamfer matching [21], and this distance is represented as v .”
Learning Modulated Loss for Rotated Object Detection (2019, background): “Object detection is an important and fundamental task in computer vision, and over the decades it has experienced a switch from traditional machine learning methods [1, 2, 3, 4] to deep learning methods.”
Sketch-based manga retrieval using manga109 dataset (2015, methodology): “Among them, contour-based object localization methods [32], [33] are closely related to our manga problem because an object is represented by its contour.”
Shape discovery from unlabeled image collections (2009, methodology): “We propose a shape discovery method in which local appearance (patch) matches serve to anchor the surrounding edge fragments, yielding a more reliable affinity function for images that accounts for both shape and appearance.”
Fast directional chamfer matching (2010, background): “There exist several new variants of chamfer matching mainly to improve the cost function using orientation information [11, 16].”
Class-specific Hough forests for object detection (2009, methodology): “We used the training-testing split (100 horse images and 100 background image for training, 228 horse images and 228 background images for testing) as suggested in [24].”
Learning to localize detected objects (2012, methodology): “Our experiments show that, even without head annotations, changing one training parameter can yield similar improvements.”
Detecting Object Boundaries Using Low-, Mid-, and High-level Information (2007, background): “However, despite some progress made in this direction [10,11,33,39], the problem remains unsolved.”
From a Set of Shapes to Object Discovery (2010, methodology): “matching results of Oriented Chamfer Distance [2], and other columns show DTW results.”
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].”