Groups of Adjacent Contour Segments for Object Detection

By Vittorio Ferrari, Loic Fevrier, Frédéric Jurie, Cordelia Schmid. 2008

644 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Fast Edge Detection Using Structured Forests (2014, neutral): “F”
Unsupervised Learning of Edges (2015, background): “Endowing machine vision systems with similar capabilities is of interest as edges are useful for diverse tasks such as optical flow [31], object detection [40, 13], and object proposals [39, 46, 3].”
Data-Driven Grasp Synthesis—A Survey (2013, background): “These can be, e.g., a common texture [62] or shape [63, 64], the occurrence of speciﬁc local features [65, 66] or their speciﬁc spatial constellation [67, 68].”
Discriminant Saliency, the Detection of Suspicious Coincidences, and Applications to Visual Recognition (2009, background): “For example, for objects with characteristic shapes, such as sheep or cows, the addition of contourbased features (such as adjacent contour segments [ 65 ]) should prove beneficial.”
Fast directional chamfer matching (2010, methodology): “…this problem is to utilize features that exhibit the least variability within ob- ∗Partially supported by MURI from the Office of Naval Research under the Grant N00014 − 08−I−0638. ject classes and across imaging conditions together with a similarity measure that models the maximum invariances.”
Beyond sliding windows: Object localization by efficient subwindow search (2008, methodology): “Typically, these consist of reducing the number of necessary function evaluations by searching only over a coarse grid of possible rectangle locations and by allowing only rectangles of certain fixed sizes as candidates [7, 11, 19].”
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.”
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, background): “Non-photorealistic rendering from images and video would be boosted too, not least because highly aesthetic renderings depend critically on the level of abstraction available to algorithms.”
Structured Forests for Fast Edge Detection (2013, background): “The detection of edges is a critical preprocessing step for a variety of tasks, including object recognition [36, 12], segmentation [23, 1], and active contours [19].”
Semantic Edge Detection with Diverse Deep Supervision (2018, methodology): “2017), object detection (Ferrari et al. 2008; Maninis et al. 2017), and instance segmentation (Hayder et al.”
Boundary Cues for 3D Object Shape Recovery (2013, background): “Our ﬁndings suggest a 3D representation that incorporates interior occlusions and folds might beneﬁt such existing systems.”
50 Years of object recognition: Directions forward (2013, background): “The authors of [367] conclude their paper by comparing their object localization algorithm to the algorithm by Dalal and Triggs [335], and demonstrating that their algorithm performs favourably.”
Richer Convolutional Features for Edge Detection (2016, background): “Due to its farreaching applications in many high-level applications including object detection [2], [3], object proposal generation [4], [5], and image segmentation [6], [7], edge detection is a core low-level problem in computer vision.”
Detecting Object Boundaries Using Low-, Mid-, and High-level Information (2007, background): “There are other works [3,7,12,21,25,28,31] in the literature tackling similar problem.”
Object detection using a max-margin Hough transform (2009, methodology): “We use the same training and test splits used by authors of [9] for a fair comparison.”
Measuring the Objectness of Image Windows (2011, methodology): “In Section 5 we evaluate objectness on the very challenging PASCAL VOC 2007 dataset, and then show applications to aiding class-specific object detectors [11], [18], [50] in Sections 6 and 7.”
DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection (2015, background): “Accurately detecting object contours serves as the basis for many tasks, such as image segmentation [2], scene understanding [3] and object detection [17, 30, 48].”
Pixel Difference Networks for Efficient Edge Detection (2021, background): “boundaries play an important role in various higher-level computer vision tasks such as object recognition and detection [29, 11], object proposal generation [6, 54], image editing [10], and image segmentation [41, 4].”