Combined Object Categorization and Segmentation With an Implicit Shape Model

By Bastian Leibe, Ales Leonardis, Bernt Schiele. 2004

1,031 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

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation (2020, methodology): “BBFNet [8] obtains instance segmentation results by Watershed transform [84,4] and Hough-voting [5,51].”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, background): “There are a large number of publically available databases of visual objects (Torralba et al. 2004; Agarwal et al. 2004; Leibe et al. 2004; Opelt et al. 2006b; Everingham et al. 2006; Fei-Fei et al. 2004, 2007; Griffin et al. 2006; Carmichael and Hebert 2004; Li and Shapiro 2002; LeCun et al. 2004; ”
Synthetic Data for Text Localisation in Natural Images (2016, neutral): “While this construction may sound abstract, it is actually a common one, implemented for example by Implicit Shape Models (ISM) [28] and Hough voting [16].”
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (2019, methodology): “Additionally, our method bears a similarity to Hough-Voting-based methods [4, 39, 21, 5] and recent works by Kendall et al.”
Recognition using regions (2009, background): “Here, we are working in a long-standing tradition in computer vision [8, 3, 21, 20, 27, 24].”
50 Years of object recognition: Directions forward (2013, methodology): “Leibe, Schiele and Leonardis [178], [198], [199] model objects using a constellation of appearance parts to achieve simultaneous recognition and segmentation.”
Human activities recognition using depth images (2013, methodology): “To localize the i activity, we apply the boosted ensemble Hi [·] on all windows of the test video, and employ the powerful mean shift mode estimation technique [7] on the confidence measure of each window, similar to [16].”
Learning object categories from Google's image search (2005, background): “Examples range from 50 images (with segmentation) [15], through hundreds (with no segmentation) [10], to thousands of images [14, 23].”
Cost-Sensitive Boosting (2011, methodology): “Both ideas have been explored in detail in the literature, with classifiers that explicitly segment the object to detect [51], [48], [55], [49], [56], learn configurations of its parts [53], [50] or both [48], [49].”
Detecting Partially Occluded Objects with an Implicit Shape Model Random Field (2012, background): “The first approach, as proposed in [9], is based on applying mean shift over the voting space to estimate the probability density for the correct object lo-”
Discriminative Models for Multi-Class Object Layout (2009, methodology): “Our algorithm for optimizing (1) is analogous to greedy algorithms traditionally used for NMS [16].”
Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes (2007, methodology): “In this way, we differ from the shape based segmentation works in [4, 31, 16] and classification works in [1, 18, 17, 11, 5].”
Layered object detection for multi-class segmentation (2010, neutral): “Early approaches bias a segmentation engine using the output of object models [27, 17], while others iterate between bottom-up and top-down cues [14, 15, 23].”
The Pascal Visual Object Classes Challenge: A Retrospective (2014, background): “This gener-alises the problem of non-maximum suppression for a single predictor (see e.g. Dalal and Triggs, 2005; Viola and Jones, 2004; Felzenszwalb et al, 2010; Leibe et al, 2004) to the output of multiple predictors.”