Robust Object Detection with Interleaved Categorization and Segmentation

By Bastian Leibe, Ales Leonardis, Bernt Schiele. 2008

1,081 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Non-maximum Suppression (2017, background): “Hough voting establishes correspondences between detections and the image evidence supporting them, which can avoid overusing image content for several detections [15, 1, 14, 34].”
The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, neutral): “Earlier methods relied on Hough voting [36, 57].”
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (2017, methodology): “This approach is inspired by [28] which identifies instances using Hough votes from object parts.”
Bridging Category-level and Instance-level Semantic Image Segmentation (2016, background): “Note that the above process has some connections with the generalized Hough transform based approaches to object detection and segmentation [19], and that predicting bounding-boxes is not an indispensable component but a trivial implementation of maxima searching in our proposed method.”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “Like all its “probabilistic Hough transform” predecessors we know of [3, 31, 33], however, it lacks a proper probabilistic interpretation.”
Robust tracking-by-detection using a detector confidence particle filter (2009, methodology): “Sticking to the detectors originally used with these sequences, we employ the ISM detector [15] for ETH Central, TUD crossing, and UBC Hockey, and the HOG detector [7] for i-Lids and Soccer.”
On Detection of Multiple Object Instances Using Hough Transforms (2010, methodology): “Notably, the new model can reuse the training procedures and the vote representations developed in previous works on Hough-based detection, such as Implicit Shape models [3] or Hough forests [5].”
Robust Multiperson Tracking from a Mobile Platform (2009, background): “Human detection has reached an impressive level [10], [16], [30], [53], [54], [57], with many systems also being able to estimate the silhouettes of the detected pedestrians [19], [30], [48], [58].”
Dense interest points (2010, background): “Later, the same interest point detectors have also been applied successfully in the context of categorylevel object recognition, scene classification and image understanding (e.g. [7, 9, 19]).”
Opening up Open World Tracking (2021, background): “Closed-world multi-object tracking benchmarks [16,18,24] and methods [7,40,78] focus on tracking object classes that belong to a predefined set of frequently observed classes.”
Multi-view traffic sign detection, recognition, and 3D localisation (2011, background): “The vast majority works from a single image [6, 1, 9].”
Object Detection and Tracking for Autonomous Navigation in Dynamic Environments (2010, methodology): “Independently, Leibe et al. (2007a) introduced a tracking framework in which a redundant set of candidate trajectories is generated online in each time step and is pruned to a consistent subset using statistical model selection.”
Hough Regions for Joining Instance Localization and Segmentation (2012, methodology): “We compared our method to the Implicit Shape Model (ISM) [5], which also provides segmentations for each detected instance.”
Fast PRISM: Branch and Bound Hough Transform for Object Class Detection (2011, methodology): “Modified GMM. Contrary to the ISM (Leibe et al. 2008), we are not forced to use densities pc(I).”
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles (2008, methodology): “Our basic mathematical tool is a model selection framework, as introduced in [32] and adapted in [28].”
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, methodology): “Deformable models of various types are widely used to model object classes for detection tasks, including several kinds of deformable template models [8, 9] and a variety of part-based models [1, 10, 22, 20, 23, 27, 42].”
Part-based clothing segmentation for person retrieval (2011, methodology): “Our approach is probably most similar to the segmentation step of the Implicit Shape Model (ISM) [13].”