A coarse-to-fine approach for fast deformable object detection

By Marco Pedersoli, Andrea Vedaldi, Jordi Gonzàlez. 2011

214 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

CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification (2021, background): “, image pyramids [1], scale-space representation [29], and coarse-to-fine approaches [28]).”
Fast, Accurate Detection of 100,000 Object Classes on a Single Machine (2013, methodology): “[7] utilize a variation on probably approximate learning (PAC) to learn a cascade of detectors that provides a 20-fold speedup of their earlier model, and [12] introduce a new coarse-to-fine method that complements the approach in [7], and can be combined with it to achieve up to two orders of magni”
The Fastest Deformable Part Model for Object Detection (2014, methodology): “It has been found in previous works [10, 22, 8] that in DPM most of the time is spent on calculating the appearance term due to the high dimension.”
Bottom-Up Segmentation for Top-Down Detection (2013, background): “To mitigate this, [27] consider lateral connections between high resolution parts.”
Regionlets for Generic Object Detection (2013, methodology): “Most existing approaches [ 3], 2], [1], [4], [7] train an object detector at a fixed scale and aspect ratio.”
Training Deformable Part Models with Decorrelated Features (2013, background): “Popular approaches include cascades [11], coarse-to-ﬁne processing [22], and sparse representations [23, 24].”
Using depth and appearance features for informed robot grasping of highly wrinkled clothes (2012, background): “Furthermore, in the context of current object detection literature, the label deformable object often refers to those that have some degree of articulation, like people or animals, as in [5], rather than to highly flexible objects such as cloth.”
Leaving Some Stones Unturned: Dynamic Feature Prioritization for Activity Detection in Streaming Video (2016, background): “, [39], [40]) determine a fixed ordering of features to quickly reject unlikely regions.”
Fast Feature Pyramids for Object Detection (2014, background): “Notable recent efforts for increasing detection speed include work by Felzenszwalb et al. [44] and Pedersoli et al. [45] on cascaded and coarse-to-fine deformable part models, respectively, Lampert et al.'s [46] application of branch and bound search for detection, and Doll ar et al.'s work on cross”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “Cascades have been successfully applied to the star-structured models of [7] in [43] and [42] for this purpose.”
Reinforcement Learning for Visual Object Detection (2016, background): “Motivated by these limitations, other authors have proposed to use cascades of classifiers[39] [11] [15] [30], to progressively narrow the search space, where weak but fast classifiers are applied early to eliminate image regions unlikely to contain the target, while investing computational…”
Pedestrian detection at 100 frames per second (2012, methodology): “Coarse-to-fine search is another popular method to arrive at fast object detection [15].”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “Therefore, the other models like the tree model in [31], [73], [98], the loopy graph model in [64], [84], the complete graphmodel in [6] and the pictorial structures in [1], [31] can be used for both single- and two-pedestrian detection.”
Learning Chained Deep Features and Classifiers for Cascade in Object Detection (2017, methodology): “[9] proved that a form of bootstrapping for SVMs converges to the global optimal solution deﬁned on the entire dataset.”
Learning coarse-to-fine sparselets for efficient object detection and scene classification (2015, methodology): “In recent years, since the seminal work of [4, 5] and with the success of deformable part models (DPMs) [6, 7], part model-based methods have demonstrated impressive performance for object detection [6-13] and scene classification [14-21].”
Sparselet Models for Efficient Multiclass Object Detection (2012, background): “Previous efforts have addressed hypothesis pruning in a cascaded implementation [1], and in coarse-to-fine search schemes [2].”
Crosstalk Cascades for Frame-Rate Pedestrian Detection (2012, background): “Finally, research on optimizing other types of classifiers [1,2,3,17,18,19] is of considerable interest, however, such methods have difficulty matching the speed achieved by boosted classifiers.”