Generic object recognition with boosting

By Andreas Opelt, Axel Pinz, Michael Fussenegger, Peter Auer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006

431 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/6bb4de9c81b221f97d541b81134aab9029c42b91

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

iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning (2016, methodology): “COIL [41] Handheld 100 1 1 72 Implicit No 7,200 SOIL-47 [29] Handheld — 47 1 42 Implicit No 1,974 Pascal [14] Misc 20 790-10,129 1 1 Yes Partial 11,540 Caltech-101 [15] Google 102 31-800 (μ = 90) 1 1 No No 9,144 Caltech-256 [22] Google 257 80-827 (μ = 119) 1 1 No No 30,607 LabelMe [48] Misc 900 ? ∼1”
Asymmetric Cuts: Joint Image Labeling and Partitioning (2014, background): “Column (a) shows the original images, taken from benchmark datasets [31,30,10].”
Figure-ground segmentation by transferring window masks (2012, background): “It consists of two gaussian mixture models (GMM), one for the foreground A1, one for the background A0 A(xi|ci = 1) = A1(xi) A(xi|ci = 0) = A0(xi) (6) Each GMM has 5 components.”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, methodology): “In this section we describe the details of the annotation tool and the results of the online collection effort.”
Incremental learning of object detectors using a visual shape alphabet (2006, methodology): “1 Plane 50 50 400 Caltech [5] 2 CarRear 50 50 400 Caltech [5] 3 Motorbike 50 50 400 Caltech [5] 4 Face 50 50 217 Caltech [5] 5 BikeSide 45 45 53 Graz02 [12] 6 BikeRear 15 15 16 Graz02 [12] 7 BikeFront 10 10 12 Graz02 [12] 8 Cars2-3Rear 17 17 18 Graz02 [12] 9 CarsFront 20 20 20 Graz02 [12] 10 Bottles”
Foreground Focus: Unsupervised Learning from Partially Matching Images (2009, methodology): “This dataset has 250 positive training, 250 negative training, and 125 testing images of bikes taken from the GRAZ-01 (100 positive training, 100 negative training, and 50 testing) and GRAZ-02 (150 positive training, 150 negative training, and 75 testing) datasets (Opelt et al. 2006), respectively.”
Multiple instance classification: Review, taxonomy and comparative study (2013, methodology): “Regarding the standard classiﬁer G , in [31, 2] the authors use AdaBoost with decision stumps, and in [33, 1, 32] they use SVM. our In additional notes [19] we show how the Auer and Ortner’s method [2] can be expressed as a D-BoW algorithm, although it is easy to see it from the original paper [2].”
Pylon Model for Semantic Segmentation (2011, methodology): “Graz-02 dataset [23] equal recall-precision Method Bikes Cars People Marszalek&Schmid [21] 53.”
A Review of Computer Vision Techniques for the Analysis of Urban Traffic (2011, methodology): “In [104] and [106], binary AdaBoost is used for generic object recognition, where boosting automatically performs the feature selection.”
Top-down visual saliency via joint CRF and dictionary learning (2012, methodology): “However, as target objects are likely to appear anywhere in a scene, this contextual prior is less effective (e.g., images from the Graz-02 and PASCAL VOC datasets).”
Features for image retrieval: an experimental comparison (2008, methodology): “These approaches are successfully used for object recognition and detection [35,36,37, 38 ,39,40] and CBIR [26,41,42,43].”
Understanding bag-of-words model: a statistical framework (2010, methodology): “Challenge 2006 data set [4] and Graz02 data set [ 15 ].”
Large scale mining and retrieval of visual data in a multimodal context (2008, methodology): “All training data and the positive test set are as defined in the paper which originally proposed this dataset [Opelt et al., 2003].”
Robust Object Recognition with Cortex-Like Mechanisms (2007, result): “Results obtained with the C 2 SMFs are superior to previous approaches [17], [18] on the MIT-CBCL data sets and comparable to the best systems [46], [47] on the CalTech5 data sets.”
Learning relational object categories using behavioral exploration and multimodal perception (2014, methodology): “A wide variety of computer vision methods have been developed that attempt to solve this problem using visual image features coupled with machine learning classifiers [14], [15], [16].”