Analyzing appearance and contour based methods for object categorization

By Bastian Leibe, Bernt Schiele. 2003

885 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (2018, background): “Many of the aforementioned object datasets include annotations of object poses [34, 38, 47, 63, 64].”
Understanding Deep Features with Computer-Generated Imagery (2015, methodology): “A database of natural images captured in controlled conditions and spanning different factors of variations, e.g. the NORB [22], ETH-80 [23] and RGB-D object [20] datasets, where different objects are rotated on a turntable and lighting is varied during image capture, are difﬁcult and costly to…”
Sharing Visual Features for Multiclass and Multiview Object Detection (2007, background): “There has been work on training a single multiclass classifier to distinguish between different classes of object, but this typically assumes that the object has been separated from the background (see e.g., [25], [22]).”
A Deeper Look at Dataset Bias (2015, background): “…of Caltech256 [19] and Bing [40], 89 classes of SUN [42], 35 classes of Caltech101 [11], 17 classes of Of ﬁ ce [36], 18 classes of RGB-D [27], 16 classes of Animals with At-tributes (AwA) [28] and Pascal VOC07 [9], 13 classes of MSRCORID [31], 7 classes of ETH80 [29], and 4 classes of a-Yahoo [10].”
Manifold Discriminant Analysis (2009, methodology): “For object categorization, we use the benchmark database ETH-80 [17].”
Deep Reconstruction Models for Image Set Classification (2015, background): “Index Terms—Image set classification, deep learning, auto-encoders, video based face recognition, object recognition Ç”
Grassmann discriminant analysis: a unifying view on subspace-based learning (2008, methodology): “Recognition rates of subjects from Yale face database (Left), and classi.cation rates of categories in ETH-80 database (Right).”
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices (2013, methodology): “To this end, we used the ETH-80 dataset [11] which contains 8 categories with 10 objects each and 41 images per object.”
A list of household objects for robotic retrieval prioritized by people with ALS (2008, background): “Physically impaired people often have difficulty retrieving objects from the floor and shelves, and these problems can be exacerbated by reduced strength and dexterity in the upper extremities, which can increase the chances of dropping an object.”
Covariance discriminative learning: A natural and efficient approach to image set classification (2012, methodology): “For the object categorization task, we use the benchmark database ETH-80 [15].”
A performance evaluation of local descriptors (2005, background): “panoramas [4], and recognition of object categories [8, 9, 22 , 35].”
Beyond PASCAL: A benchmark for 3D object detection in the wild (2014, background): “PASCAL3D+ (ours) ETH-80 [13] [26] 3DObject [22] EPFL Car [20] [27] KITTI [8] NYU Depth [24] NYC3DCars [19] IKEA [15] Comparison of our PASCAL3D+ dataset with some of the other 3D datasets.”
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints (2016, methodology): “t, the prediction was successfully modiﬁed to a bathtub whose cross-section surface is an ellipse. 5 Experiment on a real image dataset In this section, we describe the experimental results on ETH-80 [32], which is a dataset of real images captured using a rotating table. The objective of this exper”
3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, methodology): “On the ETH dataset, it performs closely to the GRAPH + SumMin method and is slightly worse when the number of training sample per class is set to 2.”
Multi-view Subspace Clustering (2015, background): “• ETH-80 data set contains 8 categories, including apples , pears, tomatoes, cows, dogs, horses, cups and cars.”
A Visual Category Filter for Google Images (2004, methodology): “While methods exist to model object categories [9, 13, 15], it is essential that the approach can learn from a contaminated training set with a minimal amount of supervision.”
Multi-manifold deep metric learning for image set classification (2015, methodology): “We conducted image set classiﬁcation experiments on ﬁve publicly available datasets including the Hon-da/UCSD [22], CMU Mobo [9], YouTube Celebrities (YTC) [15], PubFig [19] face datasets, and the ETH-80 object dataset [23].”