The Amsterdam Library of Object Images

By Jan-Mark Geusebroek, Gertjan J. Burghouts, Arnold M. W. Smeulders. 2004

1,004 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, 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 Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

Distance based similarity models for content based multimedia retrieval (2013, background): “, 2007], ALOI [Geusebroek et al., 2005], and MSRA-MM [Wang et al.”
Interpreting and Unifying Outlier Scores (2011, methodology): “3 Improvement in Outlier Ensembles We constructed ensembles for the KDDCup 1999 dataset as well as an image data set derived from the Amsterdam Library of Object Images [18] (50.”
Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations (2007, methodology): “The ALOI database [33] with 500 general object categories taken at different viewing angles provides another experimental data set for the proposed method.”
iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning (2016, methodology): “, NORB [35], COIL [41], SOIL-47 [29], ALOI [19], GRAZ [42], BigBIRD [55]) or by constructing 3D graphic models and rendering textures to them (e.”
CSIFT: A SIFT Descriptor with Color Invariant Characteristics (2006, methodology): “Sample images from ALOI [10] for a colored object under different illumination directions and intensities.”
Transfer of View-manifold Learning to Similarity Perception of Novel Objects (2017, methodology): “We have tested our approach with real image database (Geusebroek et al., 2005) and found it only yields a slight improvement over AlexNet.”
Meta-Recognition: The Theory and Practice of Recognition Score Analysis (2011, background): “Different values of the shape parameter yield the extreme value type I, II, and III distributions.”
Performance evaluation of local colour invariants (2009, neutral): “We consider the ALOI database [60] to match regions that are computed from 26,000 images of 1000 objects in total.”
Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases (2020, background): “Viewpoint, Illumination Direction and Illumination Color The ALOI dataset[37] contains images of 1000 objects taken on a turntable by varying viewpoint, illumination direction and illumination color separately.”
A Comparative Evaluation of Unsupervised Anomaly Detection Algorithms for Multivariate Data (2016, methodology): “Object Images (ALOI) The aloi dataset is derived from the “Amsterdam Library of Object Images” collection [63].”
Online Continual Learning on Sequences (2020, neutral): “NORB [36] 5 25 20 20* grayscale turntable no COIL-100 [57] - 100 20 54* RGB turntable no iLab-20M [4] 15 704 - RGB turntable no RGB-D [75] 51 300 - RGB-D turntable no BigBIRD [78] - 100 - RGB-D turntable no ALOI [16] - 1000 - RGB turntable no BigBrother [12] - 7 54 ∼20 RGB wall cam.”
Contextual Memory Trees (2018, methodology): “To test the effect of the multiplier c (the leaf memories multiplier), we switch to the ALOI dataset (Geusebroek et al., 2005), which has 100 examples per class enabling good generalization.”
Learning Stochastic Feedforward Neural Networks (2013, methodology): “We trained SFNNs to generate colorful images of common objects from the Amsterdam Library of Objects database [20], conditioned on the foreground masks.”
CURE-OR: Challenging Unreal and Real Environments for Object Recognition (2018, background): “[26], NORB [25], RGB-D [27], and BigBIRD [28] datasets are large-scale but their controlled conditions are limited to relative camera location, rotation, or lighting.”
The Extreme Value Machine (2015, methodology): “f standard multi-class benchmarks including LETTER [22], which has 26 classes, 16 features and 20000 instances; MNIST [23] with 10 classes, 785 features and 70000 instances; and the largest test ALOI [24] with 1000 classes, 128 features, and 108000 instances. Multi-class classiﬁcation (i.e., closed ”