Small codes and large image databases for recognition

By Antonio Torralba, Rob Fergus, Yair Weiss. 2008

801 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Information Retrieval & Search

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

In Information Retrieval & Search

Citations in the corpus

Learning with Hierarchical-Deep Models (2013, methodology): “Gist descriptors have previously been used for this data set [41] apples and oranges, and not like other classes of images, suc h as dolphins, that reside in very different parts of the hiera rchy.”
Unsupervised Object Discovery and Tracking in Video Collections (2015, methodology): “At the ﬁrst iteration, the nearest-neighbor search is based on distances between GIST descriptors [34] of frames as the tube r is initialized as the entire video.”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “3 At the first iteration, as the potential object regions become entire image regions, nearest-neighbor matching with the GIST descriptor [52] is used.”
Efficient representation of local geometry for large scale object retrieval (2009, methodology): “The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark.”
Efficient Learning of Deep Boltzmann Machines (2010, methodology): “The new learning algorithm has been successfully used in many application domains (Hinton et al., 2006; Ranzato et al., 2007; Torralba et al., 2008; Lee et al., 2009; Nair & Hinton, 2010) primarily because of the following three key characteristics.”
Image Classification Using Super-Vector Coding of Local Image Descriptors (2010, methodology): “The previous work includes SVMs using pyramid matching kernels [4], biologically-inspired models [5][6], and KNN methods [7][8][9].”
Deep Learning and Convolutional Neural Networks for Medical Image Computing (2017, methodology): “, GIST [32], bag-of-visual-words (BoVW) and bag-of-frequency [12]).”
The Power of Asymmetry in Binary Hashing (2013, methodology): “These datasets include: LabelMe and Peekaboom are collections of images, represented as 512D GIST features [13], Photo-tourism is a database of image patches, represented as 128 SIFT features [12], MNIST is a collection of 785D greyscale handwritten images, and Nursery contains 8D features.”
Minimal Loss Hashing for Compact Binary Codes (2011, methodology): “Multilayer neural nets trained by Torralba et al. (2008) (NNCA) are considered the superior method for semantic 22K LabelMe .”