Discovering object categories in image collections

By Josef Sivic, Bryan C. Russell, Alexei A. Efros, Andrew Zisserman, William T. Freeman. 2005

547 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Self-Supervised Training Enhances Online Continual Learning (2021, background): “A natural downstream setting that our work facilitates is open world learning [7] or automatic class discovery [63, 75], where an agent must identify samples outside of its training distribution as unknown and then learn them.”
Unsupervised Discovery of Mid-Level Discriminative Patches (2012, background): “Moreover, discovering these second-order relationships can provide us with “doublets” [34] (which could be further generalized to grouplets [22,35]) that can themselves be highly discriminative and useful as mid-level features in their own right.”
Discovering objects and their location in images (2005, background): “These results demonstrate that we can successfully build object class models from an unsupervised analysis of images.”
Unsupervised Object Discovery and Tracking in Video Collections (2015, background): “…process a discovery and tracking procedure since ﬁnding the tubes maximizing foreground conﬁdence across videos is akin to unsupervised object discovery [4, 11, 12, 28, 31], whereas ﬁnding the tubes maximizing temporal consistency within a video is similar to object tracking [1, 2, 13, 26, 40, 41].”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, background): “Unsupervised object discovery is most closely related to cosegmentation and colocalization, and also to weakly-supervised localization.”
Is object localization for free? - Weakly-supervised learning with convolutional neural networks (2015, unknown): “Unsupervised methods [34, 48] do not require any supervisory signal, just images.”
Toward unsupervised, multi-object discovery in large-scale image collections (2020, background): “Early work on object discovery [12,15,20,27,30] focused on a restricted setting where images are from only a few distinctive object classes.”
Spatial Latent Dirichlet Allocation (2007, methodology): “For example, in order to cluster image patches, which are treated as words, into classes of objects, researchers treated images as documents [2].”
The Pyramid Match Kernel: Efficient Learning with Sets of Features (2007, methodology): “, 2004), and more recently has been shown for classification of object categories using SVMs, Naı̈ve Bayes classifiers, and a probabilistic Latent Semantic Analysis framework (Csurka et al., 2004; Willamowski et al., 2004; Sivic et al., 2005).”
Unsupervised Learning of Categories from Sets of Partially Matching Image Features (2006, methodology): “Conventional clustering methods or latent semantic analysis (LSA) may then be directly applied [9, 3], and have been shown to yield promising results when learning object categories or filtering keyword-based image retrieval outputs.”
Moving vistas: Exploiting motion for describing scenes (2010, methodology): “The patch based bag-of-words approach has been used to model objects [ 26 ], scenes [9, 15], and human actions [5, 19] from videos.”
Simultaneous image classification and annotation (2009, unknown): “(1)According to [25], pLSA performs similarly to unsupervised LDA in practice.”
A correlated topic model of Science (2007, methodology): “The same kind of modeling tools have also been used in a variety of nontext settings, such as image processing [26, 13], recommendation systems [18], the modeling of user profiles [14] and the modeling of network data [1].”
Unsupervised Activity Perception by Hierarchical Bayesian Models (2007, background): “In computer vision, hierarchical Bayesian models have been applied to scene categorization [5], object recognition [9], and human action recognition [7].”
Image Classification Using Super-Vector Coding of Local Image Descriptors (2010, background): “Typically those models extend the famous topic models on bag-of-word representation by further considering the spatial information of visual words [2][3].”
Weakly-supervised Discovery of Visual Pattern Configurations (2014, background): “Existing approaches discover high-level object categories [26, 12, 5], mid-level patches [22, 3, 14], or low-level foreground features [16] by grouping similar visual patterns (i.”
A Comparative Study of Bag-of-Words and Bag-of-Topics Models of EO Image Patches (2015, background): “However, it has been shown in previous works [8]–[11] that these relations can result in the discovery of objects and their parts in images.”
Learning Object Categories From Internet Image Searches (2010, methodology): “In this paper, we investigate the ability of a pLSA-based model, based on Sivic et al. [35], to successfully learn from Fig.”