Discovering objects and their location in images
Published 1 January 2005Open access
Josef Šivic, Bryan Russell, Alexei A. Efros, Andrew Zisserman, William T. Freeman
Citations980
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work treats object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics, and develops a model developed in the statistical text literature: probabilistic latent semantic analysis (pLSA).
Abstract
We seek to discover the object categories depicted in a set of unlabelled images. We achieve this using a model developed in the statistical text literature: probabilistic Latent Semantic Analysis (pLSA). In text analysis this is used to discover topics in a corpus using the bag-of-words document representation. Here we treat object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics. The model is applied to images by using a visual analogue of a word, formed by vector quantizing SIFT-like region descriptors. The topic discovery approach successfully translates to the visual domain: for a small set of objects, we show that both the object categories and their approximate spatial layout are found without supervision. Performance of this unsupervised method is compared to the supervised approach of Fergus et al. [8] on a set of unseen images containing only one object per image. We also extend the bag-of-words vocabulary to include ‘doublets’ which encode spatially local co-occurring regions. It is demonstrated that this extended vocabulary gives a cleaner image segmentation. Finally, the classification and segmentation methods are applied to a set of images containing multiple objects per image. These results demonstrate that we can successfully build object class models from an unsupervised analysis of images.
Keywords
Computer Science
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Rapid object detection using a boosted cascade of simple features
18,097 Citations2005Paul Viola, Michael Jones
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Object recognition from local scale-invariant features
16,195 Citations1999David Lowe
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Video Google: a text retrieval approach to object matching in videos
6,414 Citations2003Sivic, Zisserman
An approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video, represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion.
International Journal of Computer VisionModeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
6,410 Citations2001Aude Oliva, Antonio Torralba
The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
Visual categorization with bags of keypoints
4,147 Citations2004G. Csurka
Probabilistic latent semantic indexing
3,916 Citations1999Thomas Hofmann
Probabilistic Latent Semantic Indexing is a novel approach to automated document indexing which is based on a statistical latent class model for factor analysis of count data.
Image and Vision ComputingRobust wide-baseline stereo from maximally stable extremal regions
3,664 Citations2004Jiřı́ Matas, Ondřej Chum +2 more
The high utility of MSERs, multiple measurement regions and the robust metric is demonstrated in wide-baseline experiments on image pairs from both indoor and outdoor scenes.
A Bayesian Hierarchical Model for Learning Natural Scene Categories
3,613 Citations2005Li Fei-Fei, Pietro Perona
This work proposes a novel approach to learn and recognize natural scene categories by representing the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning.
Journal of the American Statistical AssociationHierarchical Dirichlet Processes
3,567 Citations2006Yee Whye Teh, Michael I. Jordan +2 more
This work considers problems involving groups of data where each observation within a group is a draw from a mixture model and where it is desirable to share mixture components between groups, and considers a hierarchical model, specifically one in which the base measure for the childDirichlet processes is itself distributed according to a Dirichlet process.
Machine LearningUnsupervised Learning by Probabilistic Latent Semantic Analysis
2,443 Citations2001Thomas Hofmann
This paper proposes to make use of a temperature controlled version of the Expectation Maximization algorithm for model fitting, which has shown excellent performance in practice, and results in a more principled approach with a solid foundation in statistical inference.
Computer Vision and Image UnderstandingLearning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories
2,052 Citations2007Li Fei-Fei, Rob Fergus +1 more
The incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum-likelihood, which have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible.
Object class recognition by unsupervised scale-invariant learning
2,035 Citations2003Rob Fergus, Pietro Perona +1 more
The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).
Lecture notes in computer scienceObject Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary
1,608 Citations2002Pınar Duygulu, Kobus Barnard +2 more
This work shows how to cluster words that individually are difficult to predict into clusters that can be predicted well, and cannot predict the distinction between train and locomotive using the current set of features, but can predict the underlying concept.
Lecture notes in computer scienceAn Affine Invariant Interest Point Detector
1,300 Citations2002Krystian Mikolajczyk, Cordelia Schmid
A novel approach for detecting affine invariant interest points that can deal with significant affine transformations including large scale changes and shows an excellent performance in the presence of large perspective transformations including significant scale changes.
A statistical method for 3D object detection applied to faces and cars
1,061 Citations2002Henry Schneiderman, Takeo Kanade
Using this method, this work has developed the first algorithm that can reliably detect human faces with out-of-plane rotation and the first algorithms thatCan reliably detect passenger cars over a wide range of viewpoints.
Lecture notes in computer scienceUnsupervised Learning of Models for Recognition
599 Citations2000Markus Weber, Max Welling +1 more
A method to learn object class models from unlabeled and unsegmented cluttered cluttered scenes for the purpose of visual object recognition that achieves very good classification results on human faces and rear views of cars.
Learning the semantics of words and pictures
526 Citations2002Kobus Barnard, David Forsyth
The model is very promising for information retrieval tasks such as database browsing and searching for images based on text and/or image features, and can be used for novel applications such as associating words with pictures, and unsupervised learning for object recognition.
Lecture notes in computer scienceMulti-view Matching for Unordered Image Sets, or “How Do I Organize My Holiday Snaps?”
525 Citations2002F. Schaffalitzky, Andrew Zisserman
This paper invests how a combination of image invariants, covariants, and multiple view relations can be used in concord to enable efficient multiple view matching and produces a matching algorithm which is linear in the number of views.
IEEE Transactions on Information TheoryMinimum complexity density estimation
497 Citations1991Andrew R. Barron, Thomas M. Cover
An index of resolvability is proved to bound the rate of convergence of minimum complexity density estimators as well as the information-theoretic redundancy of the corresponding total description length to demonstrate the statistical effectiveness of the minimum description-length principle as a method of inference.
Discovering object categories in image collections
442 Citations2005Josef Šivic, Bryan Russell +3 more
Given a set of images containing multiple object categories, this work seeks to discover those categories and their image locations without supervision using generative models from the statistical text literature: probabilistic Latent Semantic Analysis (pLSA), and Latent Dirichlet Allocation (LDA).
DSpace@MIT (Massachusetts Institute of Technology)Contextual Models for Object Detection Using Boosted Random Fields
303 Citations2004Antonio Torralba, Kevin Murphy +1 more
This work introduces Boosted Random Fields (BRFs), which uses Boosting to learn the graph structure and local evidence of a conditional random field (CRF) and applies it to detect stuff and things in office and street scenes.
Lecture notes in computer scienceWeak Hypotheses and Boosting for Generic Object Detection and Recognition
265 Citations2004Andreas Opelt, Michael Fussenegger +2 more
The first stage of a new learning system for object detection and recognition using Boosting as the underlying learning technique and the inclusion of features from segmented re- gions and even spatial relationships leads us a significant step towards generic object recognition.
Hidden semantic concept discovery in region based image retrieval
53 Citations2004Ruofei Zhang, Zhongfei Zhang
This work addresses content based image retrieval (CBIR), focusing on developing a hidden semantic concept discovery methodology to address effective semantics-intensive image retrieval.
Lecture notes in computer scienceImproved Video Content Indexing by Multiple Latent Semantic Analysis
13 Citations2004Fabrice Souvannavong, Bernard Mérialdo +1 more
This work has successfully proposed an adaptation of LSA to model video content for object retrieval and semantic content estimation and presents a new model composed of multiple LSA’s (M-LSA) to better represent the video content.