Learning object categories from Google's image search

By Rob Fergus, Li Fei-Fei, Pietro Perona, Andrew Zisserman. 2005

864 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Transferable Visual Models From Natural Language Supervision (2021, background): “This line of work queries image search engines to build image datasets by querying for terms and uses the queries as the labels for the returned images (Fergus et al., 2005).”
LabelMe: A Database and Web-Based Tool for Image Annotation (2008, background): “It has been shown that image features can be used to improve the quality of the ranking returned by online queries (Fergus et al. 2005; Berg and Forsyth 2006).”
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections (2006, background): “Therefore, what we need is a way to group visual words spatially [8, 24] to make them more descriptive.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “es [3, 121], semantic [246, 174, 87, 256] or multi-view embedding [110, 153, 196, 104, 25, 238] especially used to perform cross-modal image retrieval. In the same spirit, webly supervised approaches [82, 242, 189, 14, 62, 37, 93] are also related to DA and HDA as is these approaches rely on collect”
Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds (2011, background): “, [22, 21]); however, such methods assume a single prominent object of interest per image, whereas for detection we will have cluttered candidate images that require a bounding box to identify the object of interest.”
Semantic Label Sharing for Learning with Many Categories (2010, background): “These include: Li et al. [8], Fergus et al. [9], Berg et al. [10], amongst others.”
Learning Visual Representations using Images with Captions (2007, methodology): “[9] developed a method using Google’s image search to learn visual categories, and report results comparable to fully supervised paradigms.”
Automatic Feature Decomposition for Single View Co-training (2011, background): “To address this problem, several researchers suggested a weakly-supervised learning setting (Fergus et al., 2005; Vijayanarasimhan & Grauman, 2008; Bergamo & Torresani, 2010), in which additional images are retrieved from image search engines such as GoogleTMor BingTMimage search using the category…”
The truth about cats and dogs (2011, background): “Within the window there may be be a single feature type represented, such as HOG [6] or HOG parts [11], or a bag of visual words [23], or a grid or pyramid of visual words [12, 26], or a combination of such features and kernels [18, 38].”
Multiple Viewpoint Recognition and Localization (2010, positive): “It is similar in spirit to the constellation models of Fergus et al. [19], with the exception that our features are detector responses from multiple viewpoints.”
Learning Models for Object Recognition from Natural Language Descriptions (2009, methodology): “searching Google Images for “car” or “voiture” to find example car images [10, 17, 19], in this paper we consider the use of Natural Language Processing (NLP) methods to extract information beyond keywords from naturally occurring English text.”
Evaluating Color Descriptors for Object and Scene Recognition (2010, background): “In general, systems for category recognition on images [1], [2], [3], [4], [5] and video [6], [7], [8] use machine learning based on image descriptions to distinguish object and scene categories .”
Harvesting Image Databases from the Web (2007, methodology): “Fuller implementation details are given in [9], and are reproduced in our implementation.”
OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning (2007, methodology): “We use the same training and testing datasets as in Fergus et al. (2005b).”
Learning Color Names for Real-World Applications (2009, background): “[13] within the context of object category learning.”
Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search (2012, methodology): “…et al. 2003; Gupta and Davis 2008; Berg et al. 2004; Li et al. 2009; Hwang and Grauman 2010b), using keyword search for inexpensive dataset creation (Fergus et al. 2005; Li et al. 2007; Schroff et al. 2007; Vijayanarasimhan and Grauman 2008), and building richer image representations based on the…”
Unsupervised Learning of Visual Sense Models for Polysemous Words (2008, methodology): “Two types of local feature points are detected in the image: e dge features [6] and scale-invariant salient points.”