Evaluating bag-of-visual-words representations in scene classification

By Jun Yang, Yu-Gang Jiang, Alexander G. Hauptmann, Chong-Wah Ngo. Multimedia Information Retrieval, 2007

960 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/07c44c676f9ed88c4c2cab2f257615d632c56ec7

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

View-invariant human action recognition via robust locally adaptive multi-view learning (2015, methodology): “As the frame number of different silhouette image sequences may not be the same, to obtain a fixed-length video based feature representation, we adopt the bag-of-words scheme (Yang et al., 2007).”
Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification (2015, methodology): “We build a Bag-of-Words (BoW) [19, 53] feature using k-means followed by SVM with RBF kernel [10], as a non-CNN baseline.”
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks (2018, background): “The family of bag-of-visual-words [5, 47, 34] models demonstrated the effectiveness of pooling the information contained in local descriptors to form a global image representation out of a local one.”
Online multimodal deep similarity learning with application to image retrieval (2013, methodology): “For local features, we extract the bag-of-visual-words representation [49] using two kinds of descriptors: (i) SIFT feature [30] and HessianAffine interest region detector with a threshold of 500; and (ii) SURF feature [3] and SURF detector with a threshold of 500.”
Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher Vectors (2016, methodology): “The bag-of-visual-words (BOVW) model [1], which is one of the most popular approaches in image analysis and classification applications, provides an efficient approach to solve the problem of scene classification.”
Dissimilarity-based people re-identification and search for intelligent video surveillance (2013, background): “The first one is the Bag of Words (BoW) model for describing images [135], which is widely used in scene classification.”
Application and Evaluation of a Hierarchical Patch Clustering Method for Remote Sensing Images (2016, methodology): “In contrast, optical images can also be well classified by the Bagof-Words (BoW) method [21] since it describes the general as well as the detailed information contained in an image patch.”
Feature Learning and Analysis for Cleanliness Classification in Restrooms (2019, methodology): “One famous method for image feature analysis is Bag-offeature (BoF) [7].”
Going Beyond Text: A Hybrid Image-Text Approach for Measuring Word Relatedness (2011, methodology): “Inspired by the bag-of-words approach employed in information retrieval, the “bag of visual code-words” is a similar technique used mainly for scene classiﬁcation (Yang et al., 2007).”
UNICORN: Runtime Provenance-Based Detector for Advanced Persistent Threats (2020, methodology): “However, unlike traditional histogram-based similarity analysis [13], [24], [133], UNICORN constantly updates the histogram as new edges arrive.”
Privacy-CNH: A Framework to Detect Photo Privacy with Convolutional Neural Network using Hierarchical Features (2016, methodology): “SVM with BOVW: The work of (Zerr et al. 2012) and (Squicciarini, Caragea, and Balakavi 2014) both explored SIFT descriptors by (Lowe 2004) to extract features from images and learned a visual word dictionary.”
Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world (2014, methodology): “…vectors are extracted using the unsupervised bag-of-visual-words (BoVW) representational architecture (Sivic and Zisserman, 2003; Csurka et al., 2004), that has been widely and successfully applied to computer vision tasks such as object recognition and image retrieval (Yang et al., 2007).”
ReVision: automated classification, analysis and redesign of chart images (2011, methodology): “A common approach is to use a “bag of visual words” representation [29] where the “words” are low-level image features such as gradients or local region textures.”
Distributional Semantics in Technicolor (2012, methodology): “The visual features are extracted with the use of a standard bag-of-visual-words ( BoVW ) representation of images, inspired by NLP (Sivic and Zisser-man, 2003; Csurka et al., 2004; Nister and Stewe-nius, 2006; Bosch et al., 2007; Yang et al., 2007).”
Scene classification using multi-scale deeply described visual words (2016, methodology): “One particular method, called the bag-of-visual-words (BoVW), has been proposed and successfully applied to scene classi ﬁ cation (Yang et al. 2007).”
Learning Representations by Predicting Bags of Visual Words (2020, methodology): “To this end, we take inspiration from the so-called Bag-ofWords [67] (BoW) model in computer vision and propose using as self-supervised task one where we wish (to train a convnet) to predict the histogram of visual words of an image (also known as its BoW representation) when given as input a pertu”
Kernel Methods in Computer Vision (2009, background): “This work [Yang et al., 2007] compares many different feature and preprocessing operations for scene classification.”