Visual categorization with bags of keypoints

By Gabriella Csurka, Christopher R. Dance, Lixin Fan, Jutta Katharina Willamowski, C. Bray. 2002

5,385 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Describing Textures in the Wild (2013, methodology): “The most common coding method is to vector quantize the descriptors using an algorithm such as K -means [19], resulting in the so-called bag-of-visual-words (BoVW) representation [8].”
Deep Clustering for Unsupervised Learning of Visual Features (2018, neutral): “For example, the “bag of features” model uses clustering on handcrafted local descriptors to produce good image-level features [11].”
Return of the Devil in the Details: Delving Deep into Convolutional Nets (2014, background): “In fact, most of the quantitative improvements to image understanding obtained in the past dozen years can be ascribed to the introduction of improved representations, from the Bag-of-Visual-Words (BoVW) [1], [2] to the (Improved) Fisher Vector (IFV) [3].”
Understanding deep image representations by inverting them (2014, background): “Most image understanding and computer vision methods build on image representations such as textons [17], histogram of oriented gradients (SIFT [20] and HOG [4]), bag of visual words [3][27], sparse [37] and local coding [34], super vector coding [40], VLAD [10], Fisher Vectors [23], and, lately, de”
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.”
DeltaPhish: Detecting Phishing Webpages in Compromised Websites (2017, methodology): “This approach is usually referred to as Bag of Visual Words (BoVW) [37].”
Genetic CNN (2017, neutral): “, GPU), the Convolutional Neural Networks (CNNs) [19][32] have shown superior performance over the conventional Bag-ofVisual-Words [3][38][29] and compositional models [9].”
Long-Term Temporal Convolutions for Action Recognition (2016, neutral): “video features [2], [4], [5] aggregated with Bag-of-Features histograms [18] or Fisher Vector representations [19].”
Bilinear CNN Models for Fine-Grained Visual Recognition (2015, methodology): “The bilinear model also generalizes several widely used orderless texture descriptors such as the Bag-of-Visual-Words [8], VLAD [20], Fisher vector [28], and second-order pooling (O2P) [3].”
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images (2015, background): “Notable examples of representations include textons (Leung and Malik 2001), histogram of oriented gradients (SIFT, Lowe 2004 and HOG, Dalal and Triggs 2005), bag of visual words (Csurka et al. 2004; Sivic and Zisserman 2003), sparse (Yang et al.”
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections (2006, background): “Most researchers follow the approach of using clustered affine-invariant point descriptors as “visual words” [5, 22].”
Context Encoding for Semantic Segmentation (2018, methodology): “Then a visual vocabulary (dictionary) is often learned and the global feature statistics are described by classic encoders such as Bag-of-Words (BoW) [8, 13, 26, 46], VLAD [25] or Fisher Vector [44].”
Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet (2019, methodology): “Many successful image classiﬁcation models have been based on this pipeline (Csurka et al., 2004; Jurie & Triggs, 2005; Zhang et al., 2007; Lazebnik et al., 2006), see O’Hara & Draper (2011) for an up-to-date overview.”
Discovering objects and their location in images (2005, methodology): “Others have used similar descriptors for object classification [5, 15], but in a supervised setting.”
Multi-scale Orderless Pooling of Deep Convolutional Activation Features (2014, background): “For much of the past decade, orderless bag-of-features (BoF) methods [15,17,18,19,20] were considered to be the state of the art.”
Layer-Wise Relevance Propagation for Neural Networks with Local Renormalization Layers (2016, methodology): “This was done for neural networks, bag of word models [3,10], and in a subsequent work [2], for Fisher vectors.”