Video Google: a text retrieval approach to object matching in videos

By Josef Sivic, Andrew Zisserman. 2003

7,305 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

Going deeper with convolutions (2014, methodology): “[12] Antanas Verikas, Adas Gelzinis, and Marija Bacauskiene.”
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition (2014, background): “Deep-networksbased approaches have recently been substantially improving upon the state of the art in image classification [3], [4], [5], [6], object detection [7], [8], [5], many other recognition tasks [9], [10], [11], [12], and even non-recognition tasks.”
Product Quantization for Nearest Neighbor Search (2011, methodology): “Similarly to the “Video-Google” approach [24], a codebook is”
Momentum Contrast for Unsupervised Visual Representation Learning (2019, background): “Computer vision, in contrast, further concerns dictionary building [54, 9, 5], as the raw signal is in a continuous, high-dimensional space and is not structured for human communication (e.”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, background): “Image retrieval based on local features, bags-of-visual-words (BoVWs) and inverted indices [35, 45] has been shown to be more accurate than global descriptors at matching buildings, but requires more space and lacks the invariance to match e.g . natural scenes or articulated objects.”
Webly Supervised Learning of Convolutional Networks (2015, neutral): “One possibility is to use commercial text-based image search engine to increase di-3 versity in the training data.”
An Empirical Study of Training Self-Supervised Vision Transformers (2021, neutral): “This is analogous to bag-ofwords models [40].”
CrossTransformers: spatially-aware few-shot transfer (2020, background): “Discriminative parts [5, 10, 22, 34, 42, 83] and visual words [74, 100] have a rich history, and have found applications in deformable-parts models [26], and classification [70, 100].”
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”
This looks like that: deep learning for interpretable image recognition (2018, background): “It relates to traditional “bag-of-visual-words” models used in image recognition [21, 6, 17, 38, 31].”
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos (2016, background): “BOvW [58] and FV [43] or Fourier temporal pyramids in [73].”
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection (2017, background): “, bag of words (BoW) [38] or Fisher vector based encodings [33], to produce a global representation for video and to train a classifier on the action labels.”
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning (2015, methodology): “Bag-of-Words (BoWs) [28] and Fisher vector encoding [25] are then applied to accumulate the local descriptors and generate the video representation.”
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.”
Unsupervised Discovery of Mid-Level Discriminative Patches (2012, methodology): “We compare our approach with Visual Words [1] and Russell et. al [24] baseline, plus a number of intermediate results of our method: 1) HOG K-Means (visual word analog for HOG features), 2) Initial Clustering (SVMs trained on the K-Means clusters without discriminative re-clustering), and 3) No…”