Efficient Visual Search of Videos Cast as Text Retrieval

By Josef Sivic, Andrew Zisserman. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009

539 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/4deed69b18e18bb87b2fb563bd5240c4fbd8c68b

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

Simultaneous Localization and Mapping: A Survey of Current Trends in Autonomous Driving (2017, unknown): “Bag-of-words approaches based on visual clues [132][135] belong to this category.”
A Survey on Metric Learning for Feature Vectors and Structured Data (2013, methodology): “This similarity function can be seen as a generalization of the cosine similarity, widely used in text and image retrieval (see for instance Baeza-Yates and Ribeiro-Neto, 1999; Sivic and Zisserman, 2009).”
Online Defect Prediction for Imbalanced Data (2015, background): “Bag-of-words Bag-of-words is a commonly used feature in the machine learning community [34, 51].”
Query-driven iterated neighborhood graph search for large scale indexing (2012, background): “For instance, the state-of-the-art duplicate image search [49, 50] depends on the bag-of-words descriptor, which usually exploits ANN search techniques to group large scale local features into visual words using k-means or similar algorithms [36] and map visual features to visual words.”
End-to-End Learning of Representations for Asynchronous Event-Based Data (2019, unknown): “, [14, 33, 35, 60, 63].”
Reliable detection of audio events in highly noisy environments (2015, background): “, 2013), video-based object detection (Sivic and Zisserman, 2009) or music classification (Fu et al.”
Pyramid of Spatial Relatons for Scene-Level Land Use Classification (2015, methodology): “Inspired by the success of the BOW model in text retrieval literature and the robustness of local features as image representation [2], [13], [20], [27], the computer vision community adapts the BOW to represent an image by treating local features as visual words [8], [35].”
It ’ s in the bag : Stronger supervision for automated face labelling (2015, methodology): “Shot boundary detection and subtitle processing was done using methods described in [21].”