Video Google: a text retrieval approach to object matching in videos
Citations
40,257 citations
15,935 citations
Cites methods from "Video Google: a text retrieval appr..."
...Many of the submissions used variations on the basic bag-of-visual-words method (Csurka et al (2004); Sivic and Zisserman (2003)) that was so successful in VOC2006, see Zhang et al (2007): local features are computed (for example SIFT descriptors); vector quantised (often by using k-means) into a…...
[...]
...Many of the submissions used variations on the basic bag-of-visual-words method (Csurka et al. 2004; Sivic and Zisserman 2003) that was so successful in VOC2006, see Zhang et al....
[...]
8,702 citations
7,057 citations
5,919 citations
Cites background or methods from "Video Google: a text retrieval appr..."
...Such vectors can be generated by the Bag-ofWords approach [16] that pools the features together....
[...]
..., by vector quantization [15], [16], [30], sparse coding [17], [18], or Fisher kernels [19]....
[...]
...the Bag-of-Words (BoW) model [16], is one of the most successful methods in computer vision....
[...]
...These encoded features consist of the feature maps, and are then pooled by Bag-of-Words [16] or spatial pyramids [14], [15]....
[...]
References
16,989 citations
"Video Google: a text retrieval appr..." refers methods in this paper
...The method is illustrated for matching on two full length feature films....
[...]
14,696 citations
"Video Google: a text retrieval appr..." refers background in this paper
...In addition the components are weighted in various ways (described in more detail in section 4), and in the case of Google the weighting of a web page depends on the number of web pages linking to that particular page [3]....
[...]
13,327 citations
9,923 citations
3,422 citations