VisualRank: Applying PageRank to Large-Scale Image Search

By Yushi Jing, Shumeet Baluja. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008

499 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c2b6b21bfd2f989e0791570c6a782ef561dfae7a

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

Automatic tag expansion using visual similarity for photo sharing websites (2010, methodology): “Due to the limitations of Content Based Image Retrieval (CBIR) methods [28, 30], other than some recent efforts for web-scale retrieval [10], accessing the content through tags is still the most commonly used way.”
Online multimodal deep similarity learning with application to image retrieval (2013, background): “Similarity search is a fundamental issue of multimedia information retrieval research, which has been actively studied for years across several communities, including multimedia, signal processing, computer vision, and machine learning [28, 22].”
Visual Discovery at Pinterest (2017, background): “Various works [19] [12] have been proposed to improve the ranking of the image search results using visual features.”
Content-based visual search learned from social media (2012, methodology): “Considering that the OKAPI-BM25 ranking function originally aims for text retrieval and hence might not be optimal for tag-based image retrieval, we further compare with a recent achievement in web image retrieval by Jing and Baluja [52] (see details in Section 2.”
Automatic Construction of Action Datasets Using Web Videos with Density-Based Cluster Analysis and Outlier Detection (2015, methodology): “Here we use our method of shot collection and apply their idea of using VisualRank to shot ranking to compare with our proposed method of shot selection which composed of diversity based shot clustering and LOF based shot ranking.”
Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest (2015, methodology): “Visual features are widely used in both content-based recommendation systems and image search systems [5], [11], and the the learning-to-rank framework used in this paper from [14] has been widely used in industry [8], [9], [12], [18].”
PRISM: concept-preserving social image search results summarization (2014, methodology): “Other methods consider only the visual similarity among images [8].”
Multimodal Graph-Based Reranking for Web Image Search (2012, methodology): “Several different graph-based learning approaches have been investigated for reranking [14], [23], [17] (in the next section we will introduce the details).”
Learning Object Categories From Internet Image Searches (2010, methodology): “A number of different approaches to this problem have been proposed, for example, the approach of Jing and Baluja [22] who adapt the PageRank algorithm to the visual domain.”
Deep Learning for Content-Based Image Retrieval: A Comprehensive Study (2014, background): “Content-based image retrieval (CBIR) is one of the fundamental research challenges extensively studied in multimedia community for decades [30, 25, 45].”
Image ranking based on user browsing behavior (2012, background): “[14, 15] based on the content of the images, is to extract the interest points from each image, classify the common ones, and create visual links between them.”
Tag ranking (2009, unknown): “Random walk methods have been widely applied in machine learning and information retrieval fields [18, 19, 20].”
An Attribute-Assisted Reranking Model for Web Image Search (2015, methodology): “Jing and Baluja proposed a VisualRank framework to efficiently model similarity of Google image search results with graph [19].”
Reinforced Similarity Integration in Image-Rich Information Networks (2013, unknown): “Index Terms—Information retrieval, image mining, information network, ranking Ç”
Learning of Multimodal Representations With Random Walks on the Click Graph (2016, background): “, [13], [21], [22]) which help re-rank the initial returned list to make a better relevance score.”
Image Classification and Retrieval are ONE (2015, methodology): “Popular post-processing approaches include geometric veriﬁcation [8], query expansion [9] and diﬀusion-based algorithms [23][60].”