Flickr tag recommendation based on collective knowledge

By Börkur Sigurbjörnsson, Roelof van Zwol. The Web Conference, 2008

1,087 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bef7fe96a7cc9d752875923a50295807e29a1a7f

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

Visual-Textual Joint Relevance Learning for Tag-Based Social Image Search (2013, background): “As reported in [12], only about 50% of the tags provided by Flickr users are really related to the images.”
Exploring place through user-generated content: Using Flickr tags to describe city cores (2010, background): “Particularly for tags with low frequencies, issues were identi ﬁ ed with respect to quality and idiosyncrasy, as is re ﬂ ected in the long tail distribution with 56.5% of tags being used only once, a typical property of tagged images [26,34].”
A performance evaluation of gradient field HOG descriptor for sketch based image retrieval (2013, methodology): “score measure in association rule mining [47, 48, 42].”
Understanding web images by object relation network (2012, background): “Tag recommendation [24, 29] enriches the semantics carried by existing tags by suggesting similar tags.”
Placing flickr photos on a map (2009, background): “According to recent literature [2, 21] users spend considerable eﬀort to organise their“memory”geographically by describing photos with tags related to locations where they were taken.”
The Effect of Population and "Structural" Biases on Social Media-based Algorithms: A Case Study in Geolocation Inference Across the Urban-Rural Spectrum (2017, background): “For instance, researchers have used social media to develop new recommender systems (e.g., [38,59]), summarize the character of cities (e.g., [9,66]), and infer the location of Internet users (e.g., [34,41,45]), among other applications (e.g., [4,30,49]).”
Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications (2013, methodology): “Another possible solution is the image tag recommendation method [32], [33].”
Personalized Deep Learning for Tag Recommendation (2017, methodology): “For example, between February 2004 to June 2007, around 64 percent of Flickr uploaded photos had 1 to 3 tags and around 20 percent had no tags [20].”
Tree2Vector: Learning a Vectorial Representation for Tree-Structured Data (2018, methodology): “The detailed implementation of these measures can be found in [1], [29], and [39].”
How annotation styles influence content and preferences (2013, background): “Choosing a common set of images for people to tag is an approach that has also been used in other tagging studies [5, 18].”
Automatic tag expansion using visual similarity for photo sharing websites (2010, methodology): “In [29], co-occurrence information for tags, obtained from a large pool of Flickr images, are used to recommend additional tags to a photo with initial user-defined tags.”
Finding meaning on YouTube: Tag recommendation and category discovery (2010, methodology): “The system that we propose is based on the collective knowledge, similar to the approach in [24] but analyzing the video content instead of the metadata.”
Nonnegative shared subspace learning and its application to social media retrieval (2010, background): “Sig-urbjörnsson and Zwol [24] investigate how users tag photos and the information contained in Flickr tags.”
Evaluating similarity measures for emergent semantics of social tagging (2009, methodology): “among tags have been built using co-occurrence [4, 44] and Jaccard’s coefficient [18], also to reconstruct a concept hierarchy [19].”
Image Labeling on a Network: Using Social-Network Metadata for Image Classification (2012, background): “The same problem was studied in [21], who exploit the relationships between tags to suggest future tags based on existing ones.”
Secure Deep Graph Generation with Link Differential Privacy (2020, background): “By releasing and sharing structured relational data with research facilities and enterprise partners, data companies harvest the enormous potential value from their data, which benefits decision-making on various aspects, including social, financial, environmental, through collectively improved ads,”