Image webs: Computing and exploiting connectivity in image collections

By Kyle Heath, Natasha Gelfand, M. Ovsjanikov, Mridul Aanjaneya, Leonidas J. Guibas. 2010

110 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, 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 Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

Citations in the corpus

Unsupervised Visual Representation Learning by Context Prediction (2015, background): “Geometry may also be used to for verifying links between images [41, 6, 21], although this can fail for deformable objects.”
FlowWeb: Joint image set alignment by weaving consistent, pixel-wise correspondences (2015, background): “Recent work exploits the connectivity within an image collection by deﬁning a graph over images (e.g. [15, 27, 47, 13]) or objects (e.g. [28, 20, 6]).”
MatchMiner: Efficient Spanning Structure Mining in Large Image Collections (2012, methodology): “Many state-of-the-art image matching systems [4, 8, 9] use techniques based on image retrieval techniques (such as bag-of-words and inverted files [10]) to determine likely matches, but these metrics are not always good predictors of whether two images match.”
LDAHash: Improved Matching with Smaller Descriptors (2012, background): “scene, we have many conjunctive closure matches [36] such”
Retrieving landmark and non-landmark images from community photo collections (2010, background): “Futhermore, despite the eﬀort spent in constructing a model, the output is not used in any way to help retrieval or location recognition of a new photo.”
Persistence Images: A Stable Vector Representation of Persistent Homology (2015, background): “mpare diﬀerent data sets. Topological approaches to understanding data have been used in a variety of applications, for example, image webs, signal analysis, neuroscience, and biological aggregations [3, 4, 5, 6, 7, 8]. 1 Concurrent to this revolution in topology, a growing general interest in data ”
Metric graph reconstruction from noisy data (2011, background): “Recently, Heath et al.(18) built large graphs from image collections, by linking together images with partial shared content.”
Dataset fingerprints: Exploring image collections through data mining (2015, background): “Other graph building approaches are [13, 12].”
Web-Scale Image Clustering Revisited (2015, methodology): “Parallelism has widely been utilized for large scale clustering [24, 15], while algorithms for distributed systems exist for many popular clustering algorithms like Parallel kmeans [39] or parallel DB-SCAN [25].”
Reconstructing the World* in Six Days *(As Captured by the Yahoo 100 Million Image Dataset) (2015, background): “However, once a successful match is achieved and there is a remaining budget, further matches are only performed on nearest neighbors that do not belong to the same connected component (similar to [18] and [11]).”