World-scale mining of objects and events from community photo collections

By Till Quack, Bastian Leibe, Luc Van Gool. 2008

296 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps (2018, methodology): “The database serves as the index of an image retrieval sys-tem [28,29,30,31,32,33] or the training data of a landmark classiﬁer [34,35,36].”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, background): “5 shows examples of the different types of images PlaNet can localize. landmarks, which can also be recognized by landmark recognition engines [1, 37, 54], PlaNet can often correctly localize street scenes, landscapes, buildings of characteristic architecture, locally typical objects like red phone…”
Unsupervised Visual Representation Learning by Context Prediction (2015, background): “Visual data mining [41, 13, 47, 42], or unsupervised object discovery [48, 44, 20], aims to use a large image collection to discover image fragments which happen to depict the same semantic objects.”
Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification (2018, background): “Approaches that focus on landmark recognition use either a pre-defined set of landmarks or cluster a given photo collection in an unsupervised manner to retrieve the most interesting areas for geolocalization [4,23,28,48].”
Social Network Data Analytics (2011, methodology): “Pathak et al.[84] presented the Community-Author-Recipient-Topic (CART) model in a setting of email communication networks, assuming that the discussion among users within a community is relevant to these users as well as the community.”
Web-Scale Image Clustering Revisited (2015, methodology): “Leveraging the billions of images available in community photo collections, many recent approaches utilize their metadata, e.g. tags or geotags for clustering [19, 27, 11, 3].”
Tour the world: Building a web-scale landmark recognition engine (2009, background): “Contrasting to [8], [12] and [7], the principal focus of our approach is to explore landmarks at a world-scale.”
Visual Place Recognition with Repetitive Structures (2015, background): “Scalable place recognition methods [3, 7, 18, 31, 37] often build on the efficient bag-of-visual-words representation developed for object and image retrieval [6, 13, 15, 24, 26, 40].”
Automatic tag expansion using visual similarity for photo sharing websites (2010, unknown): “The work presented in [27] collects geo-tagged images from Flickr and clusters them using textual, visual and spatial cues.”
Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search (2012, background): “…richer image representations based on the two simultaneous “views” for retrieval or clustering (Monay and Gatica-Perez 2003; Hardoon and Shawe-Taylor 2003; Quattoni et al. 2007; Bekkerman and Jeon 2007; Quack et al. 2008; Blaschko and Lampert 2008; Yakhnenko and Honavar 2009; Qi et al. 2009).”
I know what you did last summer: object-level auto-annotation of holiday snaps (2009, methodology): “First, in order to automatically create a reference database we build on large-scale data crawling from community photo collections [18].”
Visual landmark recognition from Internet photo collections: A large-scale evaluation (2014, methodology): “Landmark object discovery approaches [1, 11, 4, 5, 6] aim at finding interesting buildings and other objects, but no systematic evaluation has been performed that analyzes what types of objects can be discovered and how recognition performance varies with these types.”
Avoiding Confusing Features in Place Recognition (2010, background): “Community photo-collections (such as Flickr) are now often used in computer vision tasks with the focus on clustering [20, 21, 5], 3D modelling [9, 7] and summarization [22].”
Retrieving landmark and non-landmark images from community photo collections (2010, methodology): “For geo-clustering, [15] and [36] use the same algorithm as for visual clustering, whereas [27] and [8] simply quantize locations into overlapping rectangular tiles.”