I know what you did last summer: object-level auto-annotation of holiday snaps

By Stephan Gammeter, Lukas Bossard, Till Quack, Luc Van Gool. 2009

102 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): “Instead of matching against a ﬂat collection of photos, landmark recognition systems [1, 14, 22, 37, 54] build a database of landmark buildings by clustering images from internet photo collections.”
Image webs: Computing and exploiting connectivity in image collections (2010, background): “As we brieﬂy survey in Section 2, considerable research has already been devoted to exploiting match links to detect images of popular landmarks [25] and to annotate them [11], or for 3-”
Creating Summaries from User Videos (2014, methodology): “We follow this idea and use the framework of [8] to classify the scene in a frame as famous or non-famous, based on the presence of famous buildings.”
Retrieving landmark and non-landmark images from community photo collections (2010, methodology): “We count inliers and whenever a new maximum is found, we find a least squares estimate of an affine transform from the given inliers and store the best model so far—this is the “simple” method of Locally Optimized RANSAC (LO-RANSAC) [4].”
Fast image-based localization using direct 2D-to-3D matching (2011, background): “Image-based localization is also an important part in the pipeline of higher-level computer vision tasks such as semantic object annotation [9] and can be used as an initial pose estimate to speed up large-scale reconstructions from Internet photo collections [27].”
Visual landmark recognition from Internet photo collections: A large-scale evaluation (2014, methodology): “[2] estimate bounding boxes around the landmark in each image in a cluster and remove every visual word from the index that never occurs inside a bounding box.”
Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking (2018, methodology): “Numerous methods of image retrieval [7, 31, 5, 27, 47, 3, 48, 20, 37, 10] and visual localization [9, 1] have used these datasets for evaluation.”
Large-scale image retrieval with compressed Fisher vectors (2010, background): “With such techniques, [9] reports a compression factor of approximately 2 while [13] reports a factor of 4.”