Proceedings of the 5th International Conference on Image and Video Retrieval

By Till Quack, Vittorio Ferrari, Luc Van Gool. 2006

630 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, background): “While global features have the benefit to retrieve diverse natural scene images based on ambient information, local image features yield higher precision in retrieving structured objects such as buildings and are thus more frequently used [8,9,10,11,12,13,14,15,16].”
PlaNet - Photo Geolocation with Convolutional Neural Networks (2016, background): “Most local feature based approaches therefore focus on localization within cities, either based on photos from photo sharing websites [5, 36] or street view [2, 7, 26, 27, 43, 51, 52].”
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition (2015, methodology): “In detail, as the test queries are perspective images from camera phones, each panorama is represented by a set of perspective images sampled evenly in different orientations and two elevation angles [11, 24, 35, 80].”
Generic 3D Representation via Pose Estimation and Matching (2016, methodology): “This is different from many previous works [3,26,59,52,8,14,20] from both visual odometery and SfM literature that perform the estimation through a two step process consisting of finding point correspondences between images followed by pose estimation.”
Weighted Substructure Mining for Image Analysis (2007, neutral): “[11] use frequent item set mining on interest points extracted for each video frame in a video sequence.”
Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval (2007, neutral): “These response images may subsequently be ranked using spatial information to ensure that the response and the query not only contain similar features, but that the features occur in compatible spatial configurations [14, 17, 18, 20].”
World-scale mining of objects and events from community photo collections (2008, neutral): “Mining objects from visual data has been proposed for video for instance in [28, 21].”
Learned Contextual Feature Reweighting for Image Geo-Localization (2017, methodology): “We collected 6K Flickr images with GPS-tags, and 17K Google Streetview Research Dataset images, both covering the same region as the reference images in the evaluation benchmark [10].”
Singularities, Expanders and Topology of Maps. Part 2: from Combinatorics to Topology Via Algebraic Isoperimetry (2010, background): “Barany’s bound baff(n) ≥ 1/(n + 1)n+1 was improved by a polynomial factor in [W] (also see [DeHST]), but an exponential lower bound, baff(n) ≥ βn for some β > 0, remains problematic.”
Geometric min-Hashing: Finding a (thick) needle in a haystack (2009, neutral): “The closest work on this topic is [25] and [22], the databases used in this paper are an order of magnitude larger.”
Geometric Loss Functions for Camera Pose Regression with Deep Learning (2017, methodology): “Traditionally, this has been modelled as an image retrieval problem [6, 9, 53, 45] enabling the use of efficient and scalable retrieval approaches [35, 38] such as Bag-of-Words (BoW) [47], VLAD [17, 10], and Fisher vectors [18].”
Efficient & Effective Prioritized Matching for Large-Scale Image-Based Localization (2017, methodology): “In contrast to our method, these approaches only approximate the pose of the query camera [14], [17], [18], [20].”
Spatial Pyramid-Enhanced NetVLAD With Weighted Triplet Loss for Place Recognition (2020, methodology): “[9] used GPS to narrow the searching space in an image database.”
Image Retrieval for Image-Based Localization Revisited (2012, background): “Further information, such as building outlines or 3D geometry, can be combined with the image database to improve localization approaches [2, 4].”
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map (2017, methodology): “Note that previous work on SF-0 also used GPS prior [12].”
Mining Mid-level Features for Image Classification (2014, neutral): “…of computer vision problems, including image clas-siﬁcation (Kim et al. 2010; Nowozin et al. 2007; Yuan et al. 2007, 2011), action recognition (Gilbert et al. 2009; Quack et al. 2006), scene understanding (Yao and Fei-Fei 2010), object recognition and object-part detection (Quack et al. 2007).”
Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD (2015, methodology): “Our method falls into the category of image-retrieval-based methods where a geolocation of the image is approximated by identifying geo-tagged reference images depicting the same place [3, 5, 16, 35].”