Learned Contextual Feature Reweighting for Image Geo-Localization
By Hyo Jin Kim, Enrique Dunn, Jan-Michael Frahm. 2017
247 citations recorded by the source corpus.
Subfields: Aerospace Engineering, 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 Aerospace Engineering
- Marc Pollefeys
- Torsten Sattler
- Josef Sivic
- Tobias Weyand
- Jack Sim
- Tomás Pajdla
- Akihiko Torii
- Hongdong Li
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Ming-Hsuan Yang
- Huchuan Lu
- Xiaogang Wang
- Dacheng Tao
- Ming-Ming Cheng
- Andrew Zisserman
- Yi Yang
Citations in the corpus
- CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps (2018, background): “[7] learn a weighting mask for the NetVLAD descriptor to focus on image regions containing location cues.”
- Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map (2017, background): “, [6, 8, 11, 19, 25, 28]) try to identify the similar databased images depicting the same landmarks as the query image.”
- Cross-View Policy Learning for Street Navigation (2019, background): “9,27], made from Google Street View imagery and Google Maps street connectivity. 2.2. Cross-View Matching Matching street viewpoints with aerial imagery has been a challenging computer vision problem [23,20,25,34]. Recent approaches include geometry-based methods and deep learning. Li et al. would e”
- Geolocation Estimation of Photos Using a Hierarchical Model and Scene Classification (2018, methodology): “These mainly apply retrieval techniques to match a query image against a reference dataset [3,12,18,20,29,34,46].”
- InLoc: Indoor Visual Localization with Dense Matching and View Synthesis (2019, methodology): “descriptors [81] or (densely extracted) descriptors based on convolutional neural networks (CNN) [5], [41], [46], [91].”
- Learning and aggregating deep local descriptors for instance-level recognition (2020, methodology): “Its contextually re-weighted counterpart, proposed by Kim and Frahm [24], introduces a learned attention map which is generated by a small network.”
- Detect Globally, Refine Locally: A Novel Approach to Saliency Detection (2018, methodology): “Our module is inspired by the success of contextual reweighting network [13] in image geo-localization.”