Image retrieval with geometry-preserving visual phrases

By Yimeng Zhang, Zhaoyin Jia, Tsuhan Chen. Computer Vision and Pattern Recognition, 2011

336 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/de90778bf9548820f32d5951ea936004ff17baff

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

Ranking consistency for image matching and object retrieval (2014, background): “Recently, there has been a great deal of research to increase the accuracy of object retrieval by measuring the spatial consistency between the query and result images [5,11,12].”
Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern (2014, background): “…role in a wide range of applications that includes static and dynamic texture classification [1], [2], [3], [4], [5], object and scene recognition [6], [7], [8], [9], [10], face detection and recognition [11], image retrieval [12], [13], stereo correspondence, 3D reconstruction and many more.”
Effective and Efficient Global Context Verification for Image Copy Detection (2017, methodology): “State-of-the-art near-duplicate detection methods such as [7], [12], [16], [17], [30]–[34] also rely on the BOW model.”
Image Geo-Localization Based on MultipleNearest Neighbor Feature Matching UsingGeneralized Graphs (2014, background): “Index Terms—Geo-location, image localization, Generalized Minimum Clique Problem (GMCP), generalized minimum spanning tree (GMST), feature matching, multiple nearest neighbor feature matching, feature correspondence, generalized graphs Ç”
Sketch-based manga retrieval using manga109 dataset (2015, methodology): “This kind of task has been tackled in spatial veriﬁcation-based reranking methods [25], [26], [27], [28], [29], [30], [31].”
Visual Place Recognition with Repetitive Structures (2015, neutral): “Examples include: (i) learning better visual vocabularies [21, 28]; (ii) developing quantization methods less prone to quantization errors [14, 27, 44]; (iii) combining returns from multiple query images depicting the same scene [4, 6]; (iv) exploiting the 3D or graph structure of the database [11,…”
Good Practice in CNN Feature Transfer (2016, background): “From this observation, it is desirable that further discriminative cues be incorporated in the bottom features, e.g., spatial constraints [47], or multi-feature fusion [48].”
Person Re-identification: Past, Present and Future (2016, background): “A posting stores the image ID and the term frequency (TF) of the indexed descriptor and in a series of works, a number of other meta data can be stored, such as binary signature [148], feature coordinates [149], etc .”
Exhaustive Geometric Veriﬁcation for Image Retrieval Accepted for ECCV 2012 (background): “Several authors have tried to enforce geometric consistency of the matches using multiple bins during voting [2, 18, 19].”
Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons (2016, methodology): “To this end, researchers propose visual phrase [23, 24] as a mid-level data structure connecting low-level descriptors and high-level”
SuperGlue: Learning Feature Matching With Graph Neural Networks (2019, background): “We can for example consider its spatial and visual relationship with other co-visible keypoints, such as ones that are salient [29], self-similar [48], statistically co-occurring [65], or adjacent [52].”
Leveraging Structure from Motion to Learn Discriminative Codebooks for Scalable Landmark Classification (2013, background): “Recently, feature correspondences were exploited to learn spatial co-occurrence statistics [34, 36].”