Data-driven visual similarity for cross-domain image matching

By Abhinav Shrivastava, Tomasz Malisiewicz, Abhinav Kumar Gupta, Alexei A. Efros. 2011

305 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Image-Based Recommendations on Styles and Substitutes (2015, background): “The system shares these characteristics with more common forms of recommender system, but does so on the basis of the appearance of the object, rather than metadata, reviews, or similar.”
Unsupervised Discovery of Mid-Level Discriminative Patches (2012, background): “Our work is also informed by [32], who show that discriminative machinery, such as a linear SVM, could be successfully used in a fully unsupervised manner.”
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, background): “Shrivista et al [52] show that an Exemplar SVM trained on a huge database is capable of classification of both photographs and artwork.”
Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching (2017, background): “This is a crossdomain image matching problem [29], [30], [31].”
Data-driven exemplar model selection (2014, methodology): “We train ESVMs using 5000 random images from Flickr as our negative set [34].”
Multi-Resolution Language Grounding with Weak Supervision (2014, background): “An exemplar SVM is an SVM ﬁt with one positive and many negative instances, allowing us to deﬁne an example by what it is not (Malisiewicz et al., 2011; Shrivastava et al., 2011).”
Learning and Calibrating Per-Location Classifiers for Visual Place Recognition (2013, methodology): “The exemplar support vector machine can be learnt at query time where the weight vector is used as a new query image representation (Shrivastava et al. 2011).”
Improving Image-Sentence Embeddings Using Large Weakly Annotated Photo Collections (2014, background): “to multi-view learning [13, 7], transfer learning [14–16], and methods that use Internet data to help recognition [17–21].”
How do humans sketch objects? (2012, methodology): “Retrieval results are purely based on geometric similarity between the sketch and the image content [Chalechale et al. 2005; Eitz et al. 2011a; Shrivastava et al. 2011; Eitz et al. 2012].”
Learning Visual Affordances for Robotic Manipulation (2019, background): “), in this chapter we refer to it as a cross-domain image matching problem ([99, 106, 11]).”
How Do You Tell a Blackbird from a Crow? (2013, background): “[21] weight regions in an image by their distinctiveness for purposes of cross-domain similar image search.”