Residual Enhanced Visual Vectors for on-device image matching
By David M. Chen, Sam S. Tsai, Vijay Ramaseshan Chandrasekhar, Gabriel Takacs, Huizhong Chen, Ramakrishna Vedantham, Radek Grzeszczuk, Bernd Girod. 2011
46 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
- Tomás Pajdla
- Akihiko Torii
- Andrew Zisserman
- Andrea Vedaldi
- Qi Tian
In Computer Vision and Pattern Recognition
- Andrew Zisserman
- Luc Van Gool
- Andrea Vedaldi
- Yi Yang
- Dacheng Tao
- Xiaogang Wang
- Ming-Hsuan Yang
- Jitendra Malik
Citations in the corpus
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “Previous work uses sliding window methods [26] or region grouping methods [5, 6, 19] very successfully for this.”
- VoxCeleb2: Deep Speaker Recognition (2018, methodology): “For example, [26] uses a Siamese feed-forward DNN to discriminatively compare two voices, however this relies on pre-computed MFCC features, whilst [27] also learns the features instead of using MFCCs.”
- All About VLAD (2013, methodology): “As might be expected, papers are now investigating how to improve on the original VLAD formulation [2, 5].”
- Utterance-level Aggregation for Speaker Recognition in the Wild (2019, methodology): “In some cases, the network is further trained for verification using the contrastive loss [2, 3, 23] or other metric learning losses such as the triplet loss [7].”
- Scalar quantization for large scale image search (2012, methodology): “In [28], a compact image signature, called Residual Enhanced Visual Vector, is designed via quantization residue aggregation and classification-aware dimensionality reduction .”
- InLoc: Indoor Visual Localization with Dense Matching and View Synthesis (2019, methodology): “is predicted by transferring the geotag of the most similar image retrieved from database [5], [8], [21], [41], [65], [81], [82].”
- Voxceleb: Large-scale speaker verification in the wild (2020, methodology): “In some cases, the network is further trained for verification using the contrastive loss (Nagrani et al., 2017; Chung et al., 2018; Chen et al., 2011) or other metric learning losses such as the triplet loss (Li et al., 2017).”