Improved Local Coordinate Coding using Local Tangents

By Kai Yu, Tong Zhang. 2010

167 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

High-Performance Neural Networks for Visual Object Classification (2011, neutral): “.37 11 93 0 100 edge 29.11 0.36 15 104 5 100 no 20.26 0.21 11 111 5 100 edge 21.87 0.57 5 120 5 100 hat 21.44 0.44 4 136 5 200 no 19.90 0.16 5 248 5 300 no 19.51 0.18 5 532 5 400 no 19.54 0.16 5 875 (Yu and Zhang, 2010). Unlike Coates et al. (2010), however, we use the original images without any pa”
Bag of visual words and fusion methods for action recognition: Comprehensive study and good practice (2014, neutral): “Typical methods include Local Tangentbased Coding (LTC) [62], Super Vector Coding (SVC) [65], Vector of Locally Aggregated Descriptors (VLAD) [16], and Fisher Vector (FV) [35] .”
Learning image representations from the pixel level via hierarchical sparse coding (2011, background): “90 Extended local coordinate coding (unsupervised) [21] 1.”
Convolutional Deep Belief Networks on CIFAR-10 (2010, background): “In [6], the authors achieve 74.5% with a sparse-coding scheme.”
The Manifold Tangent Classifier (2011, methodology): “More recently, the Local Coordinate Coding (LCC) algorithm (Yu et al., 2009) and its Local Tangent LCC variant (Yu and Zhang, 2010) were proposed to build a a local chart around each training example (with a local low-dimensional coordinate system around it) and use it to define a representation…”
Are sparse representations really relevant for image classification? (2011, background): “challenge winning system presented in [36].”
A Review on Human Activity Recognition Using Vision-Based Method (2017, background): “(2010) [70], 122 Localized soft assignment coding (LSC/SA-k) Liu et al.”
An Analysis of Single-Layer Networks in Unsupervised Feature Learning (2011, background): “Among the algorithms considered in the literature are sparse-coding [22, 17, 32], RBMs [8, 13], sparse RBMs [18], sparse autoencoders [7, 25], denoising auto-encoders [30], “factored” [24] and mean-covariance [23] RBMs, as well as many others [19, 33].”
Histogram of Oriented Normal Vectors for Object Recognition with a Depth Sensor (2012, background): “Yu and Zhang [32] extended the Local Coordinate Coding (LCC) [33] algorithm by exploring the local tangent directions.”
Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives (2012, methodology): “This result has been further extended with the use of local tangent directions (Yu and Zhang, 2010), as well as to multiple layers (Lin et al. , 2010).”
Large Scale Visual Recognition (2012, background): “One line of work is concerned with developing effective feature representations [95, 96, 97, 98] and achieving state of the art performances.”
Beyond spatial pyramids: Receptive field learning for pooled image features (2012, methodology): “Different from other methods, [23] trains LCC on the whole image without pooling.”
Tiled convolutional neural networks (2010, background): “3% Improved Local Coordinate Coding (Improved LCC) [25] 74.”
Direct Modeling of Complex Invariances for Visual Object Features (2013, background): “They commonly use spatial pyramids of some sort (Lazebnik et al., 2006; Yang et al., 2009; Yu & Zhang, 2010), and operate on image patches.”