Learning Partially Shared Dictionaries for Domain Adaptation
Viresh Ranjan,Gaurav Harit,C. V. Jawahar +2 more
- Vol. 9010, pp 247-261
TLDR
This work presents a dictionary learning based approach to tackle the problem of domain mismatch and conducts cross-domain object recognition experiments on popular benchmark datasets and shows improvement in results over the existing state of art domain adaptation approaches.Citations
More filters
Journal ArticleDOI
On discrete cosine transform
TL;DR: In this article, a generalized discrete cosine transform with three parameters was proposed and its orthogonality was proved for some new cases, and a new type of discrete W transform was proposed.
Journal ArticleDOI
Projected Transfer Sparse Coding for cross domain image representation
Xiao Li,Min Fang,Ju-Jie Zhang +2 more
TL;DR: A Projected Transfer Sparse Coding algorithm that learns the projection matrix, the discriminative sparse representations, and the dictionary in a unified objective function, and yields state-of-the-art results on image representation.
Proceedings ArticleDOI
Feature Projection-Based Unsupervised Domain Adaptation for Acoustic Scene Classification
TL;DR: This work proposes an unsupervised domain adaptation method for ASC based on the projection of spectro-temporal features extracted from both the source and target domain onto the principal subspace spanned by the eigenvectors of the sample covariance matrix of source-domain training data.
References
More filters
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Book
Compressed sensing
TL;DR: It is possible to design n=O(Nlog(m)) nonadaptive measurements allowing reconstruction with accuracy comparable to that attainable with direct knowledge of the N most important coefficients, and a good approximation to those N important coefficients is extracted from the n measurements by solving a linear program-Basis Pursuit in signal processing.
Book
A wavelet tour of signal processing
TL;DR: An introduction to a Transient World and an Approximation Tour of Wavelet Packet and Local Cosine Bases.
Proceedings ArticleDOI
Object recognition from local scale-invariant features
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Journal ArticleDOI
Speeded-Up Robust Features (SURF)
TL;DR: A novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.