Maximum Margin Correlation Filter: A New Approach for Localization and Classification

102 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.

Correlation filters with limited boundaries (2014, methodology): “A full discussion on other correlation filters such as Optimal Tradeoff Filters (OTF) [21], Unconstrained MACE (UMACE) [24] filters, Multi-Channel Correlation Filters (MCCF) [16], Maximum Margin Correlation Filters (MMCF) [22], kernel MOSSE [13], etc.”
End-to-End Representation Learning for Correlation Filter Based Tracking (2017, background): “Notable efforts have been devoted to its improvement, for example by mitigating the effect of periodic boundaries [10, 15, 8], incorporating multi-resolution feature maps [21, 9] and augmenting the objective with a more robust loss [26].”
TILDE: A Temporally Invariant Learned DEtector (2014, methodology): “This way of enforcing the shape of the responses is a generalization of the approach of [29] to any type of shape.”
Real-time part-based visual tracking via adaptive correlation filters (2015, background): “Correlation filter based trackers have been proven to be competitive with far more complicated tracking methods [7, 12, 17, 33].”
Decomposition-Based Transfer Distance Metric Learning for Image Classification (2014, methodology): “Following [9], we choose V (xi, xj , yij) = g(yij [1− ‖xi − xj‖A]) and adopt the hinge loss [33] for g, i.”