Encoding CNN activations for writer recognition
V Christlein, A Maier - 2018 13th IAPR international workshop …, 2018 - ieeexplore.ieee.org
2018 13th IAPR international workshop on document analysis systems …, 2018•ieeexplore.ieee.org
The encoding of local features is an essential part for writer identification and writer retrieval.
While CNN activations have already been used as local features in related works, the
encoding of these features has attracted little attention so far. In this work, we compare the
established VLAD encoding with triangulation embedding. We further investigate
generalized max pooling as an alternative to sum pooling and the impact of decorrelation
and Exemplar SVMs. With these techniques, we set new standards on two publicly available …
While CNN activations have already been used as local features in related works, the
encoding of these features has attracted little attention so far. In this work, we compare the
established VLAD encoding with triangulation embedding. We further investigate
generalized max pooling as an alternative to sum pooling and the impact of decorrelation
and Exemplar SVMs. With these techniques, we set new standards on two publicly available …
The encoding of local features is an essential part for writer identification and writer retrieval. While CNN activations have already been used as local features in related works, the encoding of these features has attracted little attention so far. In this work, we compare the established VLAD encoding with triangulation embedding. We further investigate generalized max pooling as an alternative to sum pooling and the impact of decorrelation and Exemplar SVMs. With these techniques, we set new standards on two publicly available datasets (ICDAR13, KHATT).
ieeexplore.ieee.org
以上显示的是最相近的搜索结果。 查看全部搜索结果