Encoding CNN Activations for Writer Recognition
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).
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalWriter RetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval
We present BullingerDB, a large-scale benchmark dataset for historical document analysis based on the correspondence of Heinrich Bullinger (1504-1575). The corpus comprises 20,898 pages and 499,222 text lines written by …
Handwritten Text RecognitionWriter adaptation for offline text recognition: An exploration of neural network-based methods
Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the…
Automatic Speech RecognitionHandwriting RecognitionHandwritten Text RecognitionHTR+4Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
Deep convolutional neural networks (CNNs) have proven highly effective for visual recognition, where learning a universal representation from activations of convolutional layer plays a fundamental problem. In this paper,…
Action RecognitionFine-Grained Image Classificationimage-classificationImage Classification+3Writer-Aware CNN for Parsimonious HMM-Based Offline Handwritten Chinese Text Recognition
Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling…
Handwritten Chinese Text RecognitionLanguage ModelingLanguage ModellingTokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition
Inertial measurement unit-based online handwriting recognition enables the recognition of input signals collected across different writing surfaces but remains challenged by uneven character distributions and inter-write…
Handwriting RecognitionData Augmentation