IAM-OnDB - an on-line English sentence database acquired from handwritten text on a whiteboard

By Marcus Liwicki, Horst Bunke. 2005

230 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

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

In Artificial Intelligence

1. Yoshua Bengio
2. Quoc V. Le
3. J. Urgen Schmidhuber
4. Mohit Bansal
5. Kyunghyun Cho
6. Sergey Levine
7. Ruslan Salakhutdinov
8. Jianfeng Gao

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Yoshua Bengio
6. Trevor Darrell
7. Andrew Zisserman
8. Jitendra Malik

In Evaluation & Benchmarks

1. Alex Graves
2. Yoshua Bengio
3. Junyoung Chung
4. Geoffrey E. Hinton
5. Quoc V. Le
6. Sungjin Ahn
7. Jimmy Ba
8. Andrew M. Dai

Citations in the corpus

• Layer Normalization (2016, methodology): “To show the effectiveness of layer normalization on longer sequences, we performed hand-writing generation tasks using the IAM Online Handwriting Database [Liwicki and Bunke, 2005].”
• Generating Sequences With Recurrent Neural Networks (2013, methodology): “All the data used for this paper were taken from the IAM online handwriting database (IAM-OnDB) [21].”
• HyperNetworks (2016, methodology): “We will train our model on the IAM online handwriting database (Liwicki & Bunke, 2005) and have our model predict pen strokes as per Section 4.2 of (Graves, 2013).”
• LSTM: A Search Space Odyssey (2015, neutral): “2) IAM Online: The IAM Online Handwriting Database [38]4 consists of English sentences as time series of pen movements that have to be mapped to characters.”
• Hierarchical Multiscale Recurrent Neural Networks (2016, methodology): “We extend the evaluation of the HM-LSTM to a real-valued sequence modelling task using IAMOnDB (Liwicki and Bunke, 2005) dataset.”
• Unconstrained On-line Handwriting Recognition with Recurrent Neural Networks (2007, methodology): “Connectionist temporal classification (CTC) [3] is an objective function designed for sequence labelling with RNNs. Unlike previous objective functions it does not require pre-segmented training data, or post-processing to transform the network outputs into transcriptions.”
• Differentiable Learning-to-Normalize via Switchable Normalization (2018, methodology): “(1) We introduce Switchable Normalization (SN), which is applicable in both CNNs and RNNs/LSTMs, and improves the other normalization techniques on many challenging benchmarks and tasks including image recognition in ImageNet (Russakovsky et al., 2015), object detection in COCO (Lin et al., 2014), s”
• Unconstrained Online Handwriting Recognition with Recurrent Neural Networks (2007, methodology): “IAM-OnDB consists of pen trajectories collected from 221 different writers using a ‘smart whiteboard’ [12].”