Aggregation Cross-Entropy for Sequence Recognition

Xie, Zhong; Huang, Yao‐Xiong; Zhu, Youwen; Jin, Lianwen; Liu, Yuliang; Xie, Lele

doi:10.1109/cvpr.2019.00670

Cited by 109 publications

(56 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the confusion among the 7360 classes is higher, Table IX shows an overall comparison of our proposed method and other state-of-the-art methods without/with a language model on the ICDAR 2013 competition set. we list the state-of-theart oversegmentation method heterogeneous CNN [7], CNNs-RNNLM [8] and the segmentationfree method SMDLSTM-CTC [15], CNN-ACE [16] in Table IX for comparison. With the same configuration of vocabulary size (4 more garbage classes adopted in our HMM system), the proposed WCNN-PHMM yielded the best performance whether a language model was employed or not.…”

Section: ) Visualization Analysis For Writer Codementioning

confidence: 99%

“…In [15], the authors used separable MDLSTM-RNN (SMDLSTM-RNN) with CTC loss, instead of the traditional LSTM-CTC method. More recently, the authors in [16] proposed a novel aggregation cross-entropy loss for sequence recognition, which was shown to exhibit competitive performance for offline HCTR. In [17], we verified that combining hybrid deep CNN-HMM (DCNN-HMM) with a powerful language model could achieve the best reported results of the segmentation-free approaches on the ICDAR 2013 competition dataset.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Wang

2020

Pattern Recognition

View full text Add to dashboard Cite

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 each of the large vocabulary of Chinese characters with a uniform and fixed number of hidden states requires high memory and computational costs and makes the tens of thousands of HMM state classes confusing. Another key issue of CNN-HMM for HCTR is the diversified writing style, which leads to model strain and a significant performance decline for specific writers. To address these issues, we propose a writer-aware CNN based on parsimonious HMM (WCNN-PHMM). First, PHMM is designed using a data-driven state-tying algorithm to greatly reduce the total number of HMM states, which not only yields a compact CNN by state sharing of the same or similar radicals among different Chinese characters but also improves the recognition accuracy due to the more accurate modeling of tied states and the lower confusion among them. Second, WCNN integrates each convolutional layer with one adaptive layer fed by a writer-dependent vector, namely, the writer code, to extract the irrelevant variability in writer information to improve recognition performance.The parameters of writer-adaptive layers are jointly optimized with other network parameters in the training stage, while a multiple-pass decoding strategy is adopted to learn the writer code and generate recognition results. Validated on the ICDAR 2013 competition of CASIA-HWDB database, the more compact WCNN-PHMM of a 7360-class vocabulary can achieve a relative character error rate (CER) reduction of 16.6% over the conventional CNN-HMM without considering language modeling. By adopting a powerful hybrid language model (N-gram language model and recurrent neural network language model), the CER of WCNN-PHMM is reduced to 3.17%. Moreover, the state-tying results of PHMM explicitly show the information sharing among similar characters and the confusion reduction of tied state classes. Finally, we visualize the learned writer codes and demonstrate the strong relationship with the writing styles of different writers. To the best of our knowledge, WCNN-PHMM yields the 2 best results on the ICDAR 2013 competition set, demonstrating its power when enlarging the size of the character vocabulary. Index TermsOffline handwritten Chinese text recognition, writer-aware CNN, parsimonious HMM, state tying, adaptation, hybrid language model.

show abstract

Section: ) Visualization Analysis For Writer Codementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Wang

2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…In practical use, the model prediction is generated by the RNN model. Following the recommendations of Xie et al [47], the overall computation complexity of the proposed method consists of the four computation complexities of O(1), O(|C ε |), O(|C ε |), and O(|C ε |). The computation complexity of the loss function is O(|C ε |).…”

Section: Computational Complexity Analysismentioning

confidence: 99%

Lithuanian Speech Recognition Using Purely Phonetic Deep Learning

Pipiras¹,

Maskeliūnas

Damaševičius

2019

Computers

View full text Add to dashboard Cite

Automatic speech recognition (ASR) has been one of the biggest and hardest challenges in the field. A large majority of research in this area focuses on widely spoken languages such as English. The problems of automatic Lithuanian speech recognition have attracted little attention so far. Due to complicated language structure and scarcity of data, models proposed for other languages such as English cannot be directly adopted for Lithuanian. In this paper we propose an ASR system for the Lithuanian language, which is based on deep learning methods and can identify spoken words purely from their phoneme sequences. Two encoder-decoder models are used to solve the ASR task: a traditional encoder-decoder model and a model with attention mechanism. The performance of these models is evaluated in isolated speech recognition task (with an accuracy of 0.993) and long phrase recognition task (with an accuracy of 0.992).

show abstract

“…In recent years, deep learning has achieved tremendous success in fundamental computer vision applications such as image recognition [8,27,30], object detection [6,15,20,22] and image segmentation [7,17]. In light of this, deep learning has also been applied to areas such as text detection [4,34,46] and text recognition [11,13,35,37,40], as well as their downstream tasks such as key information extraction [5,29,39] and named entity recognition [3,36].…”

Section: Introductionmentioning

confidence: 99%

Mmocr

Kuang

Sun

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

We present MMOCR-an open-source toolbox which provides a comprehensive pipeline for text detection and recognition, as well as their downstream tasks such as named entity recognition and key information extraction. MMOCR implements 14 state-of-theart algorithms, which is significantly more than all the existing open-source OCR projects we are aware of to date. To facilitate future research and industrial applications of text recognition-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of text detection, recognition and understanding. MMOCR is publicly released at https://github.com/open-mmlab/mmocr.

show abstract

Aggregation Cross-Entropy for Sequence Recognition

Cited by 109 publications

References 45 publications

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Writer-aware CNN for parsimonious HMM-based offline handwritten Chinese text recognition

Lithuanian Speech Recognition Using Purely Phonetic Deep Learning

Mmocr

Contact Info

Product

Resources

About