2021

Vision Transformer for Fast and Efficient Scene Text Recognition

Atienza, Rowel

Understand

Scene text recognition (STR) enables computers to read text in natural scenes such as object labels, road signs and instructions.

STR helps machines perform informed decisions such as what object to pick, which direction to go, and what is the next step of action.
In the body of work on STR, the focus has always been on recognition accuracy.
There is little emphasis placed on speed and computational efficiency which are equally important especially for energy-constrained mobile machines.

Built on

Bookstein, F.L.: Principal warps: Thin-plate splines and the decomposition of deformations. Trans on Pattern Analysis and Machine Intelligence 11
1989
Earlier work this paper cites.
Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R., Ashida, K., Nagai, H., Okamoto, M., Yamamoto, H., et al.: Icdar 2003 robust reading competitions: entries, results, and future directions. Intl Journal of Document Analysis and Recognition 7
2005
Earlier work this paper cites.
Graves, A., Fernández, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML. pp. 369–376 (2006)
2006
Earlier work this paper cites.
Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: ICCV. pp. 1457–1464. IEEE (2011)
2011
Earlier work this paper cites.
Mishra, A., Alahari, K., Jawahar, C.: Scene text recognition using higher order language priors. In: BMVC. BMVA (2012)
2012
Earlier work this paper cites.
Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR. pp. 3538–3545. IEEE (2012)
2012
Earlier work this paper cites.
Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
Original
2012
Earlier work this paper cites.
Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De Las Heras, L.P.: Icdar 2013 robust reading competition. In: ICDAR. pp. 1484–1493. IEEE (2013)
2013
Earlier work this paper cites.
Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: ICCV. pp. 569–576 (2013)
2013
Earlier work this paper cites.
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)
Original
2014
Earlier work this paper cites.
Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. NIPS Workshop on Deep Learning (2014)
2014
Earlier work this paper cites.
Risnumawan, A., Shivakumara, P., Chan, C.S., Tan, C.L.: A robust arbitrary text detection system for natural scene images. Expert Systems with Applications 41
2014
Earlier work this paper cites.
Yao, C., Bai, X., Liu, W.: A unified framework for multioriented text detection and recognition. Trans on Image Processing 23
2014
Earlier work this paper cites.
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV. pp. 1026–1034 (2015)
2015
Earlier work this paper cites.

Similar

Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Original
2015
Cited alongside, same era.
Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., et al.: Icdar 2015 competition on robust reading. In: ICDAR. pp. 1156–1160. IEEE (2015)
2015
Cited alongside, same era.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. Intl Journal of Computer Vision 115
2015
Cited alongside, same era.
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. ICLR (2015)
2015
Cited alongside, same era.
Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: CVPR. pp. 2315–2324 (2016)
2016
Cited alongside, same era.
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR. pp. 770–778 (2016)
2016
Cited alongside, same era.
Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)
Original
2016
Cited alongside, same era.
Lee, C.Y., Osindero, S.: Recursive recurrent nets with attention modeling for ocr in the wild. In: CVPR. pp. 2231–2239 (2016)
2016
Cited alongside, same era.
Liu, W., Chen, C., Wong, K.Y.K., Su, Z., Han, J.: Star-net: a spatial attention residue network for scene text recognition. In: BMVC. vol. 2, p. 7 (2016)
2016
Cited alongside, same era.
Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. Trans on Pattern Analysis and Machine Intelligence 39
2016
Cited alongside, same era.
Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: CVPR. pp. 4168–4176 (2016)
2016
Cited alongside, same era.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., Polosukhin, I.: Attention is all you need. In: NeuRIPS. pp. 6000–6010 (2017)
2017
Cited alongside, same era.

Then

Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: ICCV. pp. 4715–4723 (2019)
2019
Later among the works it cites.
Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: A simple and strong baseline for irregular text recognition. In: AAAI. vol. 33, pp. 8610–8617 (2019)
2019
Later among the works it cites.
Sheng, F., Chen, Z., Xu, B.: Nrtr: A no-recurrence sequence-to-sequence model for scene text recognition. In: ICDAR. pp. 781–786. IEEE (2019)
2019
Later among the works it cites.
Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: ICML. pp. 6105–6114. PMLR (2019)
2019
Later among the works it cites.
Zhan, F., Lu, S.: Esir: End-to-end scene text recognition via iterative image rectification. In: CVPR. pp. 2059–2068 (2019)
2019
Later among the works it cites.
Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: A survey. arXiv preprint arXiv:2005.03492 (2020)
Original
2020
Later among the works it cites.
Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: Randaugment: Practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 702–703 (2020)
2020
Later among the works it cites.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2020)
2020
Later among the works it cites.
Lee, J., Park, S., Baek, J., Oh, S.J., Kim, S., Lee, H.: On recognizing texts of arbitrary shapes with 2d self-attention. In: CVPR Workshops. pp. 546–547 (2020)
2020
Later among the works it cites.
Litman, R., Anschel, O., Tsiper, S., Litman, R., Mazor, S., Manmatha, R.: Scatter: selective context attentional scene text recognizer. In: CVPR. pp. 11962–11972 (2020)
2020
Later among the works it cites.
Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., Wang, W.: Seed: Semantics enhanced encoder-decoder framework for scene text recognition. In: CVPR. pp. 13528–13537 (2020)
2020
Later among the works it cites.
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877 (2020)
Original
2020
Later among the works it cites.
Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: CVPR. pp. 12113–12122 (2020)
2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…