Zhineng Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhineng Chen has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Shuai Zhao
Chinese Academy of Sciences
3 shared publications- Zhendong Mao
University of Science and Technology of China, Hefei, China
3 shared publications Bo Xu
Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2 shared publicationsHongtao Xie
University of Science and Technology of China
2 shared publicationsWenming Guo
Beijing University of Posts and Telecommunications
2 shared publications- Yangyang Li
China Academy of Electronics and Information Technology, Beijing, China
2 shared publications
Latest Publications
- 30 March 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (45-46) , 33925-33942
Context propagation embedding network for weakly supervised semantic segmentation
- 30 March 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (45-46) , 33925-33942
Context propagation embedding network for weakly supervised semantic segmentation
- 20 March 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (11) , 16247-16265
Object-difference drived graph convolutional networks for visual question answering
- 20 March 2020
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 80 (11) , 16247-16265
Object-difference drived graph convolutional networks for visual question answering
- Open Access
NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
Scene text recognition has attracted a great many researches due to its importance to various applications. Existing methods mainly adopt recurrence or convolution based networks. Though have obtained good performance, these methods still suffer from two limitations: slow training speed due to the internal recurrence of RNNs, and high complexity due to stacked convolutional layers for long-term feature extraction. This paper, for the first time, proposes a no-recurrence sequence-to-sequence text recognizer, named NRTR, that dispenses with recurrences and convolutions entirely. NRTR follows the encoder-decoder paradigm, where the encoder uses stacked self-attention to extract image features, and the decoder applies stacked self-attention to recognize texts based on encoder output. NRTR relies solely on self-attention mechanism thus could be trained with more parallelization and less complexity. Considering scene image has large variation in text and background, we further design a modality-transform block to effectively transform 2D input images to 1D sequences, combined with the encoder to extract more discriminative features. NRTR achieves state-of-the-art or highly competitive performance on both regular and irregular benchmarks, while requires only a small fraction of training time compared to the best model from the literature (at least 8 times faster).
Open AccessNRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
Scene text recognition has attracted a great many researches due to its importance to various applications. Existing methods mainly adopt recurrence or convolution based networks. Though have obtained good performance, these methods still suffer from two limitations: slow training speed due to the internal recurrence of RNNs, and high complexity due to stacked convolutional layers for long-term feature extraction. This paper, for the first time, proposes a no-recurrence sequence-to-sequence text recognizer, named NRTR, that dispenses with recurrences and convolutions entirely. NRTR follows the encoder-decoder paradigm, where the encoder uses stacked self-attention to extract image features, and the decoder applies stacked self-attention to recognize texts based on encoder output. NRTR relies solely on self-attention mechanism thus could be trained with more parallelization and less complexity. Considering scene image has large variation in text and background, we further design a modality-transform block to effectively transform 2D input images to 1D sequences, combined with the encoder to extract more discriminative features. NRTR achieves state-of-the-art or highly competitive performance on both regular and irregular benchmarks, while requires only a small fraction of training time compared to the best model from the literature (at least 8 times faster).
- 10 October 2019
- Published by Springer Nature
- p. 712-720
ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
- 10 October 2019
- Published by Springer Nature
- p. 712-720
ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
- Open Access
ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e.g., symmetric contracting and expansive paths as well as lateral skip-connections. It remains a research direction to devise novel architectures to further benefit the segmentation. In this paper, we develop an ACE-net that aims to enhance the feature representation and utilization by augmenting the contracting and expansive paths. In particular, we augment the paths by the recently proposed advanced techniques including ASPP, dense connection and deep supervision mechanisms, and novel connections such as directly connecting the raw image to the expansive side. With these augmentations, ACE-net can utilize features from multiple sources, scales and reception fields to segment while still maintains a relative simple architecture. Experiments on two typical biomedical segmentation tasks validate its effectiveness, where highly competitive results are obtained in both tasks while ACE-net still runs fast at inference.
Open AccessACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
Nowadays U-net-like FCNs predominate various biomedical image segmentation applications and attain promising performance, largely due to their elegant architectures, e.g., symmetric contracting and expansive paths as well as lateral skip-connections. It remains a research direction to devise novel architectures to further benefit the segmentation. In this paper, we develop an ACE-net that aims to enhance the feature representation and utilization by augmenting the contracting and expansive paths. In particular, we augment the paths by the recently proposed advanced techniques including ASPP, dense connection and deep supervision mechanisms, and novel connections such as directly connecting the raw image to the expansive side. With these augmentations, ACE-net can utilize features from multiple sources, scales and reception fields to segment while still maintains a relative simple architecture. Experiments on two typical biomedical segmentation tasks validate its effectiveness, where highly competitive results are obtained in both tasks while ACE-net still runs fast at inference.
- 1 July 2019
- Published by Elsevier in Pattern Recognition Letters
- Vol. 125, 228-234
Pyrboxes: An efficient multi-scale scene text detector with feature pyramids
- 1 July 2019
- Published by Elsevier in Pattern Recognition Letters
- Vol. 125, 228-234
Pyrboxes: An efficient multi-scale scene text detector with feature pyramids
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (5) , 1248-1260
Double-Bit Quantization and Index Hashing for Nearest Neighbor Search
As binary code is storage efficient and fast to compute, it has become a trend to compact real-valued data to binary codes for the nearest neighbors (NN) search in a large-scale database. However, the use of binary code for the NN search leads to low retrieval accuracy. To increase the discriminability of the binary codes of existing hash functions, in this paper, we propose a framework of double-bit quantization and index hashing for an effective NN search. The main contributions of our framework are: first, a novel double-bit quantization (DBQ) is designed to assign more bits to each dimension for higher retrieval accuracy; second, a double-bit index hashing (DBIH) is presented to efficiently index binary codes generated by DBQ; and third, a weighted distance measurement for DBQ binary codes is put forward to re-rank the search results from DBIH. The empirical results on three benchmark databases demonstrate the superiority of our framework over existing approaches in terms of both retrieval accuracy and query efficiency. Specifically, we observe an absolute improvement on precision of 10%–25% in most cases and the query speed increases over 30 times compared to traditional binary embedding methods and linear scan, respectively.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (5) , 1248-1260
Double-Bit Quantization and Index Hashing for Nearest Neighbor Search
As binary code is storage efficient and fast to compute, it has become a trend to compact real-valued data to binary codes for the nearest neighbors (NN) search in a large-scale database. However, the use of binary code for the NN search leads to low retrieval accuracy. To increase the discriminability of the binary codes of existing hash functions, in this paper, we propose a framework of double-bit quantization and index hashing for an effective NN search. The main contributions of our framework are: first, a novel double-bit quantization (DBQ) is designed to assign more bits to each dimension for higher retrieval accuracy; second, a double-bit index hashing (DBIH) is presented to efficiently index binary codes generated by DBQ; and third, a weighted distance measurement for DBQ binary codes is put forward to re-rank the search results from DBIH. The empirical results on three benchmark databases demonstrate the superiority of our framework over existing approaches in terms of both retrieval accuracy and query efficiency. Specifically, we observe an absolute improvement on precision of 10%–25% in most cases and the query speed increases over 30 times compared to traditional binary embedding methods and linear scan, respectively.
- 10 May 2018
- Published by Springer Nature
- p. 346-355
Tire X-ray Image Impurity Detection Based on Multiple Kernel Learning
- 10 May 2018
- Published by Springer Nature
- p. 346-355
Tire X-ray Image Impurity Detection Based on Multiple Kernel Learning
- 31 December 2016
- Published by Springer Nature
- p. 638-648
Micro-Expression Recognition by Aggregating Local Spatio-Temporal Patterns
- 31 December 2016
- Published by Springer Nature
- p. 638-648
Micro-Expression Recognition by Aggregating Local Spatio-Temporal Patterns
- 22 October 2016
- Published by Springer Nature
- p. 525-536
Chinese Image Text Recognition with BLSTM-CTC: A Segmentation-Free Method
- 22 October 2016
- Published by Springer Nature
- p. 525-536
Chinese Image Text Recognition with BLSTM-CTC: A Segmentation-Free Method