Search

Your search keyword '"Chen, Song-Lu"' showing total 42 results
Start Over Author "Chen, Song-Lu"

Refine your results

42 results on '"Chen, Song-Lu"'

1. HQOD: Harmonious Quantization for Object Detection

Author

Huang, Long, Dong, Zhiwei, Chen, Song-Lu, Zhang, Ruiyao, Ti, Shutong, Chen, Feng, and Yin, Xu-Cheng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high classification scores but poor localization positions or low classification scores but accurate localization positions will worsen the performance of detectors after Non-Maximum Suppression. Furthermore, when object detectors collaborate with Quantization-Aware Training (QAT), we observe that the task inharmony problem will be further exacerbated, which is considered one of the main causes of the performance degradation of quantized detectors. To tackle this issue, we propose the Harmonious Quantization for Object Detection (HQOD) framework, which consists of two components. Firstly, we propose a task-correlated loss to encourage detectors to focus on improving samples with lower task harmony quality during QAT. Secondly, a harmonious Intersection over Union (IoU) loss is incorporated to balance the optimization of the regression branch across different IoU levels. The proposed HQOD can be easily integrated into different QAT algorithms and detectors. Remarkably, on the MS COCO dataset, our 4-bit ATSS with ResNet-50 backbone achieves a state-of-the-art mAP of 39.6%, even surpassing the full-precision one., Comment: 2024 IEEE International Conference on Multimedia and Expo (ICME), July 15 - July 19, 2024, Niagra Falls, Ontario, Canada

Published
2024

2. InterFormer: Interactive Local and Global Features Fusion for Automatic Speech Recognition

Author

Lai, Zhi-Hao, Zhang, Tian-Hao, Liu, Qi, Qian, Xinyuan, Wei, Li-Fang, Chen, Song-Lu, Chen, Feng, and Yin, Xu-Cheng

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

The local and global features are both essential for automatic speech recognition (ASR). Many recent methods have verified that simply combining local and global features can further promote ASR performance. However, these methods pay less attention to the interaction of local and global features, and their series architectures are rigid to reflect local and global relationships. To address these issues, this paper proposes InterFormer for interactive local and global features fusion to learn a better representation for ASR. Specifically, we combine the convolution block with the transformer block in a parallel design. Besides, we propose a bidirectional feature interaction module (BFIM) and a selective fusion module (SFM) to implement the interaction and fusion of local and global features, respectively. Extensive experiments on public ASR datasets demonstrate the effectiveness of our proposed InterFormer and its superior performance over the other Transformer and Conformer models., Comment: Accepted by Interspeech 2023

Published
2023

3. Rethinking Speech Recognition with A Multimodal Perspective via Acoustic and Semantic Cooperative Decoding

Author

Zhang, Tian-Hao, Qin, Hai-Bo, Lai, Zhi-Hao, Chen, Song-Lu, Liu, Qi, Chen, Feng, Qian, Xinyuan, and Yin, Xu-Cheng

Subjects
Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Attention-based encoder-decoder (AED) models have shown impressive performance in ASR. However, most existing AED methods neglect to simultaneously leverage both acoustic and semantic features in decoder, which is crucial for generating more accurate and informative semantic states. In this paper, we propose an Acoustic and Semantic Cooperative Decoder (ASCD) for ASR. In particular, unlike vanilla decoders that process acoustic and semantic features in two separate stages, ASCD integrates them cooperatively. To prevent information leakage during training, we design a Causal Multimodal Mask. Moreover, a variant Semi-ASCD is proposed to balance accuracy and computational cost. Our proposal is evaluated on the publicly available AISHELL-1 and aidatatang_200zh datasets using Transformer, Conformer, and Branchformer as encoders, respectively. The experimental results show that ASCD significantly improves the performance by leveraging both the acoustic and semantic information cooperatively., Comment: Accepted by Interspeech 2023

Published
2023

5. Robust Autonomous Unmanned Aerial Vehicle System for Efficient Tracking of Moving Objects

Author

Dong, Zhiwei, Yong, Yang, Wang, Zining, Chen, Song-Lu, Yin, Xu-Cheng, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Guo, Jinyang, editor, Ma, Yuqing, editor, Ding, Yifu, editor, Gong, Ruihao, editor, Zheng, Xingyu, editor, He, Changyi, editor, Lu, Yantao, editor, and Liu, Xianglong, editor

Published
2024
Full Text
View/download PDF

6. Multi-task Learning for License Plate Recognition in Unconstrained Scenarios

Author

Mo, Zhen-Lun, Chen, Song-Lu, Liu, Qi, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Barney Smith, Elisa H., editor, Liwicki, Marcus, editor, and Peng, Liangrui, editor

Published
2024
Full Text
View/download PDF

7. Irregular License Plate Recognition via Global Information Integration

Author

Liu, Yuan-Yuan, Liu, Qi, Chen, Song-Lu, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Rudinac, Stevan, editor, Hanjalic, Alan, editor, Liem, Cynthia, editor, Worring, Marcel, editor, Jónsson, Björn Þór, editor, Liu, Bei, editor, and Yamakata, Yoko, editor

Published
2024
Full Text
View/download PDF

8. Improving Small License Plate Detection with Bidirectional Vehicle-Plate Relation

Author

Dai, Songkang, Chen, Song-Lu, Liu, Qi, Zhu, Chao, Liu, Yan, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Rudinac, Stevan, editor, Hanjalic, Alan, editor, Liem, Cynthia, editor, Worring, Marcel, editor, Jónsson, Björn Þór, editor, Liu, Bei, editor, and Yamakata, Yoko, editor

Published
2024
Full Text
View/download PDF

9. Non-autoregressive Transformer with Unified Bidirectional Decoder for Automatic Speech Recognition

Author

Zhang, Chuan-Fei, Liu, Yan, Zhang, Tian-Hao, Chen, Song-Lu, Chen, Feng, and Yin, Xu-Cheng

Subjects
Computer Science - Computation and Language, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Non-autoregressive (NAR) transformer models have been studied intensively in automatic speech recognition (ASR), and a substantial part of NAR transformer models is to use the casual mask to limit token dependencies. However, the casual mask is designed for the left-to-right decoding process of the non-parallel autoregressive (AR) transformer, which is inappropriate for the parallel NAR transformer since it ignores the right-to-left contexts. Some models are proposed to utilize right-to-left contexts with an extra decoder, but these methods increase the model complexity. To tackle the above problems, we propose a new non-autoregressive transformer with a unified bidirectional decoder (NAT-UBD), which can simultaneously utilize left-to-right and right-to-left contexts. However, direct use of bidirectional contexts will cause information leakage, which means the decoder output can be affected by the character information from the input of the same position. To avoid information leakage, we propose a novel attention mask and modify vanilla queries, keys, and values matrices for NAT-UBD. Experimental results verify that NAT-UBD can achieve character error rates (CERs) of 5.0%/5.5% on the Aishell1 dev/test sets, outperforming all previous NAR transformer models. Moreover, NAT-UBD can run 49.8x faster than the AR transformer baseline when decoding in a single step., Comment: 5 pages, 3 figures. Paper submitted to ICASSP 2022

Published
2021

12. End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining

Author

Chen, Song-Lu, Tian, Shu, Ma, Jia-Wei, Liu, Qi, Yang, Chun, Chen, Feng, and Yin, Xu-Cheng

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

License plate detection is the first and essential step of the license plate recognition system and is still challenging in real applications, such as on-road scenarios. In particular, small-sized and oblique license plates, mainly caused by the distant and mobile camera, are difficult to detect. In this work, we propose a novel and applicable method for degraded license plate detection via vehicle-plate relation mining, which localizes the license plate in a coarse-to-fine scheme. First, we propose to estimate the local region around the license plate by using the relationships between the vehicle and the license plate, which can greatly reduce the search area and precisely detect very small-sized license plates. Second, we propose to predict the quadrilateral bounding box in the local region by regressing the four corners of the license plate to robustly detect oblique license plates. Moreover, the whole network can be trained in an end-to-end manner. Extensive experiments verify the effectiveness of our proposed method for small-sized and oblique license plates. Codes are available at https://github.com/chensonglu/LPD-end-to-end.

Published
2020

13. Complex Glyph Enhancement for License Plate Generation

Author

Chen, Yu-Xiang, Liu, Qi, Chen, Song-Lu, Zhou, Fang, Liu, Yan, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Lu, Huchuan, editor, Ouyang, Wanli, editor, Huang, Hui, editor, Lu, Jiwen, editor, Liu, Risheng, editor, Dong, Jing, editor, and Xu, Min, editor

Published
2023
Full Text
View/download PDF

14. End-to-End Multi-line License Plate Recognition with Cascaded Perception

Author

Chen, Song-Lu, Liu, Qi, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Fink, Gernot A., editor, Jain, Rajiv, editor, Kise, Koichi, editor, and Zanibbi, Richard, editor

Published
2023
Full Text
View/download PDF

15. Adaptive Rounding Compensation for Post-training Quantization

Author

Lin, Jinhui, Wang, Heng, Liu, Yan, Chen, Song-Lu, Zhang, Ruiyao, Dong, Zhiwei, Chen, Feng, Yin, Xu-Cheng, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Tanveer, Mohammad, editor, Agarwal, Sonali, editor, Ozawa, Seiichi, editor, Ekbal, Asif, editor, and Jatowt, Adam, editor

Published
2023
Full Text
View/download PDF

16. LiteHandNet: A Lightweight Hand Pose Estimation Network via Structural Feature Enhancement

Author

Huang, Zhi-Yong, Chen, Song-Lu, Liu, Qi, Zhang, Chong-Jian, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Dang-Nguyen, Duc-Tien, editor, Gurrin, Cathal, editor, Larson, Martha, editor, Smeaton, Alan F., editor, Rudinac, Stevan, editor, Dao, Minh-Son, editor, Trattner, Christoph, editor, and Chen, Phoebe, editor

Published
2023
Full Text
View/download PDF

17. Feature Enhancement and Reconstruction for Small Object Detection

Author

Zhang, Chong-Jian, Chen, Song-Lu, Liu, Qi, Huang, Zhi-Yong, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Dang-Nguyen, Duc-Tien, editor, Gurrin, Cathal, editor, Larson, Martha, editor, Smeaton, Alan F., editor, Rudinac, Stevan, editor, Dao, Minh-Son, editor, Trattner, Christoph, editor, and Chen, Phoebe, editor

Published
2023
Full Text
View/download PDF

20. Anchor-Free Location Refinement Network for Small License Plate Detection

Author

Li, Zhen-Jia, Chen, Song-Lu, Liu, Qi, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Yu, Shiqi, editor, Zhang, Zhaoxiang, editor, Yuen, Pong C., editor, Han, Junwei, editor, Tan, Tieniu, editor, Guo, Yike, editor, Lai, Jianhuang, editor, and Zhang, Jianguo, editor

Published
2022
Full Text
View/download PDF

21. Robust Chinese License Plate Generation via Foreground Text and Background Separation

Author

Sun, Yi-Fan, Liu, Qi, Chen, Song-Lu, Zhou, Fang, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Peng, Yuxin, editor, Hu, Shi-Min, editor, Gabbouj, Moncef, editor, Zhou, Kun, editor, Elad, Michael, editor, and Xu, Kun, editor

Published
2021
Full Text
View/download PDF

22. Fast Recognition for Multidirectional and Multi-type License Plates with 2D Spatial Attention

Author

Liu, Qi, Chen, Song-Lu, Li, Zhen-Jia, Yang, Chun, Chen, Feng, Yin, Xu-Cheng, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Lladós, Josep, editor, Lopresti, Daniel, editor, and Uchida, Seiichi, editor

Published
2021
Full Text
View/download PDF

23. Recurrent Graph Convolutional Network for Skeleton-Based Abnormal Driving Behavior Recognition

Author

Wang, Shun, Zhou, Fang, Chen, Song-Lu, Yang, Chun, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Del Bimbo, Alberto, editor, Cucchiara, Rita, editor, Sclaroff, Stan, editor, Farinella, Giovanni Maria, editor, Mei, Tao, editor, Bertini, Marco, editor, Escalante, Hugo Jair, editor, and Vezzani, Roberto, editor

Published
2021
Full Text
View/download PDF

30. Bloody Image Classification with Global and Local Features

Author

Chen, Song-Lu, Yang, Chun, Zhu, Chao, Yin, Xu-Cheng, Diniz Junqueira Barbosa, Simone, Series editor, Chen, Phoebe, Series editor, Du, Xiaoyong, Series editor, Filipe, Joaquim, Series editor, Kara, Orhun, Series editor, Kotenko, Igor, Series editor, Liu, Ting, Series editor, Sivalingam, Krishna M., Series editor, Washio, Takashi, Series editor, Tan, Tieniu, editor, Li, Xuelong, editor, Chen, Xilin, editor, Zhou, Jie, editor, Yang, Jian, editor, and Cheng, Hong, editor

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results