Feng Su
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
Feng Su has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
Jiahao Shi
Nanjing University
3 shared publications- Mingjun Li
Nanjing University
3 shared publications - Shuo Xu
Nanjing University
3 shared publications Like Xue
Nanjing University, Nanjing, China
2 shared publicationsLong Chen
Nanjing University
2 shared publicationsYang Wang
Nanjing University
2 shared publications
Latest Publications
- 5 December 2024
- Published by Springer Nature
- p. 316-331
MPGTSRN: Scene Text Image Super-Resolution Guided by Multiple Visual-Semantic Prompts
- 5 December 2024
- Published by Springer Nature
- p. 316-331
MPGTSRN: Scene Text Image Super-Resolution Guided by Multiple Visual-Semantic Prompts
- 5 December 2024
- Published by Springer Nature
- p. 237-253
Arbitrary-Shaped Scene Text Recognition with Deformable Ensemble Attention
- 5 December 2024
- Published by Springer Nature
- p. 237-253
Arbitrary-Shaped Scene Text Recognition with Deformable Ensemble Attention
- Open Access
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 353-361
Learning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition
- 12 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 353-361
Open AccessLearning and Fusing Multi-Scale Representations for Accurate Arbitrary-Shaped Scene Text Recognition
- 9 March 2023
- Published by Springer Nature
- p. 107-123
Reading Arbitrary-Shaped Scene Text from Images Through Spline Regression and Rectification
- 9 March 2023
- Published by Springer Nature
- p. 107-123
Reading Arbitrary-Shaped Scene Text from Images Through Spline Regression and Rectification
- Open Access
- 22 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 9-13
Multimodal Product Identification
This technical report describes the overview of our approach to the "Watch and Buy: Multimodal Product Identification Challenge". Specifically, we tackle this problem with a three-stage framework, i.e., product detection, retrieval and classification. For the product detection, we leverage the performance by Cascade R-CNN and deformable convolution to alleviate the impact of image distortion. For the product retrieval, we enhance the Multiple Granularity Network (MGN) with global and local context through IBN, SE and Non-local blocks. The task of product classification suffers from fashion variation. To this end, we propose to fuse the global feature of the integral images and local feature of products. Experiments demonstrate that our works could achieve competitive performance with the state-of-the-art methods and our overall approach achieves a F1 score of 0.648, ranking the second place in the final challenge.
- 22 October 2021
- Published by Association for Computing Machinery (ACM)
- p. 9-13
Open AccessMultimodal Product Identification
This technical report describes the overview of our approach to the "Watch and Buy: Multimodal Product Identification Challenge". Specifically, we tackle this problem with a three-stage framework, i.e., product detection, retrieval and classification. For the product detection, we leverage the performance by Cascade R-CNN and deformable convolution to alleviate the impact of image distortion. For the product retrieval, we enhance the Multiple Granularity Network (MGN) with global and local context through IBN, SE and Non-local blocks. The task of product classification suffers from fashion variation. To this end, we propose to fuse the global feature of the integral images and local feature of products. Experiments demonstrate that our works could achieve competitive performance with the state-of-the-art methods and our overall approach achieves a F1 score of 0.648, ranking the second place in the final challenge.
- 25 February 2021
- Published by Springer Nature
- p. 241-256
Accurate Arbitrary-Shaped Scene Text Detection via Iterative Polynomial Parameter Regression
- 25 February 2021
- Published by Springer Nature
- p. 241-256
Accurate Arbitrary-Shaped Scene Text Detection via Iterative Polynomial Parameter Regression
- Open Access
Learning content and context with language bias for Visual Question Answering
Visual Question Answering (VQA) is a challenging multimodal task to answer questions about an image. Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context. However, reducing language bias also weakens the ability of VQA models to learn context prior. To address this issue, we propose a novel learning strategy named CCB, which forces VQA models to answer questions relying on Content and Context with language Bias. Specifically, CCB establishes Content and Context branches on top of a base VQA model and forces them to focus on local key content and global effective context respectively. Moreover, a joint loss function is proposed to reduce the importance of biased samples and retain their beneficial influence on answering questions. Experiments show that CCB outperforms the state-of-the-art methods in terms of accuracy on VQA-CP v2.
Open AccessLearning content and context with language bias for Visual Question Answering
Visual Question Answering (VQA) is a challenging multimodal task to answer questions about an image. Many works concentrate on how to reduce language bias which makes models answer questions ignoring visual content and language context. However, reducing language bias also weakens the ability of VQA models to learn context prior. To address this issue, we propose a novel learning strategy named CCB, which forces VQA models to answer questions relying on Content and Context with language Bias. Specifically, CCB establishes Content and Context branches on top of a base VQA model and forces them to focus on local key content and global effective context respectively. Moreover, a joint loss function is proposed to reduce the importance of biased samples and retain their beneficial influence on answering questions. Experiments show that CCB outperforms the state-of-the-art methods in terms of accuracy on VQA-CP v2.
- 1 January 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (1) , 3-16
Hierarchical attentive deep neural networks for semantic music annotation through multiple music representations
- 1 January 2020
- Published by Springer Nature in International Journal of Multimedia Information Retrieval
- Vol. 9 (1) , 3-16
Hierarchical attentive deep neural networks for semantic music annotation through multiple music representations
- 24 December 2019
- Published by Springer Nature
- p. 112-124
A Deep Convolutional Deblurring and Detection Neural Network for Localizing Text in Videos
- 24 December 2019
- Published by Springer Nature
- p. 112-124
A Deep Convolutional Deblurring and Detection Neural Network for Localizing Text in Videos
- 18 September 2018
- Published by Springer Nature
- p. 303-314
A Robust Approach for Scene Text Detection and Tracking in Video
- 18 September 2018
- Published by Springer Nature
- p. 303-314
A Robust Approach for Scene Text Detection and Tracking in Video