Gangyan Zeng

Orcid: 0000-0003-2696-8549

According to our database1, Gangyan Zeng authored at least 9 papers between 2019 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model.
CoRR, 2024

2023
Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust and accurate textvqa.
Pattern Recognit., June, 2023

Feature Enhancement with Text-Specific Region Contrast for Scene Text Detection.
Proceedings of the Pattern Recognition and Computer Vision - 6th Chinese Conference, 2023

Filling in the Blank: Rationale-Augmented Prompt Tuning for TextVQA.
Proceedings of the 31st ACM International Conference on Multimedia, 2023

2022
TextBlock: Towards Scene Text Spotting without Fine-grained Detection.
Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2022

2021
A Cost-Efficient Framework for Scene Text Detection in the Wild.
Proceedings of the PRICAI 2021: Trends in Artificial Intelligence, 2021

Beyond OCR + VQA: Involving OCR into the Flow for Robust and Accurate TextVQA.
Proceedings of the MM '21: ACM Multimedia Conference, Virtual Event, China, October 20, 2021

2019
PororoGAN: An Improved Story Visualization Model on Pororo-SV Dataset.
Proceedings of the CSAI 2019: 2019 3rd International Conference on Computer Science and Artificial Intelligence, 2019


  Loading...