Gangyan Zeng

33 papers A* 8A 1B 1Journal 15Unranked 8
YearRankTypeTitle / Venue / Authors
2026 J jnl
MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation.
CoRR
Gengluo Li, Chengquan Zhang, Yupu Liang, Huawen Shen, Yaping Zhang, Pengyuan Lyu, Weinong Wang, Xingyu Wan, Gangyan Zeng, Han Hu, Can Ma, Yu Zhou
2026 J jnl
Retrieval Augmented video captioning with quality-aware re-ranking and cross-gating fusion.
Displays
Chengyang Fang, Jian Li, Yilong Xie, Wenhui Jiang, Gangyan Zeng, Zhixuan Li, Yuming Fang
2026 J jnl
Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training.
CoRR
Gengluo Li, Pengyuan Lyu, Chengquan Zhang, Huawen Shen, Liang Wu, Xingyu Wan, Gangyan Zeng, Han Hu, Can Ma, Yu Zhou
2026 J jnl
Towards Training-Free Scene Text Editing.
CoRR
Yubo Li, Xugong Qin, Peng Zhang, Hailun Lin, Gangyan Zeng, Kexin Zhang
2025 A* conf
CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR.
CVPR
Xugong Qin, Peng Zhang, Jun Jie Ou Yang, Gangyan Zeng, Yubo Li, Yuanyuan Wang, Wanqian Zhang, Pengwen Dai
2025 A* conf
Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective.
ACM Multimedia
Yan Zhang, Gangyan Zeng, Daiqing Wu, Huawen Shen, Binbin Li, Yu Zhou, Can Ma, Xiaojun Bi
2025 J jnl
Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective.
CoRR
Yan Zhang, Gangyan Zeng, Daiqing Wu, Huawen Shen, Binbin Li, Yu Zhou, Can Ma, Xiaojun Bi
2025 — conf
PerturbCTC: Improving Alignment in Scene Text Recognition with Feature Perturbation Based CTC.
ICDAR (4)
Zeng Li, Jin Wei, Zhijie Shen, Yaqiang Wu, Gangyan Zeng, Dongbao Yang, Zhi Qiao, Yu Zhou
2025 J jnl
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model.
ACM Trans. Multim. Comput. Commun. Appl.
Jiahao Lyu, Jin Wei, Gangyan Zeng, Zeng Li, Enze Xie, Wei Wang, Can Ma, Yu Zhou
2025 — conf
Towards Fine-Grained Document Tampering Detection: New Dataset and Benchmark.
PRCV (7)
Xugong Qin, Jiuqiang Tian, Jiayi Sheng, Tiantian Xia, Yuyi Wang, Chengrui Li, Gangyan Zeng
2025 A* conf
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark.
CVPR
Hao Guo, Xugong Qin, Jun Jie Ou Yang, Peng Zhang, Gangyan Zeng, Yubo Li, Hailun Lin
2025 J jnl
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark.
CoRR
Hao Guo, Xugong Qin, Jun Jie Ou Yang, Peng Zhang, Gangyan Zeng, Yubo Li, Hailun Lin
2025 A* conf
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues.
AAAI
Yan Zhang, Gangyan Zeng, Huawen Shen, Daiqing Wu, Yu Zhou, Can Ma
2025 B conf
TrapLLM: An LLM-powered Interactive Log-based Honeypot for Real-world Network Attacks.
TrustCom
Yunjun Ma, Gangyan Zeng, Peng Zhang, Yuchen Huang, Fuyuan Zhang, Ran Lin, Huan Qian
2025 J jnl
VidText: Towards Comprehensive Evaluation for Video Text Understanding.
CoRR
Zhoufaran Yang, Yan Shu, Zhifei Yang, Yan Zhang, Yu Li, Keyang Lu, Gangyan Zeng, Shaohui Liu, Yu Zhou, Nicu Sebe
2025 J jnl
When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding.
CoRR
Yan Shu, Hangui Lin, Yexin Liu, Yan Zhang, Gangyan Zeng, Yan Li, Yu Zhou, Ser-Nam Lim, Harry Yang, Nicu Sebe
2024 A* conf
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval.
ACM Multimedia
Gangyan Zeng, Yuan Zhang, Jin Wei, Dongbao Yang, Peng Zhang, Yiwen Gao, Xugong Qin, Yu Zhou
2024 J jnl
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval.
CoRR
Gangyan Zeng, Yuan Zhang, Jin Wei, Dongbao Yang, Peng Zhang, Yiwen Gao, Xugong Qin, Yu Zhou
2024 — conf
Improving Multimodal Rumor Detection via Dynamic Graph Modeling.
ICPR (18)
Xinyu Wu, Xiaoxu Hu, Xugong Qin, Peng Zhang, Gangyan Zeng, Yu Guo, Runbo Zhao, Xinjian Huang
2024 — conf
Perception-Enhanced Generative Transformer for Key Information Extraction from Documents.
ICPR (31)
Runbo Zhao, Jun Jie Ou Yang, Chen Gao, Xugong Qin, Gangyan Zeng, Xiaoxu Hu, Peng Zhang
2024 — conf
Show Exemplars and Tell Me What You See: In-Context Learning with Frozen Large Language Models for TextVQA.
PRCV (7)
Yan Zhang, Gangyan Zeng, Huawen Shen, Can Ma, Yu Zhou
2024 J jnl
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model.
CoRR
Jiahao Lyu, Jin Wei, Gangyan Zeng, Zeng Li, Enze Xie, Wei Wang, Yu Zhou
2024 J jnl
Towards better video services: An EEG-based interpretable model for functional quality of experience evaluation.
Displays
Yifan Niu, Kexin Di, Gangyan Zeng, Tao Wei, Yuan Zhang, Xia Wu
2024 J jnl
Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues.
CoRR
Yan Zhang, Gangyan Zeng, Huawen Shen, Daiqing Wu, Yu Zhou, Can Ma
2023 J jnl
Beyond OCR + VQA: Towards end-to-end reading and reasoning for robust and accurate textvqa.
Pattern Recognit.
Gangyan Zeng, Yuan Zhang, Yu Zhou, Xiaomeng Yang, Ning Jiang, Guoqing Zhao, Weiping Wang, Xu-Cheng Yin
2023 — conf
Feature Enhancement with Text-Specific Region Contrast for Scene Text Detection.
PRCV (7)
Xurui Sun, Jiahao Lyu, Yifei Zhang, Gangyan Zeng, Bo Fang, Yu Zhou, Enze Xie, Can Ma
2023 A* conf
Filling in the Blank: Rationale-Augmented Prompt Tuning for TextVQA.
ACM Multimedia
Gangyan Zeng, Yuan Zhang, Yu Zhou, Bo Fang, Guoqing Zhao, Xin Wei, Weiping Wang
2022 A* conf
TextBlock: Towards Scene Text Spotting without Fine-grained Detection.
ACM Multimedia
Jin Wei, Yuan Zhang, Yu Zhou, Gangyan Zeng, Zhi Qiao, Youhui Guo, Haiying Wu, Hongbin Wang, Weiping Wang
2022 A conf
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering.
ICME
Chengyang Fang, Gangyan Zeng, Yu Zhou, Daiqing Wu, Can Ma, Dayong Hu, Weiping Wang
2022 J jnl
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering.
CoRR
Chengyang Fang, Gangyan Zeng, Yu Zhou, Daiqing Wu, Can Ma, Dayong Hu, Weiping Wang
2021 — conf
A Cost-Efficient Framework for Scene Text Detection in the Wild.
PRICAI (1)
Gangyan Zeng, Yuan Zhang, Yu Zhou, Xiaomeng Yang
2021 A* conf
Beyond OCR + VQA: Involving OCR into the Flow for Robust and Accurate TextVQA.
ACM Multimedia
Gangyan Zeng, Yuan Zhang, Yu Zhou, Xiaomeng Yang
2019 — conf
PororoGAN: An Improved Story Visualization Model on Pororo-SV Dataset.
CSAI
Gangyan Zeng, Zhaohui Li, Yuan Zhang