招生信息

研究方向

学术论文

• ICML 2026 CCF-A
  Aoting Zhang, Dongbao Yang*, Chang Liu, Xiaopeng Hong, Yu Zhou. “Focus, align, and sustain: Counteracting gradient dilution in incremental object detection.”
• ECCV 2026 CCF-B, THU-A
  Aoting Zhang, Dongbao Yang*, Chang Liu, Xiaopeng Hong, Can Ma, Yu Zhou. “Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection.”
• ICLR 2026 CCF-A
  Daiqing Wu, Dongbao Yang*, Sicheng Zhao, Can Ma, and Yu Zhou. “Customizing visual emotion evaluation for MLLMs: An open-vocabulary, multifaceted, and scalable approach.”
• ACM MM 2026 CCF-A
  Yufei Feng, Dongbao Yang*, Aoting Zhang, Yichao Liu, and Yu Zhou. “H-Hub: Hierarchical domain-aware parameter adaptation for continual test-time object detection.”
• PR 2026 SCI 一区 CCF-B
  Daiqing Wu, Dongbao Yang*, Can Ma, and Yu Zhou. “EmoCaliber: Advancing reliable visual emotion comprehension via confidence verbalization and calibration.”
• ICML 2025 CCF-A
  Daiqing Wu, Dongbao Yang*, Sicheng Zhao, Can Ma, and Yu Zhou. “An empirical study on configuring in-context learning demonstrations for unleashing MLLMs’ sentimental perception capability.”
• AAAI 2025 CCF-A
  Aoting Zhang, Dongbao Yang*, Chang Liu, Xiaopeng Hong, Miao Shang, Yu Zhou. “DCA: Dividing and conquering amnesia in incremental object detection.”
• AAAI 2025 CCF-A
  Aoting Zhang, Dongbao Yang*, Chang Liu, Xiaopeng Hong, Yu Zhou. “Specifying what you know or not for multi-label class-incremental learning.”
• PR 2025 SCI 一区
  Daiqing Wu, Dongbao Yang*, Huawen Shen, Can Ma, and Yu Zhou. “Robust multimodal sentiment analysis of image-text pairs by distribution-based feature recovery and fusion.”
• ACM MM 2024 CCF-A Oral
  Daiqing Wu, Dongbao Yang*, Yu Zhou, and Can Ma. “Bridging visual affective gap: Borrowing textual knowledge by learning from noisy image-text pairs.”
• ACM MM 2024 CCF-A
  Daiqing Wu, Dongbao Yang*, Yu Zhou, and Can Ma. “Robust multimodal sentiment analysis of image-text pairs by distribution-based feature recovery and fusion.”
• AAAI 2023 CCF-A Oral
  Dongbao Yang, Yu Zhou, Xiaopeng Hong, Aoting Zhang, and Weiping Wang. “One-Shot Replay: Boosting incremental object detection via retrospecting one object.”
• ACM MM 2023 CCF-A Oral
  Dongbao Yang, Yu Zhou, Xiaopeng Hong, Aoting Zhang, Xin Wei, Linchengxi Zeng, Zhi Qiao, and Weiping Wang. “Pseudo object replay and mining for incremental object detection.”
• PR 2022 SCI 一区 CCF-B
  Dongbao Yang, Yu Zhou, Aoting Zhang, Xurui Sun, Dayan Wu, Weiping Wang, and Qixiang Ye. “Multi-view correlation distillation for incremental object detection.”
• TOMM 2022 JCR SCI 一区 CCF-B
  Dongbao Yang, Yu Zhou, Wei Shi, Dayan Wu, and Weiping Wang. “RD-IOD: Two-level residual-distillation-based triple-network for incremental object detection.”
• PR 2019 SCI 一区 CCF-B
  Hongtao Xie, Dongbao Yang*, Nannan Sun, Zhineng Chen, and Yongdong Zhang. “Automated pulmonary nodule detection in CT images using deep convolutional neural networks.”
• IJCAI 2025 CCF-A
  Wei Li, Dezhao Luo, Dongbao Yang*, Zhenhang Li, Weiping Wang, and Yu Zhou. “The Role of Video Generation in Enhancing Data-Limited Action Understanding.”
• ACM MM 2024 CCF-A
  Gangyan Zeng, Yuan Zhang, Jin Wei, Dongbao Yang*, Peng Zhang, Yiwen Gao, Xugong Qin, and Yu Zhou. “Focus, Distinguish, and Prompt: Unleashing CLIP for efficient and flexible scene text retrieval.”
• ICASSP 2024 CCF-B
  Xiaomeng Yang, Dongbao Yang*, Zhi Qiao, and Yu Zhou. “Accurate and robust scene text recognition via adversarial training.”
• ICME 2023 CCF-B
  Xinye Yang, Dongbao Yang*, Yu Zhou, Youhui Guo, and Weiping Wang. “Mask-guided stamp erasure for real document image.”
• ICANN 2024 CCF-C
  Wei Li, Dezhao Luo, and Dongbao Yang*, and Weiping Wang. “Large language model for action anticipation.”
• ICTAI 2023 CCF-C
  Hongyu Li, Yifei Zhang, and Dongbao Yang*. “Cross-architecture relational consistency for point cloud self-supervised learning.”
• MTA 2019 CCF-C
  Yanping Ma, Dongbao Yang*, Hongtao Xie, and Jian Yin. “Supervised deep hashing for image content security.”
• KSEM 2018 CCF-C
  Nannan Sun, Dongbao Yang*, Shancheng Fang, Hongtao Xie. “Deep convolutional nets for pulmonary nodule detection and classification.”
• AAAI 2025 CCF-A
  Jiahao Lyu, Wei Wang, Dongbao Yang, Jinwen Zhong, Yu Zhou. “Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance.”
• ACM MM 2025 CCF-A
  Fangmin Zhao, Weichao Zeng, Zhenhang Li, Dongbao Yang, Binbin Li, Xiaojun Bi, Yu Zhou. “Uni-DocDiff: A Unified Document Restoration Model Based on Diffusion.”
• IEEE SPL 2024 CCF-C
  Xiaomeng Yang, Zhi Qiao, Jin Wei, Dongbao Yang, and Yu Zhou. “Masked and permuted implicit context learning for scene text recognition.”
• NeurIPS 2024 CCF-A
  Weichao Zeng, Yan Shu, Zhenhang Li, Dongbao Yang, and Yu Zhou. “TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control.”
• ACM MM 2023 CCF-A
  Yan Shu, Wei Wang, Yu Zhou, Shaohui Liu, Aoting Zhang, Dongbao Yang, and Weiping Wang. “Perceiving ambiguity and semantics without recognition: An efficient and effective ambiguous scene text detector.”
• TITS 2017 SCI 一区 CCF-B
  Chenggang Yan, Hongtao Xie, Dongbao Yang, Jian Yin, Yongdong Zhang, and Qionghai Dai. “Supervised hash coding with deep neural network for environment perception of intelligent vehicles.”
• ECAI 2024 CCF-B
  Zhenhang Li, Yan Shu, Weichao Zeng, Dongbao Yang, and Yu Zhou. “First creating backgrounds then rendering texts: A new paradigm for visual text blending.”
• ICMEW 2017
  Dongbao Yang, Hongtao Xie, Jian Yin, Yizhi Liu, Chenggang Yan. “Supervised deep quantization for efficient image search.”
• ICPR 2021 CCF-C
  Yudi Chen, Wei Wang, Yu Zhou, Fei Yang, Dongbao Yang, and Weiping Wang. “Self-training for domain adaptive scene text detection.”
• CVPR 2020 CCF-A
  Zhi Qiao, Yu Zhou, Dongbao Yang, Yucan Zhou, and Weiping Wang. “SEED: Semantics enhanced encoder-decoder framework for scene text recognition.”
• AAAI 2020 CCF-A Oral
  Dezhao Luo, Chang Liu, Yu Zhou, Dongbao Yang, Can Ma, Qixiang Ye, and Weiping Wang. “Video cloze procedure for self-supervised spatio-temporal learning.”
• PRICAI 2019 CCF-C
  Yudi Chen, Yu Zhou, Dongbao Yang, and Weiping Wang. “Constrained relation network for character detection in scene images.”
• ICDAR 2019 CCF-C
  Xugong Qin, Yu Zhou, Dongbao Yang, and Weiping Wang. “Curved text detection in natural scene images with semi-and weakly-supervised learning.”

科研项目

• 主持2025.01 — 2027.12国家自然科学基金青年基金：开放环境下基于语言引导的增量目标检测技术研究
• 主持2022.12 — 2025.11国家重点研发计划子课题：视听内容理解
• 主持2025.11 — 2026.11企业横向项目：多模态检索增强生成
• 主持2025.12 — 2026.12企业横向项目：面向监控视频的多模态信息融合摘要生成
• 参与2024.01 — 2027.12国家自然科学基金面上项目：视觉与语义融合的场景文字检测与识别技术研究
• 参与2022.07 — 2024.06企业横向项目：印章识别及通用文字识别
• 参与2022.01 — 2023.12国家广电总局项目：场景文字检测识别引擎
• 参与2021.04 — 2022.10企业横向项目：关于印章处理和小字体识别的 OCR 研究
• 参与2019.11 — 2022.10国家重点研发计划子课题：多媒体数据快速识别技术研究
• 参与2018.09 — 2019.08工程建设项目：多媒体数据分析系统
• 参与2017.10 — 2020.09国家重点研发计划子课题：实时数据检测分析系统

竞赛获奖

• 2019中国人工智能·多媒体信息识别技术竞赛，手写 / 印刷文本 OCR 两项高校组冠军
• 2019ICDAR ReCTS 2019（中文招牌文字识别），“字符识别”、“端到端识别”高校组第三名

发明专利

• 2026一种基于正交知识刷新的域增量图像目标检测方法及系统，受理号：202611048253.5
• 2026一种基于梯度稀释抑制的增量目标检测方法及系统，受理号：202610836566.0
• 2023基于伪目标重放与挖掘的增量目标检测方法及装置，受理号：202311216027.X
• 2023基于单目标重放的增量目标检测方法及装置，受理号：202310102438.X
• 2025基于分治健忘症的增量目标检测方法和系统，受理号：202510190263.1
• 2025基于明确已知和未知知识的多标签类增量学习方法和系统，受理号：202510190260.8
• 2024基于对抗训练的场景文字识别方法及装置，受理号：202410434598.9
• 2023基于掩模引导的去除印章噪声的图像生成方法及系统，受理号：202310733846.5
• 2020基于语义强化编码器解码器框架的场景文字识别方法，受理号：202010416704.2
• 2020一种基于自训练的文本检测器训练方法及系统，专利号：ZL 2020 1 0428815.5
• 2019基于受限注意力模型的字符检测网络训练方法、字符检测方法和字符检测器，专利号：ZL 2019 1 0614874.9
• 2019基于完形填空任务的视频自监督学习方法，专利号：ZL 2019 1 1348018.X
• 2017一种基于深度学习的图像哈希编码方法，受理号：201710182659.7

学术服务

• Reviewer：CVPR, ICCV, ECCV, AAAI, ACM MM, IJCAI ...
• Area Chair：ICME