Peijian Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Peijian Zeng has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Nankai Lin
School of Information Science and Technology, Guangdong University of Foreign Studies, Guangzhou, China
2 shared publications - Aimin Yang
Lingnan Normal University
1 shared publication - Aimin Yang
Guangdong University of Technology, Guangzhou, China
1 shared publication - Dong Zhou
Guangdong University of Foreign Studies
1 shared publication - Hongyan Wu
College of Computer Science and Technology, National University of Defense Technology, Changsha, China
1 shared publication - Lianglun Cheng
Guangdong University of Technology, Guangzhou, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16851-16858
MARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments
Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated benchmarks. We introduce MARINER, a comprehensive benchmark built under the novel Entity-Environment-Event (3E) paradigm. MARINER contains 16,629 multi-source maritime images with 63 fine-grained vessel categories, diverse adverse environments, and 5 typical dynamic maritime incidents, covering fine-grained classification, object detection, and visual question answering tasks. We conduct extensive evaluations on mainstream Multimodal Large language models (MLLMs) and establish baselines, revealing that even advanced models struggle with fine-grained discrimination and causal reasoning in complex marine scenes. As a dedicated maritime benchmark, MARINER fills the gap of realistic and cognitive-level evaluation for maritime multimodal understanding, and promotes future research on robust vision-language models for open-water applications. Appendix and supplementary materials are available at https://lxixim.github.io/MARINER.
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16851-16858
Open AccessMARINER: A 3E-Driven Benchmark for Fine-Grained Perception and Complex Reasoning in Open-Water Environments
Fine-grained visual understanding and high-level reasoning in real-world open-water environments remain under-explored due to the lack of dedicated benchmarks. We introduce MARINER, a comprehensive benchmark built under the novel Entity-Environment-Event (3E) paradigm. MARINER contains 16,629 multi-source maritime images with 63 fine-grained vessel categories, diverse adverse environments, and 5 typical dynamic maritime incidents, covering fine-grained classification, object detection, and visual question answering tasks. We conduct extensive evaluations on mainstream Multimodal Large language models (MLLMs) and establish baselines, revealing that even advanced models struggle with fine-grained discrimination and causal reasoning in complex marine scenes. As a dedicated maritime benchmark, MARINER fills the gap of realistic and cognitive-level evaluation for maritime multimodal understanding, and promotes future research on robust vision-language models for open-water applications. Appendix and supplementary materials are available at https://lxixim.github.io/MARINER.
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (16) , 24587-24598
TAKNI: Temporal Attention-Driven Kernel Norm Integration Network for Fault Diagnosis
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (16) , 24587-24598
TAKNI: Temporal Attention-Driven Kernel Norm Integration Network for Fault Diagnosis
- 17 March 2025
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 68 (8) , 1050-1061
A novel curriculum learning framework for multi-label emotion classification
Curriculum learning (CL) is a training strategy that imitates how humans learn, by gradually introducing more complex samples and information to the model. However, in multi-label emotion classification (MEC) tasks, using a traditional CL approach can result in overfitting on easy samples and lead to biased training. Additionally, the sample difficulty varies as the model trains. To address these challenges, we propose a novel CL framework for MEC tasks called CLF-MEC. Unlike traditional approaches that assess difficulty at the sample level, we utilize category-level assessment to determine the difficulty level of samples. As the model identifies a category well, the score for that category’s samples is reduced, ensuring dynamic changes in the sample difficulty are accounted for. Our CL framework employs two training modes, namely “learning” and “tackling.” These two processes are trained alternatively to imitate the “learning-tackling” process in human learning. This ensures that samples from hard-to-learn categories receive more attention. During the “tackling” process, our method transforms the task of dealing with hard samples into an “easy” learning task by utilizing contrastive learning to enhance the semantic representation of those hard samples. Experimental results demonstrate that our CLF-MEC framework has achieved significant improvements in MEC.
- 17 March 2025
- Published by Oxford University Press (OUP) in The Computer Journal
- Vol. 68 (8) , 1050-1061
A novel curriculum learning framework for multi-label emotion classification
Curriculum learning (CL) is a training strategy that imitates how humans learn, by gradually introducing more complex samples and information to the model. However, in multi-label emotion classification (MEC) tasks, using a traditional CL approach can result in overfitting on easy samples and lead to biased training. Additionally, the sample difficulty varies as the model trains. To address these challenges, we propose a novel CL framework for MEC tasks called CLF-MEC. Unlike traditional approaches that assess difficulty at the sample level, we utilize category-level assessment to determine the difficulty level of samples. As the model identifies a category well, the score for that category’s samples is reduced, ensuring dynamic changes in the sample difficulty are accounted for. Our CL framework employs two training modes, namely “learning” and “tackling.” These two processes are trained alternatively to imitate the “learning-tackling” process in human learning. This ensures that samples from hard-to-learn categories receive more attention. During the “tackling” process, our method transforms the task of dealing with hard samples into an “easy” learning task by utilizing contrastive learning to enhance the semantic representation of those hard samples. Experimental results demonstrate that our CLF-MEC framework has achieved significant improvements in MEC.