no code implementations • 21 Dec 2023 • Yimin Sun, Chao Wang, Yan Peng
Experimental results show that our method exceeds the performance of state-of-the-art zero-shot VQA models for flood disaster scenarios in total.
no code implementations • 4 Dec 2023 • Yimin Sun, Chao Wang, Yan Peng
Most importantly, our model uses well-designed chain of thought (CoT) demonstrations to unlock the potential of the large language model, allowing zero-shot VQA to show better performance in disaster scenarios.
no code implementations • 23 Feb 2023 • Jinan Yu, Liyan Ma, Zhenglin Li, Yan Peng, Shaorong Xie
Open-world object detection (OWOD) is a challenging problem that combines object detection with incremental learning and open-set learning.
no code implementations • 26 Jul 2022 • Dan Zhang, Xi Zhou, Zi-Hao Wang, Yan Peng, Shao-Rong Xie
This paper presents a novel data-driven methodology to provide a multi-step prediction of ship roll motions in high sea states.
no code implementations • NeurIPS 2021 • Mingyuan Mao, Renrui Zhang, Honghui Zheng, Peng Gao, Teli Ma, Yan Peng, Errui Ding, Baochang Zhang, Shumin Han
Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images.
no code implementations • 6 Nov 2020 • Yong Chen, Zhi-Gang Jia, Ya-Xin Peng, Yan Peng
In this way, compared with conventional QSVD, the proposed watermarking strategy avoids more modifications to a single color image layer and a better visual quality of the watermarked image is observed.
1 code implementation • 15 Jul 2019 • Zhen-Yu Zhang, Xiangfeng Luo, Tong Liu, Shaorong Xie, Jianshu Wang, Wei Wang, Yang Li, Yan Peng
Instability and slowness are two main problems in deep reinforcement learning.