Siying Wu
Research Subjects
Research Interests
Siying Wu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Jing Zhang
School of Information Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Lubin Gan
University of Science and Technology of China, Hefei, China
2 shared publications - Xiaoyan Sun
University of Science and Technology of China, Hefei, China
2 shared publications - Yijun Wang
University of Science and Technology of China, Hefei, Anhui, China
2 shared publications - Feng Wu
University of Science and Technology of China
1 shared publication - Huyue Zhu
University of Science and Technology of China, Hefei, Anhui, China
1 shared publication
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3635-3644
MeDKCoOp: Dual Knowledge-guided Graph Prompt Learning for Biomedical Vision-Language Models
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3635-3644
Open AccessMeDKCoOp: Dual Knowledge-guided Graph Prompt Learning for Biomedical Vision-Language Models
- 27 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 300
Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment
- 27 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 300
Enhancing zero-shot brain tumor subtype classification via fine-grained patch-text alignment
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8406-8418
Vision-and-Language Navigation via Latent Semantic Alignment Learning
Vision-and-Language Navigation (VLN) requires that an agent can comprehensively understand the given instructions and the immediate visual information obtained from the environment, so as to make correct actions to achieve the navigation goal. Therefore, semantic alignment across modalities is crucial for the agent understanding its own state during the navigation process. However, the potential of semantic alignment has not been systematically explored in current studies, which limits the further improvement of navigation performance. To address this issue, we propose a new Latent Semantic Alignment Learning method to develop the semantically aligned relationships contained in the environment. Specifically, we introduce three novel pre-training tasks: Trajectory-conditioned Masked Fragment Modeling, Action Prediction of Masked Observation, and Hierarchical Triple Contrastive Learning. The first two tasks are used to reason about cross-modal dependencies, while the third one is able to learn semantically consistent representations across modalities. In this way, the Latent Semantic Alignment Learning method establishes a consistent perception of the environment and makes the agent's actions easier to explain. Experiments on common benchmarks verify the effectiveness of our proposed methods. For example, we improve the Success Rate by 1.6% on the R2R validation unseen set and 4.3% on the R4R validation unseen set over the baseline model.
- 24 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8406-8418
Vision-and-Language Navigation via Latent Semantic Alignment Learning
Vision-and-Language Navigation (VLN) requires that an agent can comprehensively understand the given instructions and the immediate visual information obtained from the environment, so as to make correct actions to achieve the navigation goal. Therefore, semantic alignment across modalities is crucial for the agent understanding its own state during the navigation process. However, the potential of semantic alignment has not been systematically explored in current studies, which limits the further improvement of navigation performance. To address this issue, we propose a new Latent Semantic Alignment Learning method to develop the semantically aligned relationships contained in the environment. Specifically, we introduce three novel pre-training tasks: Trajectory-conditioned Masked Fragment Modeling, Action Prediction of Masked Observation, and Hierarchical Triple Contrastive Learning. The first two tasks are used to reason about cross-modal dependencies, while the third one is able to learn semantically consistent representations across modalities. In this way, the Latent Semantic Alignment Learning method establishes a consistent perception of the environment and makes the agent's actions easier to explain. Experiments on common benchmarks verify the effectiveness of our proposed methods. For example, we improve the Success Rate by 1.6% on the R2R validation unseen set and 4.3% on the R4R validation unseen set over the baseline model.