Xuemei Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xuemei Xie has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Changcai Yang
1 shared publication- Guangming Shi
Peng Cheng Laboratory, Shenzhen, Guangdong, China
1 shared publication Jianxiu Yang
1 shared publication- Jianxiu Yang
School of Physics and Electronics, Shanxi Datong University, Datong, China
1 shared publication Qingzhe Pan
1 shared publicationXiaodan Song
1 shared publication
Latest Publications
- 18 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
VLSAM: Prompting SAM with vision and language for referring expression segmentation
- 18 October 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
VLSAM: Prompting SAM with vision and language for referring expression segmentation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 5380-5394
Hierarchical Scene Graph Generation With Coarse-to-Fine Reasoning
Scene graph generation denotes the process of parsing a visual input into a graph representation for downstream reasoning tasks. Most existing research models input scenes as flat scene graphs, capturing solely on horizontal relationships between two objects, while disregarding vertical dependencies. Such flat scene graphs merely describe direct relationships between objects, and cannot represent higher-level semantics. The lack of hierarchical relationships also limits the performance of scene graphs in downstream reasoning tasks. In this work, we propose hierarchical scene graph generation, a new problem task that requires the model to generate scene graphs with clear hierarchy. To achieve this goal, a hierarchical scene graph generation with coarse-to-fine reasoning framework is proposed. It contains three stages: first, summarize the main caption of the scene; second, describe the main visual elements related to the theme; and finally, add secondary elements with background. To facilitate training, a high-quality hierarchical scene graph dataset that comprises 40 K image-scene description pairs is constructed. Utilize rich knowledge and powerful multi-turn conversation capabilities of multi-modal large language models, the proposed framework can not only achieve better semantic understanding and relational modeling, but also seamlessly integrating its relational modeling capabilities to enhance visual-language tasks. Extensive experimental results demonstrate that our method constructs an effective scene representation, outperforming the state-of-the-art by 3.35% in recall while generating significantly fewer average triplets 8.7vs. 9.2. The results on downstream tasks also indicate that hierarchical scene graph significantly contributes to visual-language interactive reasoning.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 5380-5394
Hierarchical Scene Graph Generation With Coarse-to-Fine Reasoning
Scene graph generation denotes the process of parsing a visual input into a graph representation for downstream reasoning tasks. Most existing research models input scenes as flat scene graphs, capturing solely on horizontal relationships between two objects, while disregarding vertical dependencies. Such flat scene graphs merely describe direct relationships between objects, and cannot represent higher-level semantics. The lack of hierarchical relationships also limits the performance of scene graphs in downstream reasoning tasks. In this work, we propose hierarchical scene graph generation, a new problem task that requires the model to generate scene graphs with clear hierarchy. To achieve this goal, a hierarchical scene graph generation with coarse-to-fine reasoning framework is proposed. It contains three stages: first, summarize the main caption of the scene; second, describe the main visual elements related to the theme; and finally, add secondary elements with background. To facilitate training, a high-quality hierarchical scene graph dataset that comprises 40 K image-scene description pairs is constructed. Utilize rich knowledge and powerful multi-turn conversation capabilities of multi-modal large language models, the proposed framework can not only achieve better semantic understanding and relational modeling, but also seamlessly integrating its relational modeling capabilities to enhance visual-language tasks. Extensive experimental results demonstrate that our method constructs an effective scene representation, outperforming the state-of-the-art by 3.35% in recall while generating significantly fewer average triplets 8.7vs. 9.2. The results on downstream tasks also indicate that hierarchical scene graph significantly contributes to visual-language interactive reasoning.