Demo Data from EDBT 2026 / reviewers in the wild / expert
Yanxiu Dan
dblp:425/4893
· DBLP profile ↗
1ranked-venue papers
0as first author
1since 2021 · last 2025
0009-0003-0067-3002ORCID · reported
Domains — the database's venue-derived domains; a paper can count in several
Graphics, computer vision, multimedia, augmented reality and games · 1 · 1 since 2021
Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.
| Artificial intelligence
1 paper |
Vision and language · 87% Segmentation and scene understanding · 13% | |
| Computer graphics and multimedia
1 paper |
Visual content generation and editing · 100% |
Topics — the 4 heaviest of 4, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Computer vision › Vision and language
caption generation |
0.9 | 1 | 2025 | An Aesthetic Cultural Relic Poster Generation Framework Based on Multi-target Learning and Multimodal Large Language Model · ACM Multimedia 2025 |
Computer vision › Vision and language › vision-language model
multimodal large language model |
0.9 | 1 | 2025 | An Aesthetic Cultural Relic Poster Generation Framework Based on Multi-target Learning and Multimodal Large Language Model · ACM Multimedia 2025 |
Visual content generation and editing › graphic design
poster generation |
0.9 | 1 | 2025 | An Aesthetic Cultural Relic Poster Generation Framework Based on Multi-target Learning and Multimodal Large Language Model · ACM Multimedia 2025 |
Computer vision › Segmentation and scene understanding
object segmentation |
0.3 | 1 | 2025 | An Aesthetic Cultural Relic Poster Generation Framework Based on Multi-target Learning and Multimodal Large Language Model · ACM Multimedia 2025 |
Methods — techniques the papers use, named apart from their topics
multi-target learning · 1.7cascaded U2Net-SAM · 1.7
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | An Aesthetic Cultural Relic Poster Generation Framework Based on Multi-target Learning and Multimodal Large Language ModelabstractThis paper presents CrePoster, a data-driven framework to generate aesthetic posters for Chinese cultural relics, aiming to enhance the exhibition experience and promote cultural spread. CrePoster comprises three modules: (1) object segmentation module, (2) content generation module, and (3) poster generation module. Upon processing a cultural relic image, the object segmentation module first leverages a cascaded U2Net-SAM structure to obtain the visual target. Secondly, the content generation module utilizes a multi-target learning-enabled caption generator to produce professional captions. Thirdly, the Multimodal Large Language Model (MLLM) based poster generation module adaptively creates aesthetic parameters, including layout and color scheme, ultimately rendering them into refined posters. Mohan Zhang, Qianqian Hu, Chuhan Li, Yanxiu Dan, Shenglan Cui, Fang Liu 0002 |
ACM Multimedia | 4 |