Demo Data from EDBT 2026 / reviewers in the wild / expert
Wangpeng He
dblp:172/1118
· DBLP profile ↗
4ranked-venue papers
0as first author
3since 2021 · last 2025
0000-0001-9491-3342ORCID · corroborated
Domains — the database's venue-derived domains; a paper can count in several
Artificial intelligence and machine learning · 2 · 2 since 2021Graphics, computer vision, multimedia, augmented reality and games · 2 · 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.
| Databases, data mining, and information retrieval
1 paper |
Information retrieval · 100% |
Topics — the 3 heaviest of 3, each with the papers that count most for it
| Topic | Weight | Papers | Last | Evidence papers |
|---|---|---|---|---|
Information retrieval
retrieval models |
0.4 | 1 | 2019 | O2O Method for Fast 2D Shape Retrieval · IEEE Trans. Image Process. 2019 |
Information retrieval › reranking
search result re-ranking |
0.4 | 1 | 2019 | O2O Method for Fast 2D Shape Retrieval · IEEE Trans. Image Process. 2019 |
Information retrieval › image retrieval
shape retrieval |
0.4 | 1 | 2019 | O2O Method for Fast 2D Shape Retrieval · IEEE Trans. Image Process. 2019 |
Methods — techniques the papers use, named apart from their topics
post-processing · 0.4online reranking · 0.4offline analysis · 0.4
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2025 | NTFNet: Narrowing-Then-Fusing network for RGB-TIR semantic segmentation
Junjie Ye 0006, Wangpeng He, Zhiqiang Qu, Ruoxuan Xu |
Appl. Intell. | 3 |
| 2023 | Wavelet Knowledge Distillation via Decoupled Target for Scene Text Detection
Kefan Qu, Jianmin Lin, Wangpeng He |
ICIG (3) | 5 |
| 2022 | Superpixels with contour adherence via label expansion for image decomposition
Cheng Li 0017, Wangpeng He, Nannan Liao, Jianglei Gong, Shuwei Hou, Baolong Guo 0001 |
Neural Comput. Appl. | 2 |
| 2019 | O2O Method for Fast 2D Shape RetrievalabstractA novel post-processing method, online to offline (O2O), to improve the efficiency of shape retrieval is proposed in this paper. The essence of this proposed method is to move more work that requires a lot of computation to offline. Based on this approach, the O2O rerank the retrieval result online with the help of the offline analysis. The result of offline analysis can be reused indefinitely, regardless of the query shape, as long as the database is unchanged. Therefore, O2O is very efficient and suitable for real-time applications. We evaluated our method for shape retrieval and recognition on five databases including MPEG-7 CE-1 Part B, Tari 1000, Animals, Kimia 99, and Swedish Plant Leaf. Our experimental results show that as a post-processing algorithm, O2O provides highly efficient and effective shape retrieval. Baolong Guo 0001, Yunyi Yan, Wangpeng He |
IEEE Trans. Image Process. | 4 |