EDBT 2026 Demo / reviewers in the wild / expert
Song-Lu Chen
dblp:187/9111 · also Songlu Chen
· DBLP profile ↗
4ranked-venue papers in the field
1as first author
4since 2021 · last 2026
0000-0002-0780-658XORCID · verified
Domains — venue-derived; a paper can count in several
Other / Interdisciplinary · 3 (1 first)Information Retrieval & Web Search · 1
| Year | Publication | Venue | Position |
|---|---|---|---|
| 2026 | Beyond Optical Flow: Latent Micro-Motion as Visual Evidence in UAV VideoabstractOptical flow has long dominated motion representation in video by focusing on explicit pixel displacement caused by object or camera movement. In this work, we argue that video also contains a largely overlooked form of motion information, namely latent micro-motion, which arises from subtle, structure-constrained responses of rigid components to physical interaction with the environment. We study this phenomenon in UAV video, a physically grounded setting where onboard structures are continuously exposed to aerodynamic forces. Although such micro-motions are low in amplitude and are often treated as noise or residual vibration, we show that they form a consistent visual signal that becomes observable through structure-aware and temporally aggregated analysis, even when using simple segmentation and coarse motion descriptors. Through an exploratory analysis, we demonstrate that micro-motion patterns exhibit clear structure and respond systematically to changes in wind conditions, with particularly strong sensitivity to wind direction and weaker dependence on wind magnitude in the examined scenarios. These observations suggest that micro-motion constitutes a distinct regime of motion information in video, complementary to explicit displacement, and motivate a broader reconsideration of how motion is represented and exploited in physically grounded multimedia scenarios. Bowen Zhang 0011, Song-Lu Chen, Xiaobin Zhu 0001, Xu-Cheng Yin |
ICMR | 3 |
| 2024 | Multi-task Learning for License Plate Recognition in Unconstrained Scenarios
Zhen-Lun Mo, Song-Lu Chen, Qi Liu 0041, Feng Chen 0040, Xu-Cheng Yin |
ICDAR (1) | 2 |
| 2023 | End-to-End Multi-line License Plate Recognition with Cascaded Perception
Song-Lu Chen, Qi Liu 0041, Feng Chen 0040, Xu-Cheng Yin |
ICDAR (5) | 1 |
| 2021 | Fast Recognition for Multidirectional and Multi-type License Plates with 2D Spatial Attention
Qi Liu 0041, Song-Lu Chen, Zhen-Jia Li, Feng Chen 0040, Xu-Cheng Yin |
ICDAR (4) | 2 |