Yuying Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuying Liang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Bin Wang
School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China
2 shared publications - Lei Cai
School of Engineering, Huaqiao University, Quanzhou 362021, China
2 shared publications - Hexi Li
School of Computing, Guangzhou College of Applied Science and Technology, Zhaoqing 526072, China
1 shared publication - Huakun Huang
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China
1 shared publication Huanqiang Zeng
1 shared publication- Jinquan Yang
School of Computing, Guangzhou College of Applied Science and Technology, Zhaoqing 526072, China
1 shared publication
Latest Publications
- Open Access
DW-ReID: Vision–Language Learning for Person Re-Identification Under Diverse Weather Conditions
Person re-identification (ReID) under diverse weather conditions remains a critical yet insufficiently explored problem. Most existing ReID approaches are developed and benchmarked on clear-weather datasets, resulting in significant performance degradation when deployed in rainy, snowy, or hazy environments. Conventional image restoration methods, typically optimized for low-level image quality metrics, are often misaligned with the objectives of high-level identity discrimination and thus fail to improve the person ReID performance. To address these limitations, we propose DW-ReID, a unified framework that integrates weather-degraded image restoration with person re-identification tasks. The proposed DW-ReID is built upon a large-scale Contrastive Language-Image Pre-training (CLIP) model and achieved by a two-stage training paradigm. In the first stage, a set of learnable text prompts is optimized to construct identity-specific ambiguous descriptions for each person’s identity. In the second stage, the optimized text descriptions, together with a frozen text encoder, provide language supervision to jointly train a weather encoder, an image restorer, and a ReID encoder in an end-to-end manner. The experimental results on two our contributed synthetic datasets consistently demonstrate the effectiveness and superior performance of the proposed DW-ReID method.
Open AccessDW-ReID: Vision–Language Learning for Person Re-Identification Under Diverse Weather Conditions
Person re-identification (ReID) under diverse weather conditions remains a critical yet insufficiently explored problem. Most existing ReID approaches are developed and benchmarked on clear-weather datasets, resulting in significant performance degradation when deployed in rainy, snowy, or hazy environments. Conventional image restoration methods, typically optimized for low-level image quality metrics, are often misaligned with the objectives of high-level identity discrimination and thus fail to improve the person ReID performance. To address these limitations, we propose DW-ReID, a unified framework that integrates weather-degraded image restoration with person re-identification tasks. The proposed DW-ReID is built upon a large-scale Contrastive Language-Image Pre-training (CLIP) model and achieved by a two-stage training paradigm. In the first stage, a set of learnable text prompts is optimized to construct identity-specific ambiguous descriptions for each person’s identity. In the second stage, the optimized text descriptions, together with a frozen text encoder, provide language supervision to jointly train a weather encoder, an image restorer, and a ReID encoder in an end-to-end manner. The experimental results on two our contributed synthetic datasets consistently demonstrate the effectiveness and superior performance of the proposed DW-ReID method.
- 15 January 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 154
Image re-identification: Where self-supervision meets vision-language learning
- 15 January 2025
- Published by Elsevier in Image and Vision Computing
- Vol. 154
Image re-identification: Where self-supervision meets vision-language learning