Die Dai

Die Dai

Auto-generated profile, based on publicly available information

Die Dai

University of Electronic Science and Technology of China, Chengdu, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 September 2025 in CAAI Transactions on Intelligence Technology
Verified
Journal Article
Open access
DDDie Dai
Die Dai
XZXU ZHANG
XU ZHANG
ZWZhiguang Wu
Zhiguang Wu
Hongying MengHongying Meng
Hongying Meng
ZZZuyu Zhang
Zuyu Zhang
Existing occluded person re‐identification methods employ hard or soft partition strategies to explore fine‐grained information. However, the hard partition strategy which extracts region‐level features may impair the semantic connectivity of correlated human body parts. A pose‐guided soft partition establishes correlations among human keypoints, while the generated pixel‐level embeddings may lose the surrounding semantic information. In this paper, we propose a keypoint‐guided feature partition (KGFP) method that consists of a feature extractor, a hard partition branch, and a soft partition branch. Specifically, we adopt a vision transformer and a pose estimator to extract features and keypoint information. In the hard partition branch, we partition features into distinct groups and classify them into nonoccluded, semi‐occluded, and occluded features to obtain region‐level features and filter out occlusions. Furthermore, we design a dissimilarity loss to reduce the similarity between semi‐occluded and occluded features. In the soft partition branch, we introduce a graph attention network and consider global and keypoint embeddings as nodes of a graph to discover interrelationships. Additionally, we formulate image alignment as a graph matching problem and propose a feature alignment‐based graph to reduce position misalignment. Extensive experiments demonstrate that the proposed method achieves superior performance compared to state‐of‐the‐art methods on Occluded‐DukeMTMC, Markt1501, and DukeMTMC‐reID.


9 November 2026
Verified
Conference Paper
Open access
JYJiaye Yang
Jiaye Yang
YLYao Liu
Yao Liu
PJPeiyuan Jiang
Peiyuan Jiang
DDDie Dai
Die Dai
YXYuewei Xue
Yuewei Xue
QLQiao Liu
Qiao Liu