Search Results for author:
Found 5 papers, 2 papers with code
CCPA: Long-term Person Re-Identification via Contrastive Clothing and Pose Augmentation
Long-term Person Re-Identification (LRe-ID) aims at matching an individual across cameras after a long period of time, presenting variations in clothing, pose, and viewpoint.
Data Quality Aware Approaches for Addressing Model Drift of Semantic Segmentation Models
In the midst of the rapid integration of artificial intelligence (AI) into real world applications, one pressing challenge we confront is the phenomenon of model drift, wherein the performance of AI models gradually degrades over time, compromising their effectiveness in real-world, dynamic environments.
Attention-based Shape and Gait Representations Learning for Video-based Cloth-Changing Person Re-Identification
Our ASGL framework improves Re-ID performance under clothing variations by learning clothing-invariant gait cues using a Spatial-Temporal Graph Attention Network (ST-GAT).
Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-Identification
In this paper, we propose "Contrastive Viewpoint-aware Shape Learning for Long-term Person Re-Identification" (CVSL) to address these challenges.
Cloth-Changing Person Re-Identification
Contrastive Learning
+1
Temporal 3D Shape Modeling for Video-Based Cloth-Changing Person Re-Identification
In this work, we propose "Temporal 3D ShapE Modeling for VCCRe-ID" (SEMI), a lightweight end-to-end framework that addresses these issues by learning human 3D shape representations.
