Cargando…
Superpixel-Based Temporally Aligned Representation for Video-Based Person Re-Identification †
Most existing person re-identification methods focus on matching still person images across non-overlapping camera views. Despite their excellent performance in some circumstances, these methods still suffer from occlusion and the changes of pose, viewpoint or lighting. Video-based re-id is a natura...
Autores principales: | Gao, Changxin, Wang, Jin, Liu, Leyuan, Yu, Jin-Gang, Sang, Nong |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6766808/ https://www.ncbi.nlm.nih.gov/pubmed/31500196 http://dx.doi.org/10.3390/s19183861 |
Ejemplares similares
-
Sparse Adversarial Video Attacks via Superpixel-Based Jacobian Computation
por: Du, Zhenyu, et al.
Publicado: (2022) -
Superpixel Segmentation Based on Anisotropic Edge Strength
por: Wang, Gang, et al.
Publicado: (2019) -
Multi-Level Fusion Temporal–Spatial Co-Attention for Video-Based Person Re-Identification
por: Pei, Shengyu, et al.
Publicado: (2021) -
Optimal Superpixel Kernel-Based Kernel Low-Rank and Sparsity Representation for Brain Tumour Segmentation
por: Ge, Ting, et al.
Publicado: (2022) -
Robust Global Motion Estimation for Video Stabilization Based on Improved K-Means Clustering and Superpixel
por: Wu, Rouwan, et al.
Publicado: (2021)