Bi-directional exponential angular triplet loss for RGB-infrared person re-identification
RGB-Infrared person re-identification (RGB-IR Re-ID) is a cross-modality matching problem,
where the modality discrepancy is a big challenge. Most existing works use Euclidean metric …
where the modality discrepancy is a big challenge. Most existing works use Euclidean metric …
Orientation driven bag of appearances for person re-identification
Person re-identification (re-id) consists of associating individual across camera network,
which is valuable for intelligent video surveillance and has drawn wide attention. Although …
which is valuable for intelligent video surveillance and has drawn wide attention. Although …
Precise region semantics‐assisted GAN for pose‐guided person image generation
J Liu, Z Weng, Y Zhu - CAAI Transactions on Intelligence …, 2024 - Wiley Online Library
Generating a realistic person's image from one source pose conditioned on another different
target pose is a promising computer vision task. The previous mainstream methods mainly …
target pose is a promising computer vision task. The previous mainstream methods mainly …
Saliency preprocessing for person re-identification images
C Ma, Z Miao, M Li - 2016 IEEE International Conference on …, 2016 - ieeexplore.ieee.org
In this paper, we propose a preprocessing strategy for refining the pedestrian images in
person re-identification (re-id). The accomplishment of the person re-id task depends on the …
person re-identification (re-id). The accomplishment of the person re-id task depends on the …
LPCV: Learning projections from corresponding views for person re-identification
H Liu, Q Guan - … Conference on Acoustics, Speech and Signal …, 2017 - ieeexplore.ieee.org
Person re-identification is an important topic in visual surveillance, which aims at
recognizing an individual over disjoint camera views. As a major aspect of person re …
recognizing an individual over disjoint camera views. As a major aspect of person re …
Taichi distance for person re-identification
Metric learning is an important issue in person re-identification, and Mahalanobis-distance
based metric learning methods prevail in this field. All of these approaches can be …
based metric learning methods prevail in this field. All of these approaches can be …
Multiple Metric Learning in Kernel Space for Person Re-identification
T Xu, Y Song, Y Zhang - … Vision: Second CCF Chinese Conference, CCCV …, 2017 - Springer
In this paper, we present multiple metric learning in kernel space to preferably get more
discriminative metrics. Usually, the kernel-based approaches exploit kernel trick to map …
discriminative metrics. Usually, the kernel-based approaches exploit kernel trick to map …