Cycas: Self-supervised cycle association for learning re-identifiable descriptions
This paper proposes a self-supervised learning method for the person re-identification (re-
ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as …
ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as …
Large-scale pre-training for person re-identification with noisy labels
This paper aims to address the problem of pre-training for person re-identification (Re-ID)
with noisy labels. To setup the pre-training task, we apply a simple online multi-object …
with noisy labels. To setup the pre-training task, we apply a simple online multi-object …
Learning person re-identification models from videos with weak supervision
X Wang, M Liu, DS Raychaudhuri… - … on Image Processing, 2021 - ieeexplore.ieee.org
Most person re-identification methods, being supervised techniques, suffer from the burden
of massive annotation requirement. Unsupervised methods overcome this need for labeled …
of massive annotation requirement. Unsupervised methods overcome this need for labeled …
Semi-supervised person re-identification using multi-view clustering
Abstract Person Re-Identification (Re-Id) is a challenging task focusing on identifying the
same person among disjoint camera views. A number of deep learning algorithms have …
same person among disjoint camera views. A number of deep learning algorithms have …
A novel semi-supervised learning approach to pedestrian reidentification
H Han, W Ma, MC Zhou, Q Guo… - IEEE Internet of Things …, 2020 - ieeexplore.ieee.org
One of the important Internet-of-Things applications is to use image and video to realize
automatic people monitoring, surveillance, tracking, and reidentification (Re-ID). Despite …
automatic people monitoring, surveillance, tracking, and reidentification (Re-ID). Despite …
Distilled person re-identification: Towards a more scalable system
Person re-identification (Re-ID), for matching pedestrians across non-overlapping camera
views, has made great progress in supervised learning with abundant labelled data …
views, has made great progress in supervised learning with abundant labelled data …
Tracklet self-supervised learning for unsupervised person re-identification
Existing unsupervised person re-identification (re-id) methods mainly focus on cross-domain
adaptation or one-shot learning. Although they are more scalable than the supervised …
adaptation or one-shot learning. Although they are more scalable than the supervised …
Camera-aware proxies for unsupervised person re-identification
This paper tackles the purely unsupervised person re-identification (Re-ID) problem that
requires no annotations. Some previous methods adopt clustering techniques to generate …
requires no annotations. Some previous methods adopt clustering techniques to generate …
Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning
We focus on the one-shot learning for video-based person re-Identification (re-ID).
Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre-processing …
Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre-processing …
Progressive cross-camera soft-label learning for semi-supervised person re-identification
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which
only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels …
only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels …