Computer vision applications in construction safety assurance
Advancements in the development of deep learning and computer vision-based approaches
have the potential to provide managers and engineers with the ability to improve the safety …
have the potential to provide managers and engineers with the ability to improve the safety …
Person re-identification based on metric learning: a survey
Person re-identification is a challenging research issue in computer vision and has a broad
application prospect in intelligent security. In recent years, with the emergence of large-scale …
application prospect in intelligent security. In recent years, with the emergence of large-scale …
Vehicle re-identification using quadruple directional deep learning features
In order to resist the adverse effect of viewpoint variations, we design quadruple directional
deep learning networks to extract quadruple directional deep learning features (QD-DLF) of …
deep learning networks to extract quadruple directional deep learning features (QD-DLF) of …
A multiscale fusion convolutional neural network for plant leaf recognition
J Hu, Z Chen, M Yang, R Zhang… - IEEE Signal Processing …, 2018 - ieeexplore.ieee.org
Plant leaf recognition is a computer vision task used to automatically recognize plant
species. It is very challenging since rich plant leaf morphological variations, such as sizes …
species. It is very challenging since rich plant leaf morphological variations, such as sizes …
Attribute-image person re-identification via modal-consistent metric learning
Attribute-image person re-identification (AIPR) is a cross-modal retrieval task that searches
person images who meet a list of attributes. Due to large modal gaps between attributes and …
person images who meet a list of attributes. Due to large modal gaps between attributes and …
An efficient multiresolution network for vehicle reidentification
In general, vehicle images have varying resolutions due to vehicles' movements and
different camera settings. However, most existing vehicle reidentification models are single …
different camera settings. However, most existing vehicle reidentification models are single …
Incomplete descriptor mining with elastic loss for person re-identification
H Tan, X Liu, Y Bian, H Wang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In this paper, we propose a novel person Re-ID model, Consecutive Batch DropBlock
Network (CBDB-Net), to capture the attentive and robust person descriptor for the person Re …
Network (CBDB-Net), to capture the attentive and robust person descriptor for the person Re …
Learning sparse and identity-preserved hidden attributes for person re-identification
Person re-identification (Re-ID) aims at matching person images captured in non-
overlapping camera views. To represent person appearance, low-level visual features are …
overlapping camera views. To represent person appearance, low-level visual features are …
Occlusion-sensitive person re-identification via attribute-based shift attention
Occluded person re-identification is one of the most challenging tasks in security
surveillance. Most existing methods focus on extracting human body features from occluded …
surveillance. Most existing methods focus on extracting human body features from occluded …
Re-id done right: towards good practices for person re-identification
Training a deep architecture using a ranking loss has become standard for the person re-
identification task. Increasingly, these deep architectures include additional components that …
identification task. Increasingly, these deep architectures include additional components that …