Advancing 3D point cloud understanding through deep transfer learning: A comprehensive survey
The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …
deep learning (DL). However, the latter faces various issues, including the lack of data or …
Rethinking spatial invariance of convolutional networks for object counting
Previous work generally believes that improving the spatial invariance of convolutional
networks is the key to object counting. However, after verifying several mainstream counting …
networks is the key to object counting. However, after verifying several mainstream counting …
[HTML][HTML] Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization
Y Himeur, S Al-Maadeed, H Kheddar… - … Applications of Artificial …, 2023 - Elsevier
Recently, developing automated video surveillance systems (VSSs) has become crucial to
ensure the security and safety of the population, especially during events involving large …
ensure the security and safety of the population, especially during events involving large …
Crowdclip: Unsupervised crowd counting via vision-language model
Supervised crowd counting relies heavily on costly manual labeling, which is difficult and
expensive, especially in dense scenes. To alleviate the problem, we propose a novel …
expensive, especially in dense scenes. To alleviate the problem, we propose a novel …
Striking a balance: Unsupervised cross-domain crowd counting via knowledge diffusion
Supervised crowd counting relies on manual labeling, which is costly and time-consuming.
This led to an increased interest in unsupervised methods. However, there is a significant …
This led to an increased interest in unsupervised methods. However, there is a significant …
Forget less, count better: a domain-incremental self-distillation learning benchmark for lifelong crowd counting
Crowd counting has important applications in public safety and pandemic control. A robust
and practical crowd counting system has to be capable of continuously learning with the …
and practical crowd counting system has to be capable of continuously learning with the …
Daot: Domain-agnostically aligned optimal transport for domain-adaptive crowd counting
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps
between different datasets. However, existing domain adaptation methods tend to focus on …
between different datasets. However, existing domain adaptation methods tend to focus on …
Backdoor attacks on crowd counting
Crowd counting is a regression task that estimates the number of people in a scene image,
which plays a vital role in a range of safety-critical applications, such as video surveillance …
which plays a vital role in a range of safety-critical applications, such as video surveillance …
Fine-grained fragment diffusion for cross domain crowd counting
Deep learning improves the performance of crowd counting, but model migration remains a
tricky challenge. Due to the reliance on training data and inherent domain shift, model …
tricky challenge. Due to the reliance on training data and inherent domain shift, model …
Crowd counting via unsupervised cross-domain feature adaptation
G Ding, D Yang, T Wang, S Wang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Given an image, crowd counting aims to estimate the amount of target objects in the image.
With un-predictable installation situations of surveillance systems (or other equipments) …
With un-predictable installation situations of surveillance systems (or other equipments) …