A review of vision-based traffic semantic understanding in ITSs

J Chen, Q Wang, HH Cheng, W Peng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
A semantic understanding of road traffic can help people understand road traffic flow
situations and emergencies more accurately and provide a more accurate basis for anomaly …

Medical image segmentation with limited supervision: a review of deep network models

J Peng, Y Wang - IEEE Access, 2021 - ieeexplore.ieee.org
Despite the remarkable performance of deep learning methods on various tasks, most
cutting-edge models rely heavily on large-scale annotated training examples, which are …

Rethinking counting and localization in crowds: A purely point-based framework

Q Song, C Wang, Z Jiang, Y Wang… - Proceedings of the …, 2021 - openaccess.thecvf.com
Localizing individuals in crowds is more in accordance with the practical demands of
subsequent high-level crowd analysis tasks than simply counting. However, existing …

Distribution matching for crowd counting

B Wang, H Liu, D Samaras… - Advances in neural …, 2020 - proceedings.neurips.cc
In crowd counting, each training image contains multiple people, where each person is
annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth …

Bayesian loss for crowd count estimation with point supervision

Z Ma, X Wei, X Hong, Y Gong - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
In crowd counting datasets, each person is annotated by a point, which is usually the center
of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of …

An end-to-end transformer model for crowd localization

D Liang, W Xu, X Bai - European Conference on Computer Vision, 2022 - Springer
Crowd localization, predicting head positions, is a more practical and high-level task than
simply counting. Existing methods employ pseudo-bounding boxes or pre-designed …

Mapping degeneration meets label evolution: Learning infrared small target detection with single point supervision

X Ying, L Liu, Y Wang, R Li, N Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Training a convolutional neural network (CNN) to detect infrared small targets in a fully
supervised manner has gained remarkable research interests in recent years, but is highly …

Steerer: Resolving scale variations for counting and localization via selective inheritance learning

T Han, L Bai, L Liu, W Ouyang - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Scale variation is a deep-rooted problem in object counting, which has not been effectively
addressed by existing scale-aware algorithms. An important factor is that they typically …

Optimal transport minimization: Crowd localization on density maps for semi-supervised counting

W Lin, AB Chan - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
The accuracy of crowd counting in images has improved greatly in recent years due to the
development of deep neural networks for predicting crowd density maps. However, most …

One thing one click: A self-training approach for weakly supervised 3d semantic segmentation

Z Liu, X Qi, CW Fu - … of the IEEE/CVF conference on …, 2021 - openaccess.thecvf.com
Point cloud semantic segmentation often requires largescale annotated training data, but
clearly, point-wise labels are too tedious to prepare. While some recent methods propose to …