P Zhang, M Xu, Z Zhang, P Gao, J Zhang - Neurocomputing, 2023 - Elsevier
The main purpose of RGB-T salient object detection (SOD) is to fully integrate and exploit the information from the complementary fusion of modalities to address the …
M Zhang, J Li, T Zhou - Proceedings of the 30th ACM International …, 2022 - dl.acm.org
This paper solves the problem of learning image semantic segmentation using image-level supervision. The task is promising in terms of reducing annotation efforts, yet extremely …
Z Wang, Y Zhang, Y Liu, D Zhu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Existing lightweight salient object detection (SOD) methods aim to solve the problem of high computational costs that is prevalent with heavyweight methods. However, compared with …
L Liang, H Zhao, F Zhou, Q Zhang, Z Song, Q Shi - Applied Intelligence, 2023 - Springer
Accurate crowd counting is still challenging due to the variations of crowd heads. Most of crowd counting methods adopt multi-branch networks to extract multi-scale information …
M Deng, H Zhao, M Gao - The Visual Computer, 2024 - Springer
Recent progress in crowd counting and localization methods mainly relies on expensive point-level annotations and convolutional neural networks with limited receptive filed, which …
L Liang, H Zhao, F Zhou, M Ma, F Yao, X Ji - Applied Intelligence, 2023 - Springer
The accuracy of crowd counting is susceptible to scale variations of crowd head in the congested scene. Some counting networks, such as crowd density pre-classification …
C Ma, L Du, L Zhuo, J Li - … on Circuits and Systems for Video …, 2023 - ieeexplore.ieee.org
Weakly Supervised Video Salient Object Detection (WSVSOD) only requires coarse-grained manual annotations, which can achieve a good trade-off between labeling efficiency and …
Abstract The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive a dynamic scene, which is significant and imperative in …
Y Zhang, F Chen, Z Peng, W Zou, C Zhang - Entropy, 2023 - mdpi.com
An abundance of features in the light field has been demonstrated to be useful for saliency detection in complex scenes. However, bottom-up saliency detection models are limited in …