The human visual system effectively analyzes scenes based on local, global and semantic
properties. Deep learning-based saliency prediction models adopted two-stream networks …

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 …

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 …

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 …

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 …

Recent progress in crowd counting and localization methods mainly relies on expensive
point-level annotations and convolutional neural networks with limited receptive filed, which …

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 …

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 …

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 …