DP Fan, W Wang, MM Cheng… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset …
W Wang, J Shen, L Shao - IEEE Transactions on Image …, 2017 - ieeexplore.ieee.org
This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: 1) deep video saliency model training with the absence of …
The visual saliency detection model simulates the human visual system to perceive the scene and has been widely used in many vision tasks. With the development of acquisition …
Predicting where people look in static scenes, aka visual saliency, has received significant research interest recently. However, relatively less effort has been spent in understanding …
W Wang, H Song, S Zhao, J Shen… - Proceedings of the …, 2019 - openaccess.thecvf.com
This paper conducts a systematic study on the role of visual attention in Unsupervised Video Object Segmentation (UVOS) tasks. By elaborately annotating three popular video …
F Yan, C Chen, P Xiao, S Qi, Z Wang, R Xiao - Applied Sciences, 2021 - mdpi.com
The human attention mechanism can be understood and simulated by closely associating the saliency prediction task to neuroscience and psychology. Furthermore, saliency …
H Song, W Wang, S Zhao, J Shen… - Proceedings of the …, 2018 - openaccess.thecvf.com
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM). A …
We present a survey on maritime object detection and tracking approaches, which are essential for the development of a navigational system for autonomous ships. The electro …
W Wang, J Shen, F Guo… - Proceedings of the …, 2018 - openaccess.thecvf.com
In this work, we contribute to video saliency research in two ways. First, we introduce a new benchmark for predicting human eye movements during dynamic scene free-viewing, which …