scholarly journals Multi-level Net: A Visual Saliency Prediction Model

Author(s):  
Marcella Cornia ◽  
Lorenzo Baraldi ◽  
Giuseppe Serra ◽  
Rita Cucchiara
Author(s):  
Dandan Zhu ◽  
Defang Zhao ◽  
Xiongkuo Min ◽  
Tian Han ◽  
Qiangqiang Zhou ◽  
...  

2020 ◽  
Vol 34 (07) ◽  
pp. 12410-12417 ◽  
Author(s):  
Xinyi Wu ◽  
Zhenyao Wu ◽  
Jinglin Zhang ◽  
Lili Ju ◽  
Song Wang

The performance of predicting human fixations in videos has been much enhanced with the help of development of the convolutional neural networks (CNN). In this paper, we propose a novel end-to-end neural network “SalSAC” for video saliency prediction, which uses the CNN-LSTM-Attention as the basic architecture and utilizes the information from both static and dynamic aspects. To better represent the static information of each frame, we first extract multi-level features of same size from different layers of the encoder CNN and calculate the corresponding multi-level attentions, then we randomly shuffle these attention maps among levels and multiply them to the extracted multi-level features respectively. Through this way, we leverage the attention consistency across different layers to improve the robustness of the network. On the dynamic aspect, we propose a correlation-based ConvLSTM to appropriately balance the influence of the current and preceding frames to the prediction. Experimental results on the DHF1K, Hollywood2 and UCF-sports datasets show that SalSAC outperforms many existing state-of-the-art methods.


2016 ◽  
Vol 76 (22) ◽  
pp. 23859-23890 ◽  
Author(s):  
Amin Banitalebi-Dehkordi ◽  
Mahsa T. Pourazad ◽  
Panos Nasiopoulos

2021 ◽  
Author(s):  
Sai Phani Kumar Malladi ◽  
Jayanta Mukhopadhyay ◽  
Chaker Larabi ◽  
Santanu Chaudhury

Author(s):  
Bo Dai ◽  
Weijing Ye ◽  
Jing Zheng ◽  
Qianyi Chai ◽  
Yiyang Yao

2016 ◽  
Vol 25 (1) ◽  
pp. 013008 ◽  
Author(s):  
Amin Banitalebi-Dehkordi ◽  
Eleni Nasiopoulos ◽  
Mahsa T. Pourazad ◽  
Panos Nasiopoulos

Author(s):  
C. Xu ◽  
H. G. Sui ◽  
D. R. Li ◽  
K. M. Sun ◽  
J. Y. Liu

Automatic image registration is a vital yet challenging task, particularly for multi-sensor remote sensing images. Given the diversity of the data, it is unlikely that a single registration algorithm or a single image feature will work satisfactorily for all applications. Focusing on this issue, the mainly contribution of this paper is to propose an automatic optical-to-SAR image registration method using –level and refinement model: Firstly, a multi-level strategy of coarse-to-fine registration is presented, the visual saliency features is used to acquire coarse registration, and then specific area and line features are used to refine the registration result, after that, sub-pixel matching is applied using KNN Graph. Secondly, an iterative strategy that involves adaptive parameter adjustment for re-extracting and re-matching features is presented. Considering the fact that almost all feature-based registration methods rely on feature extraction results, the iterative strategy improve the robustness of feature matching. And all parameters can be automatically and adaptively adjusted in the iterative procedure. Thirdly, a uniform level set segmentation model for optical and SAR images is presented to segment conjugate features, and Voronoi diagram is introduced into Spectral Point Matching (VSPM) to further enhance the matching accuracy between two sets of matching points. Experimental results show that the proposed method can effectively and robustly generate sufficient, reliable point pairs and provide accurate registration.


Sign in / Sign up

Export Citation Format

Share Document