Article
Computer Science, Artificial Intelligence
Sheng Jin, Xuyang Dai, Qinghao Meng
Summary: This paper proposes a saliency prediction-based SLAM (SP-SLAM) method that combines ORB-SLAM3 with a saliency prediction model to improve the accuracy of visual SLAM. A multi-level strategy and predicted saliency map are introduced to further enhance system performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Chemistry, Multidisciplinary
Fei Yan, Cheng Chen, Peng Xiao, Siyu Qi, Zhiliang Wang, Ruoxiu Xiao
Summary: This study summarizes the achievements in the field of saliency prediction, including the early neurological and psychological mechanisms, the guiding role of classic models, and the development process and data comparison of classic and deep saliency prediction models. It also discusses the relationship between the model and human vision, the factors causing semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Ying Yu, Jun Qian, Qinglong Wu
Summary: This article proposes a bottom-up visual saliency model using wavelet transform for multiscale analysis and computation in the frequency domain. The model outperforms state-of-the-art approaches in saliency detection and demonstrates effectiveness and robustness in ship detection.
FRONTIERS IN NEUROROBOTICS
(2022)
Article
Computer Science, Artificial Intelligence
Binwei Xu, Haoran Liang, Ronghua Liang, Peng Chen
Summary: This paper proposes a coarse-to-fine network (CFN) for eye fixation prediction, which integrates low-level and high-level features through two different training strategies, achieving competitive performance on multiple benchmark datasets.
IET IMAGE PROCESSING
(2022)
Article
Computer Science, Information Systems
Fei Yan, Zhiliang Wang, Siyu Qi, Ruoxiu Xiao
Summary: This study proposes a multilevel saliency prediction network that uses a combination of spatial and channel information to find possible high-level features, further improving the performance of a saliency model.
Article
Computer Science, Software Engineering
Miroslav Laco, Patrik Polatsek, Simon Dekret, Wanda Benesova, Martina Barankova, Bronislava Strnadelova, Jana Koroniova, Maria Gablikova
Summary: Positive emotions have been found to influence bottom-up visual saliency, leading to a broadening and engagement effect, but may also act as a distractor in certain task performances.
Article
Computer Science, Software Engineering
Melissa Kremer, Peter Caruana, Brandon Haworth, Mubbasir Kapadia, Petros Faloutsos
Summary: This study proposes a parametric model and method for generating real-time saliency maps from the perspective of virtual agents. The model aggregates saliency scores from user-defined parameters and outputs a 2D saliency map that can be modulated by an attention field to incorporate 3D information and a character's state of attentiveness.
COMPUTERS & GRAPHICS-UK
(2022)
Article
Computer Science, Artificial Intelligence
Camilo Jara Do Nascimento, Marcos E. Orchard, Christ Devia
Summary: This study presents an artificial neural architecture that predicts human ocular scanpaths during free viewing of different types of images. By comparing different metrics, the analysis aims to measure spatial and temporal errors in scanpath patterns. The results show significant differences in prediction when people view images with high visual content compared to low visual content. The study provides insights for improving gaze-controlled interfaces, virtual reality, and understanding human visual exploration.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Neurosciences
John E. Kiat, Taylor R. Hayes, John M. Henderson, Steven J. Luck
Summary: Research has found that meaning maps can predict eye movement patterns more effectively than physical saliency in natural scene viewing. This suggests that the brain rapidly extracts the spatial distribution of semantically informative scene regions. This study used representational similarity analysis to demonstrate the link between physical saliency, semantic informativeness, and neural responses.
JOURNAL OF NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Maria Kanwal, M. Mohsin Riaz, Syed Sohaib Ali, Abdul Ghafoor
Summary: A novel scheme is proposed to identify image's saliency by formalizing the saliency map using color, depth, and histogram. The scheme achieves state-of-the-art performance on different images.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Psychology, Experimental
Heinrich R. Liesefeld, Hermann J. Mueller
Summary: The study demonstrates experience-driven top-down modulations of saliency signals at the overall-priority and dimension-specific levels that do not reach down to the specific distractor features. The findings suggest that participants rely on purely space-based suppression rather than feature-specific suppression when faced with distractors in visual search tasks.
JOURNAL OF EXPERIMENTAL PSYCHOLOGY-GENERAL
(2021)
Article
Computer Science, Artificial Intelligence
Wenguan Wang, Jianbing Shen, Jianwen Xie, Ming-Ming Cheng, Haibin Ling, Ali Borji
Summary: This research focuses on predicting visual attention in dynamic scenes, introducing a new benchmark DHF1K and a novel video saliency model ACLNet. Through extensive evaluation on multiple datasets and analysis of saliency models, ACLNet shows superior performance and fast processing speed.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Psychology, Mathematical
Ramin Fahimi, Neil D. B. Bruce
Summary: This paper reviews the history of saliency and visual attention research and analyzes metrics for measuring scanpath similarity. The study demonstrates the necessity of sequential analysis of attention and provides support for certain metrics.
BEHAVIOR RESEARCH METHODS
(2021)
Article
Computer Science, Artificial Intelligence
Weijie Wei, Zhi Liu, Lijin Huang, Alexis Nebout, Olivier Le Meur, Tianhong Zhang, Jijun Wang, Lihua Xu
Summary: This paper models the atypical visual saliency in individuals with ASD using a deep neural network, achieving state-of-the-art performance in predicting atypical attention patterns.
Article
Remote Sensing
Xianpeng Guo, Biao Hou, Chen Yang, Siteng Ma, Bo Ren, Shuang Wang, Licheng Jiao
Summary: This article proposes a method called CSG-CAM to address the explainability issue in remote sensing images. By introducing the concepts of dynamic channel pruning and channel saliency, and using channel saliency as the weights for computing saliency maps on shallow and final layers, the CSG-CAM can effectively fuse the heat maps from these two layers. Experimental results demonstrate the effectiveness of CSG-CAM in terms of both faithfulness and explainability.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2023)