Methods for comparing scanpaths and saliency maps: strengths and weaknesses

By O. Le Meur, Thierry Baccino. Behavior Research Methods, 2012

344 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/a98a0079fef4c434e5e1f775ce47f8151149bf47

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ling Shao
2. Ming-Hsuan Yang
3. Luc Van Gool
4. Deng-Ping Fan
5. Ming-Ming Cheng
6. Antonio Torralba
7. Jianbing Shen
8. Jitendra Malik

In Sensory Systems

1. Akanksha Saran
2. R. Venkatesh Babu
3. Yuchao Dai
4. Dana H. Ballard
5. Srinivas S. S. Kruthiventi
6. Jing Zhang
7. Kumar Ayush
8. Deng-Ping Fan

In Human-Computer Interaction

1. Ruohan Zhang
2. Scott Niekum
3. Akanksha Saran
4. Antonio Torralba
5. Aude Oliva
6. Dana H. Ballard
7. Elaine Schaertl Short
8. Lin Guan

Citations in the corpus

• DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, background): “The sigma for this Gaussian smoothing is generally chosen to be 1 degree of visual angle (dva) [60].”
• UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, background): “According to research in human visual perception [33], visual saliency detection is subjective to some extent.”
• Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics (2013, methodology): “Lemeur in [16] also reported about methods for comparing scanpaths and saliency maps.”
• Efficiently Guiding Imitation Learning Algorithms with Human Gaze (2020, methodology): “To generate gaze heatmaps, the discrete gaze positions are converted into a continuous distribution (Bylinskii et al. 2018) by blurring each fixation location using a Gaussian with a standard deviation equal to one visual degree (Le Meur and Baccino 2013).”
• Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset (2019, methodology): “In standard practice, discrete gaze positions are converted into a continuous distribution (Bylinskii et al. 2018) by blurring each fixation location using a Gaussian with σ equals to one visual degree (Le Meur and Baccino 2013).”
• What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, methodology): “Metric Denoted here Evaluation papers appearing in Area under ROC Curve AUC [9], [23], [24], [49], [57], [68], [88], [93] Shuffled AUC sAUC [8], [9], [49], [68] Normalized Scanpath Saliency NSS [8], [9], [23], [49], [57], [68], [88], [93] Pearson’s Correlation Coefficient CC [8], [9], [23], [24], [4”