Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics
By Nicolas Riche, Matthieu Duvinage, Matei Mancas, Bernard Gosselin, Thierry Dutoit. IEEE International Conference on Computer Vision, 2013
298 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Sensory Systems
View Paper: https://www.semanticscholar.org/paper/79c761353fe46544a758b284813dfa2908664db2
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
- Wenguan Wang
- Jianbing Shen
- Rita Cucchiara
- Lorenzo Baraldi
- Marcella Cornia
- Luc Van Gool
- Ming-Ming Cheng
- Kristen Grauman
In Sensory Systems
- Jianbing Shen
- Wenguan Wang
- Rita Cucchiara
- Xavier Giró-i-Nieto
- Dana H. Ballard
- Lorenzo Baraldi
- Giuseppe Serra
- Ruohan Zhang
Citations in the corpus
- Saliency in VR: How Do People Explore Virtual Environments? (2016, background): “Significant prior work explored rigorous benchmarking of saliency models, the impact of the metric on the evaluation result, and shortcomings of state-of-the-art models at the time [4, 6, 45].”
- AGIL: Learning Attention from Human for Visuomotor Tasks (2018, methodology): “The performance of the algorithms are evaluated using four standard metrics in the visual saliency literature [33]: Normalized Scanpath Saliency (NSS), Area Under the Curve (AUC), Kullback-Leibler divergence (KL), and Correlation Coefficient (CC).”
- Free-Lunch Saliency via Attention in Atari Agents (2019, methodology): “Following [29], we computed three metrics: normalized scanpath saliency (NSS) [28], KL divergence, and shuffled AUC [6].”
- Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model (2016, background): “In fact, saliency evaluation metrics can be categorized in location-based and distribution-based metrics [63], [64], [65].”
- SalGAN: Visual Saliency Prediction with Generative Adversarial Networks (2017, background): “A thorough comparison of metrics can be found in [3]).”
- A deep multi-level network for saliency prediction (2016, background): “…of these metrics compare the predicted saliency map with the ground truth map generated from [26] 0.4268 0.6935 0.7899 Baseline: GBVS [27] 0.4212 0.6303 0.7899 Baseline: Itti [2] 0.2046 0.6101 0.6669 fixation points, while other directly compare the predicted saliency map with fixation points [31].”
- Deep Visual Attention Prediction (2017, background): “Previous studies on saliency metrics [65] show that it’s hard to achieve a fair comparison for evaluating saliency models by any single metric.”