Predicting eye fixations using convolutional neural networks

By Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu. 2015

249 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Human-Computer Interaction

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

In Ophthalmology

In Human-Computer Interaction

Citations in the corpus

Recent advances in convolutional neural networks (2015, background): “[169] for saliency prediction are shared across three CNN”
A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (2019, background): “Deep learning-based attention models [29], [30], [31], [32], [33], [34] become increasingly popular in recent years, driven by the success of deep learning in object recognition and large-scale visual attention dataset (e.”
Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model (2016, methodology): “[43] presented a multi-resolution CNN (Mr-CNN) fine-tuned over image patches centered on fixation and nonfixation locations.”
Recurrent Mixture Density Network for Spatiotemporal Visual Attention (2016, methodology): “have been trained to produce saliency maps in this way [41, 14, 42, 32, 43, 44].”
Predicting the Driver's Focus of Attention: The DR(eye)VE Project (2017, background): “the-art results on public benchmarks [15], [16], [28], [34], [37].”
Object Detection With Deep Learning: A Review (2018, background): “[27] proposed a multi-resolution convolutional neural network (Mr-CNN) to predict eye fixations, which is achieved by learning both bottom-up visual saliency and top-down visual factors from raw image data simultaneously.”
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, methodology): “[34] construct an ensemble of CNNs, termed as Multiresolution-CNN, for predicting eye fixations.”
Recurrent Attentional Networks for Saliency Detection (2016, background): “Although there have been works on developing CNNs for visual saliency modeling, they either focus on predicting eye fixations [31], or applying CNNs to predict just the saliency value of visual sub-units (e.”
Deep learning in bioinformatics (2016, background): “One of the most important advancements thus far has been in image and speech recognition [9-15], although promising results have been disseminated in natural language processing [16, 17] and language translation [18, 19].”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “Recently, deep learning is also exploited for eye-fixation prediction (Liu et al. 2015).”
Shallow and Deep Convolutional Networks for Saliency Prediction (2016, background): “[20] proposed an architecture with three convnets working in parallel where the three final fully connected layers are combined in a single layer to obtain the saliency map.”
Non-local Deep Features for Salient Object Detection (2017, methodology): “While some methods apply a straight forward convolutional neural net (CNN) model [36], others have proposed a model tailored to the saliency detection problem [25, 26, 29, 43, 50].”
Explaining Distributed Neural Activations via Unsupervised Learning (2017, background): “Various publications have recently addressed the problem of utilizing CNNs for saliency prediction [12, 15].”
SALICON: Reducing the Semantic Gap in Saliency Prediction by Adapting Deep Neural Networks (2015, result): “We also compare our model with a very recently published saliency model based on DNN [26].”
Gaze Prediction in Dynamic 360° Immersive Videos (2018, background): “Recently, advances in deep learning have produced more accurate models [20] [33] [28] [37] [24].”
BASNet: Boundary-Aware Salient Object Detection (2019, background): “Patch-wise Deep Methods: Encouraged by the advancement on image classification of Deep CNNs [28, 59], early deep salient object detection methods search for salient objects by classifying image pixels or super pixels into salient or non-salient classes based on the local image patches extracted from”
Seeing with Humans: Gaze-Assisted Neural Image Captioning (2016, background): “In addition, the performance gap between human gaze and visual saliency poses another important research question; whether computational saliency models can achieve similar performance, especially with recently proposed deep models [68], [69].”