DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations

Kruthiventi, Srinivas S. S.; Kumar, Ashish; Babu, R. Venkatesh

doi:10.48550/arxiv.1510.02927

Cited by 21 publications

(44 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the effectiveness of the proposed deep attention model in predicting eye fixations, we evaluated it by comparison to 13 state-of-the-art models, including six classical models: ITTI [29], GBVS [44], Judd Model [25], BMS [67], CAS [47], AIM [66], and seven deep learning based models: DeeFix [51], SALICON [52], Mr-CNN [4], SalNet [15], Deep Gaze I [48], eDN [13], and SU [16]. These methods have been proposed in recent years or widely used for comparison.…”

Section: Comparison Resultsmentioning

confidence: 99%

“…DeepGaze II [50] (from DeepGaze [48]), recently was proposed that provides a deeper network with VGG19 [23], where the attention information is directly inferred from the original VGGNet, without fine-tuning on attention dataset. Kruthiventi et al [51] also proposed a DeepFix model based on VGG16. In [16], saliency prediction and object detection were achieved in a deep CNN.…”

Section: A Saliency Detectionmentioning

confidence: 99%

“…1) Single-stream network: As demonstrated in Fig. 2(a), single-stream network is the standard architecture of CNNs based attention models, which is opted by many saliency detection works [51], [14], [16], [15]. All other kinds of deep learning architectures can be viewed as variations of single-stream network.…”

Section: B Deep Learning Architectures Of Saliency Detection Modelsmentioning

confidence: 99%

“…where S and G are normalized to be probability distributions, given a saliency map S and the continuous fixation map G. A SIM of one indicates the distributions are the same, while a SIM of zero indicates no overlap. * DeeFix [51] is fine-tuned with 900 images of MIT1003 dataset, while evaluated on the other 103 images.…”

Section: ) Similarity Metric (Sim)mentioning

confidence: 99%

See 3 more Smart Citations

Deep Visual Attention Prediction

Wang,

Shen

2017

Preprint

View full text Add to dashboard Cite

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve CNN based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark datasets demonstrate our method yields state-of-the-art performance with competitive inference time 1 .

show abstract

Section: Comparison Resultsmentioning

confidence: 99%

Section: A Saliency Detectionmentioning

confidence: 99%

Section: B Deep Learning Architectures Of Saliency Detection Modelsmentioning

confidence: 99%

Section: ) Similarity Metric (Sim)mentioning

confidence: 99%

See 2 more Smart Citations

Deep Visual Attention Prediction

Wang,

Shen

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…[19] in particular proposes a CNN trained on a large dataset of 2.5M frames collected from ∼1500 subjects, and demonstrates a tracking error of 1 − 2cm. In general, CNNs are being successfully employed for saliency detection in images [20,3,16,15]. The common theme behind all these approaches is that the estimate is a 2D position or saliency map, and all of these rely on appearance-only eye gaze estimation.…”

Section: Methodsmentioning

confidence: 99%

MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality

Wu¹,

Rajendran²,

As³

et al. 2020

Preprint

View full text Add to dashboard Cite

With the emergence of Virtual and Mixed Reality (XR) devices, eye tracking has received significant attention in the computer vision community. Eye gaze estimation is a crucial component in XRenabling energy efficient rendering, multi-focal displays, and effective interaction with content. In head-mounted XR devices, the eyes are imaged off-axis to avoid blocking the field of view. This leads to increased challenges in inferring eye related quantities and simultaneously provides an opportunity to develop accurate and robust learning based approaches. To this end, we present MagicEyes, the first large scale eye dataset collected using real MR devices with comprehensive ground truth labeling. MagicEyes includes 587 subjects with 80, 000 images of human-labeled ground truth and over 800, 000 images with gaze target labels. We evaluate several state-of-the-art methods on MagicEyes and also propose a new multi-task EyeNet model designed for detecting the cornea, glints and pupil along with eye segmentation in a single forward pass.

show abstract

Advanced Statistical Methods for Eye Movement Analysis and Modelling: A Gentle Introduction

Boccignone

2019

Eye Movement Research

View full text Add to dashboard Cite

DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations

Cited by 21 publications

References 0 publications

Deep Visual Attention Prediction

Deep Visual Attention Prediction

MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality

Advanced Statistical Methods for Eye Movement Analysis and Modelling: A Gentle Introduction

Contact Info

Product

Resources

About