SALICON: Saliency in Context

By Ming Jiang, Shengsheng Huang, Juanyong Duan, Qi Zhao. 2015

756 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions? (2016, methodology): “(Jiang et al., 2015) established mouse tracking as an accurate ap-”
Global-and-local attention networks for visual recognition (2018, methodology): “We tested human responses on 40 target (animal) and 40 distractor (non-animal) images gathered from the SALICON [40] subset of the Microsoft COCO 2014.”
Faster gaze prediction with dense networks and Fisher pruning (2018, methodology): “As in [6], the model was first pre-trained using the SALICON dataset [15] while using the MIT1003 dataset [16] for validation.”
A Comprehensive Survey of Deep Learning for Image Captioning (2018, methodology): “For experiments, it uses SALICON dataset [60] and achieves good results.”
End-to-end Convolutional Network for Saliency Prediction (2015, methodology): “Table 1 and Table 2 presents our results for iSUN and SALICON datasets.”
Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset (2019, background): “Examples include MIT saliency benchmark (Bylinskii et al. ), CAT2000 (Borji and Itti 2015), and SALICON (Jiang et al. 2015).”
Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, methodology): “We use the static stimuli (10, 000 images) from the training set of SALICON [31] dataset for training our attention module.”
Attentive Systems: A Survey (2017, background): “In addition, other modalities that impact visual saliency are explored, i.e., depth (Lang et al. 2012; Desingh et al. 2013), touch (Ni et al. 2014), computer mouse movement (Jiang et al. 2015a), and audio factors (Chen et al. 2014).”
Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention (2017, methodology): “With the arrival of the SALICON dataset [19], which is still the large publicly available dataset for saliency prediction, several deep architectures have moved beyond previous approaches bringing consistent performance advances. starting point of all these architectures is a pre-trained Convolution”
Saliency in VR: How Do People Explore Virtual Environments? (2016, methodology): “[24] proposed a new methodology to collect attentional data on scales sufficient for these deep learning methods.”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “of saliency datasets has increased, and many benchmarks provide training data from which systematic parameters can be learned [14], [33], [37].”
Shallow and Deep Convolutional Networks for Saliency Prediction (2016, methodology): “SALICON [14] Microsoft CoCo [19] Mouse clicks Crowd 10,000 5,000 5,000 iSUN SUN [29] Eyetracker Crowd 6,000 926 2,000 MIT300 [2] Flickr and LabelMe [24] Eyetracker 39 300”
Learning Uncertain Convolutional Features for Accurate Saliency Detection (2017, methodology): “AUC-J sAUC CC NSS IG MIT300 [19] 0.8584 0.7109 0.7423 2.14 - iSUN [47] 0.8615 0.5498 0.8142 - 0.1725 SALICON[17] 0.7621 0.6326 0.8453 - 0.3167 Table 3.”
A deep multi-level network for saliency prediction (2016, methodology): “We evaluate the effectiveness of our proposal on two publicly available datasets: SALICON [24] and MIT300 [28].”
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks (2017, methodology): “A new version called DeepGaze 2 [21] using VGG-19 [27] and trained with the SALICON dataset [12] has recently achieved the best results in the MIT saliency benchmark.”