Learning to predict eye fixations for semantic contents using multi-layer sparse network

Shen, Chengyao; Zhao, Qi

doi:10.1016/j.neucom.2013.09.053

Cited by 44 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Very recently, deep learning has been applied for saliency prediction, either in an unsupervised way [59] or in a supervised way using recorded ground truth fixations obtained by gaze tracking [60,61,62,63]. In this paper we adopt the 195 supervised approach and use a 3D CNN.…”

Section: D Cnn For Saliency Predictionmentioning

confidence: 99%

Action recognition using saliency learned from recorded human gaze

Stefic

Patras

2016

Image and Vision Computing

View full text Add to dashboard Cite

This paper addresses the problem of recognition and localization of actions in image sequences, by utilizing, in the training phase only, gaze tracking data of people watching videos depicting the actions in question. First, we learn discriminative action features at the areas of gaze fixation and train a Convolutional Network that predicts areas of fixation (i.e. salient regions) from raw image data. Second, we propose a Support Vector Machine-based recognition method for joint recognition and localization, in which the bounding box of the action in question is considered as a latent variable. In our formulation the optimization attempts to both minimize the classification cost and maximize the saliency within the bounding box. We show that the results obtained with the optimization where saliency within the bounding box is maximized outperform the results obtained when saliency within the bounding box is not maximized, i.e. when only classification cost is minimized. Furthermore, the results that we obtain outperform the state-of-the-art results on the UCF Sports dataset.

show abstract

Section: D Cnn For Saliency Predictionmentioning

confidence: 99%

Action recognition using saliency learned from recorded human gaze

Stefic

Patras

2016

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…However, linear SVM is weak against outliers, suffering from one outlier degrading whole prediction result. More recently, Shen et al [9] suggested neural network architecture to learn saliency. Jiang et al [5] proposed random forest approach based on superpixel segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…Shen and Zhao [9] used multi-layer sparse network to predict saliency map. In [10], multi-kernel learning was employed to learn webpage saliency.…”

Section: Introductionmentioning

confidence: 99%

Random forest with data ensemble for saliency detection

Nah

Lee

2015

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

View full text Add to dashboard Cite

Saliency detection is one of the most active research area in computer vision. Since L.Itti et al. [1] suggested computational model of visual attention, numerous detection algorithms have been proposed. However, most of modern saliency detection methods are based on superpixels which make detection results have abrupt edges inside the salient part. In this paper, we propose pixel-wise detection algorithm that makes more natural detection result. It makes our algorithm excel in describing detailed part of salient objects. Furthermore, we utilize the ensemble of not only random forest but also the data itself. Our algorithm achieves comparable performance with state of the art detection results.

show abstract

“…This model is useful in avoiding background noise interference, but are still not accurate enough. Meanwhile, with the continuous improvement of the deep learning network and deep convolutional network [8] in the area of computer vision and image processing, a salient model using deep convolution network based on high-level features was proposed [9] which divides the original image into small image blocks. The small image blocks are convoluted and pooled at different levels and iterated to obtain the feature dictionary of the original image.…”

Section: Introductionmentioning

confidence: 99%

Saliency Detection by Multilevel Deep Pyramid Model

et al. 2018

View full text Add to dashboard Cite

Traditional salient object detection models are divided into several classes based on low-level features and contrast between pixels. In this paper, we propose a model based on a multilevel deep pyramid (MLDP), which involves fusing multiple features on different levels. Firstly, the MLDP uses the original image as the input for a VGG16 model to extract high-level features and form an initial saliency map. Next, the MLDP further extracts high-level features to form a saliency map based on a deep pyramid. Then, the MLDP obtains the salient map fused with superpixels by extracting low-level features. After that, the MLDP applies background noise filtering to the saliency map fused with superpixels in order to filter out the interference of background noise and form a saliency map based on the foreground. Lastly, the MLDP combines the saliency map fused with the superpixels with the saliency map based on the foreground, which results in the final saliency map. The MLDP is not limited to low-level features while it fuses multiple features and achieves good results when extracting salient targets. As can be seen in our experiment section, the MLDP is better than the other 7 state-of-the-art models across three different public saliency datasets. Therefore, the MLDP has superiority and wide applicability in extraction of salient targets.

show abstract

Learning to predict eye fixations for semantic contents using multi-layer sparse network

Cited by 44 publications

References 22 publications

Action recognition using saliency learned from recorded human gaze

Action recognition using saliency learned from recorded human gaze

Random forest with data ensemble for saliency detection

Saliency Detection by Multilevel Deep Pyramid Model

Contact Info

Product

Resources

About