A visual attention model for adapting images on small displays

By Li-Qun Chen, Xing Xie, X. Fan, Wei-Ying Ma, HongJiang Zhang, He-Qin Zhou. Multimedia Systems, 2003

478 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/929958ab2b7c86095c9c6aadd4848f44ebba0500

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

Unsupervised extraction of visual attention objects in color images (2006, background): “Lately, some confirmed conclusions on visual attention have been applied to a few multimedia applications, including handwritten digit recognition and face recognition [6], video summary [7], as well as image adaptation [8].”
Gaze-based interaction for semi-automatic photo cropping (2006, methodology): “[5], who have developed fully automated saliencebased image-cropping techniques requiring no user input.”
Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “An image attention model for adapting images based on user attention for small displays has been proposed in [Chen et al. 2003].”
Contrast-based image attention analysis by using fuzzy growing (2003, background): “Also, due to a variety of display screens used by users, especially those small display screens in PDA (Personal Digital Assistant), mobile phone and the size alterable webpage browsers, an adaptive image display scheme is needed [2].”
Predicting Human Eye Fixations via an LSTM-Based Saliency Attentive Model (2016, background): “…research effort has aimed to emulate such selective visual mechanisms, as computational saliency can be applied to a wide range of applications like image retargeting [2], [3], object recognition [4], video compression [5], tracking [6] and other data-dependent tasks such as image captioning [7].”
A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities (2022, methodology): “This heuristic algorithm is far superior to simple attentional models[55].”
An Assisted Photography Framework to Help Visually Impaired Users Properly Aim a Camera (2014, background): “Regions that are visually salient tend to be considered as information carriers that deliver the photographer’s intention and capture part of the observers’ attention as a whole [Chen et al. 2002].”
Summarizing visual data using bidirectional similarity (2008, methodology): “(ii) Importance-based cropping methods [3, 11, 15] provide nice results when the interesting information is concentrated in one region (spatial or temporal).”
We get the algorithms of our ground truths: Designing referential databases in digital image processing (2017, background): “, 2006), adaptive display on small devices (Chen et al., 2003), advertising design and image compression (Itti, 2000), the absence of any ground truth that could allow the training and evaluation of computational models prevented saliency detection from being an active topic in digital image process”
Salient Region Detection and Segmentation (2008, methodology): “The saliency maps produced by Itti’s approach have been used by other researchers for applications like adapting images on small devices [3] and unsupervised object segmentation [5, 10].”
Learning to Detect A Salient Object (2007, background): “There are many applications for visual attention, for example, automatic image cropping [23], adaptive image display on small devices [4], image/video compression, advertising design [7], and image collection browsing.”
DeepFix: A Fully Convolutional Neural Network for Predicting Human Eye Fixations (2015, methodology): “This modeling has applications in vision-related tasks such as video compression [8], object and action recognition [9], [10], image retargetting [11] and surveillance systems [12].”
Automatic thumbnail cropping and its effectiveness (2003, methodology): “[5] use a visual attention model as a cue to conduct image adaptation for small displays.”