Automatic foveation for video compression using a neurobiological model of visual attention

By Laurent Itti. IEEE Transactions on Image Processing, 2004

826 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bbb456acfec69d279b3f653b53dc1182d1b44eb6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Saliency and Gist Features for Target Detection in Satellite Images (2011, background): “Early on, the human visual processing system already makes decisionstofocusattention and processingresources onto those small regions within the ﬁeld of view which look more interesting or visually “salient” [25]–[27].”
What Do Different Evaluation Metrics Tell Us About Saliency Models? (2016, background): “Applications including adaptive image and video compression and progressive transmission [30], [35],”
Exploiting local and global patch rarities for saliency detection (2012, methodology): “For example in computer vision, it has been used for image and video compression [49], image segmentation, and object Figure 1.”
Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study (2013, background): “, object recognition [1]–[3], object detection [4], [5], target tracking [6], image compression [7], and video summarization [8]); computer graphics (e.”
Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, methodology): “Previous dynamic eye-tracking datasets [31, 52, 21, 75] were constructed under free-viewing or other task-driven settings (see Table 1).”
Depth saliency based on anisotropic center-surround difference (2014, background): “object segmentation [2], image classification [3, 4], image/video retargeting [5, 6], compression [7] and quality assessment [8].”
On the plausibility of the discriminant center-surround hypothesis for visual saliency. (2008, methodology): “In what is perhaps the most popular model for bottom-up saliency, Itti et al. (1998) measures contrast as the difference between the stimulus at a location and the stimulus in its neighborhood in a center-”
Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “Other datasets are either limited in terms of variety and scale of video stimuli [34], [36], or collected for special purposes (e.g., salient objects in videos [39], [40]).”
What Makes a Patch Distinct? (2013, background): “The detection of the most salient region of an image has numerous applications, including object detection and recognition [13], image compression [10], video summarization [16], and photo collage [8], to name a few.”
Deeply Supervised Salient Object Detection with Short Connections (2016, background): “sually distinctive objects or regions in an image. Salient object detection methods commonly serve as the ﬁrst step for a variety of computer vision applications including image and video compression [14,18], image segmentation [9], content-aware image editing [8], object recognition [40], visual tr”
A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression (2010, methodology): “3) Evaluate the Quality of the Attention-Based Compressed Image/Video: L. Itti pointed out that the quality of the attention-based compressed image/video should be evaluated by how well the results of the saliency model match the human ﬁx-ation data [25].”
Saliency Detection via Graph-Based Manifold Ranking (2013, methodology): “It has been applied to numerous vision problems including image segmentation [11], object recognition [28], image compression [16], content based image retrieval [8], to name a few.”
Modeling the influence of task on attention. (2005, result): “As part of our future work, we are planning to further confirm the above by comparing our modelÕs performance against human eye tracking data (Itti, 2004).”
Attentive Systems: A Survey (2017, methodology): “Itti (2004) use saliency maps for MPEG-1 and MPEG-4 video compression. Video summarization is considered as an application in multimedia compression. Ma et al. (2005) propose a feasible solution for video summarization, including key-frame selection and video skim extraction, based on user attention”
Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency (2019, methodology): “The heuristic saliency models [20], [21], [22], [23], [24] generally use hand-crafted features and design heuristic rules to perform visual saliency estimation in a bottom-up or topdown manner.”