Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform

By Chenlei Guo, Qi Ma, Liming Zhang. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

856 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Cognitive Neuroscience, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/16f4cfd4cbf504a151827b5a94df5deafd4930ac

How researchers see this paper

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

In Aerospace Engineering

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Segmenting Salient Objects from Images and Videos (2010, methodology): “Other methods apply Fourier transform [23, 24], mutual information formulation [25], or band-pass filtering [26].”
Salient Region Detection by UFO: Uniqueness, Focusness and Objectness (2013, methodology): “Also some methods turn to the frequency domain to search for saliency cues [10, 13, 21].”
Reweighted Infrared Patch-Tensor Model With Both Nonlocal and Local Priors for Single-Frame Small Target Detection (2017, methodology): “3 Phase spectrum of Fourier Transform [50] PFT Disk radius: 3”
An Assisted Photography Framework to Help Visually Impaired Users Properly Aim a Camera (2014, methodology): “Different situations call for different solutions, and so we chose to test several methods with a variety of street photographs [Walther and Koch 2006; Hou and Zhang 2007; Guo et al. 2008; Bian and Zhang 2008; Achanta et al. 2009].”
State-of-the-Art in Visual Attention Modeling (2013, background): “[156] showed that incorporating the phase spectrum of the Fourier transform instead of the amplitude transform leads to better saliency predictions.”
Gaze Prediction in Dynamic 360° Immersive Videos (2018, background): “Some work also attempts to use low-level appearance and motion cues as inputs or extend deep learning approaches to more complex scenarios such as stereo images [9] or videos [4] [7] [11] [31] [35] [32] [16] [12] [6] [18].”
Recurrent Mixture Density Network for Spatiotemporal Visual Attention (2016, methodology): “In this context, motion features are introduced when extending saliency methods from images to videos (Guo et al., 2008; Zhao et al., 2015; Zhai & Shah, 2006).”
Shifting More Attention to Video Salient Object Detection (2019, background): “Early VSOD models [8, 26, 28, 35, 52, 53, 62, 63, 74, 75] are built upon hand-crafted features (color, motion, etc .)”
Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics (2013, methodology): “SR [9], PFT [8], PQFT [8] and Achanta [1] use a spectral analysis approach to compute their saliency map.”
A Novel Multiresolution Spatiotemporal Saliency Detection Model and Its Applications in Image and Video Compression (2010, background): “Our work in [15] manifested the fact that the saliency map of an image can be calculated when the amplitude spectrum of the image is at a nonzero constant value.”
Saliency-aware geodesic video object segmentation (2015, background): “Even though it is not the final goal of our proposed algorithm, we still evaluate the effectiveness of our approach by comparing our spatiotemporal saliency results against the stateof-art saliency methods [31, 13, 28, 14] on the SegTrack dataset [29].”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “Early models [52]–[54] can be viewed as simple extensions of exiting static saliency models with extra temporal dimension.”
Two-Stage Learning to Predict Human Eye Fixations via SDAEs (2016, background): “[23] incorporated the phase spectrum of the Fourier transform rather than the amplitude transform, which achieves better performance.”
Saliency-Aware Video Object Segmentation (2018, methodology): “Our saliency method is one of the fastest solutions and only slower than the frequency domain based method [38].”
Region-Based Saliency Detection and Its Application in Object Recognition (2014, background): “[34] pointed out that it is not the amplitude spectrum but the phase spectrum that contributes to saliency detection.”
Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, methodology): “Similarly, in QS [16], motion features are also considered into their Quaternion Fourier Transform process for obtaining spatiotemporal saliency maps.”
Static and space-time visual saliency detection by self-resemblance. (2009, background): “However, Guo, Ma, and Zhang (2008) claimed that what plays an important role for saliency detection is not spectral residual, but the image’s phase spectrum.”
A system for retargeting of streaming video (2009, background): “To copy otherwise, to republish, to post on servers, to redistribute to lists, or to use any component of this work in other works requires prior specifi c permission and/or a fee.”
Time-Series Anomaly Detection Service at Microsoft (2019, background): “s vision is more sensitive to the innovation part. Meanwhile, the log amplitude spectrum of an image subtracting the average log amplitude spectrum captures the saliency part of the image. Guo et al. [8] argued that only phase spectrum was enough to detect the saliency part of an image and simplifie”
Saliency Detection via Absorbing Markov Chain (2013, neutral): “Fourier spectrum analysis has also been used to detect visual saliency [15, 13].”