Frequency-tuned salient region detection

By Radhakrishna Achanta, Sheila S. Hemami, Francisco J. Estrada, Sabine Süsstrunk. 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009

4,513 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/2f52d46714a3fccbe9ea293763b03550ada7bd7d

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

In Sensory Systems

Citations in the corpus

Shifting More Attention to Video Salient Object Detection (2019, methodology): “To quantitatively assess the model performance, we adopt 2 popular evaluation metrics: Mean Absolute Error ( MAE ) M [58], F-measure F [1], and the recent released structure measure S-measure S [18].”
Deep Level Sets for Salient Object Detection (2017, methodology): “Qualitative comparison with FT [1], HC [10], GMR [56], BSCA [47], MTDS [31], MDF [29], MCDL [62], ELD [26], LEGS [50].”
Global contrast based salient region detection (2011, methodology): “We have extensively evaluated our methods on publicly available benchmark data sets, and compared our methods with (eight) state-of-the-art saliency methods [17, 21, 32, 14, 15, 1, 2, 12] as well as with manually produced ground truth annotations1.”
Non-local Deep Features for Salient Object Detection (2017, background): “Prior efforts have tested simple features such as color and grayscale [2], edges [13] or texture [10], as well as more complex features such as objectness, focusness and backgroundness [18, 46, 9].”
Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “The frequency tuning method [49] detects saliency by computing color deviation from the mean image color at the pixel level.”
Surface defect saliency of magnetic tile (2018, methodology): “The 14models in the toolbox are: ITTI [30] and BMS [14] based on visual-attention mechanism; FT [28], LC [46] and HC [47] based on global color rarity; AC [34] and MSS [29] based on local color rarity; SR [48], Rudinac [49] and PHOT [36] based on frequency domain; RC [47], SF [50] and GMR [26] based”
Kubric: A scalable dataset generator (2022, neutral): “22 spawn_region=[[-1, -1, 0], [1, 1, 1]]) 23 # --- execute the simulation, render, and save data to files 24 simulator.”
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain (2013, background): “Other papers tend to find large salient regions [18], [23], [24], [25], [35], [26].”
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection (2022, methodology): “For COD and SOD, we use seven common metrics for evaluation based on [32,33], including S-measure [6] (S m ), weighted F-measure [30] (F ωβ ), mean absolute error (MAE), F-measure [1] (F β ), E-measure [7] (E m ), precision-recall (PR) curve and F β -threshold curve (F β curve).”
Saliency Detection: A Boolean Map Approach (2013, methodology): “Similar to previous works [1, 36], we binarize the saliency maps at a fixed threshold and compute the average precision and recall (PR) for each method.”
Visual Saliency Detection Based on Multiscale Deep CNN Features (2016, methodology): “This is also reflected in the lower F-measure and higher MAE achieved with MC. Performance improvement becomes more obvious on HKU-IS.”
A Co-Saliency Model of Image Pairs (2011, methodology): “Difference in selected regions can be observed from the results produced by thesemodels.Forexample,thegraycoatisidentifiedasasalient object by [ 32 ], but it fails to be detected by the method [33].”
RGBD Salient Object Detection: A Benchmark and Algorithms (2014, methodology): “The F -measure is computed with an adaptive saliency threshold that is defined as twice the mean saliency of the image [2].”
DenseCut: Densely Connected CRFs for Realtime GrabCut (2015, methodology): “For MSRA 1K dataset [AHES09] benchmark, we export the bounding box annotation from its binary mask ground truth, and use this bounding box as input to each method.”
Predicting the Driver's Focus of Attention: The DR(eye)VE Project (2017, background): “In this context, computational models focus on spotting visual discontinuities, either by clustering features or considering the rarity of image regions, locally [39], [57] or globally [1], [14], [77].”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, background): “Salient object detection [1, 5, 10, 11, 17] aims to detect and segment the most attractive objects in images or videos.”
Recurrent Attentional Networks for Saliency Detection (2016, methodology): “Bottom-up methods [21, 17, 19, 1, 32, 9, 34] make use of level local visual cues like color, contrast, orientation and texture.”
Deep Visual Attention Prediction (2017, background): “In recent decades, there is a new wave in saliency detection [31], [32] that concentrated on uniformly highlighting the most salient object regions in an image, starting with the works of Liu et al. [33] and Achanta et al. [34].”
Multi-Scale Interactive Network for Salient Object Detection (2020, methodology): “F-measure [1], F β is formulated as the weighted harmonic mean of Precision and Recall [1], e.t.”
Leveraging stereopsis for saliency analysis (2012, methodology): “(d) Saliency [11] (e) Saliency [14] (f) Saliency [1]”