Saliency Optimization from Robust Background Detection

By Wangjiang Zhu, Shuang Liang, Yichen Wei. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014

1,313 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/93914c3079f4fc8dd63602cefe5a1ec3fa495954

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

Recurrent Attentional Networks for Saliency Detection (2016, methodology): “DRFI, RBD, DSR, MC, and HS are the top-performing methods evaluated in [4], while RRWR and BSCA are two very recent saliency detection works.”
Saliency Detection via a Multiple Self-Weighted Graph-Based Manifold Ranking (2020, background): “3) RBD [61], an algorithm that proposes boundary connectivity and integrates multiple low-level cues to obtain the saliency maps.”
Few-Shot Learning via Saliency-Guided Hallucination of Samples (2019, methodology): “As our dataset contains both Image RFCN [37] MNL [46] RBD [47] Figure 3: Saliency maps generated by different methods.”
Deep Level Sets for Salient Object Detection (2017, background): “Another useful assumption called center bias prior assumes that salient objects tend to be located at the center of images [54, 64, 59, 56, 53].”
Learning to Detect Salient Objects with Image-Level Supervision (2017, methodology): “We compare WSS with 16 existing methods, including 7 unsupervised ones: FT [1], DSR [28], HS [53], MR [53], wCtr [59], MBS [56], BSCA [40]; and 9 fully supervised ones: DRFI [17], HDCT [19], LEGS [46], MC [57], MDF [26], DS [29], SELD [25], DCL [27], RFCN [49].”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, neutral): “, [14, 9, 40, 24, 57, 28, 7].”
Deep Contrast Learning for Salient Object Detection (2016, background): “Salient object detection can be performed either in a bottom-up fashion using low-level features [14, 1, 30, 23, 39, 49, 21, 51, 8] or in a top-down fashion via the incorporation of high-level knowledge [22, 5, 17, 41, 29, 19, 28].”
Salient Object Subitizing (2015, methodology): “We use the state-of-the-art salient detection method of [58], and binarize its saliency maps using Otsu’s method [39].”
Infrared and Visible Image Fusion via Decoupling Network (2022, methodology): “Similarly, Zhu et al. [37] devised a boundary-connected method that describes the spatial layout of image regions relative to image boundaries, integrating multiple low-level cues of the input image (e.g., contrast) and, thus, obtaining its saliency map.”
Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “(E ) EC SS D Metric SMD DRFI [57] RBD [63] HCT [17] DSR [62] MC [83] MR [61] HS [21] PCA [22] TD [20] GC [23] RC [12] SVO [18] WF↑ 0.”
EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “Early methods predicted the saliency map using a bottom-up pattern by the hand-craft feature, such as contrast [5], boundary background [57, 68], center prior [24, 44] and so on [22, 44, 51].”
Surface defect saliency of magnetic tile (2018, methodology): “GMR [28], MBP [29], MC [30], RBD [31] and DRFI [32] are top models of non-deeplearning models in natural scene datasets [27] , so they are used to compare to our MCue model.”
Co-Saliency Detection via a Self-Paced Multiple-Instance Learning Framework (2017, methodology): “5.3 Comparison with State-of-the-Art Methods In this section, we compared the proposed co-saliency detection approach with 9 state-of-the-art methods, including CSHS [7], SACS [8], CBCS [6], CBCS-S 1 [6], ESMG [9], ESMG- S 1 [9], EQCUT [44], HDCT [60], and RBD [61].”
DevNet: A Deep Event Network for multimedia event detection and evidence recounting (2015, methodology): “Then the evaluators were presented the temporal key evidences (key frames) generated by [35] and DevNet with fixed recounting percentage (5%) and the spatial key evidences generated by [48] and DevNet.”
A Bi-Directional Message Passing Model for Salient Object Detection (2018, background): “A majority of them utilize heuristic saliency priors, such as color contrast [4, 1], boundary background [33, 41] and center prior [10].”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “Meanwhile, some other mechanisms [28], [31], [32] have been proposed to adopt some prior knowledge, such as background prior, or global information, to detect salient objects in still images.”
Nested Network With Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images (2019, methodology): “We compare the proposed method with 14 state-of-the-art salient object detection methods on the testing subset of ORSSD data set, including 7 unsupervised methods (DSR [20], RBD [18], RRWR [48], HDCT [49], DSG [50], MILPS [51], and RCRR [15]), 4 deep learning-based methods (DSS [24], RADF [25], R3Ne”
Visual Concept Recognition and Localization via Iterative Introspection (2016, methodology): “To further verify that our introspection mechanism highlights regions whose exploration is worthwhile, we evaluated an alternative to the introspection stage by using a generic saliency measure [30].”