Saliency Detection via Absorbing Markov Chain

By Bowen Jiang, Lihe Zhang, Huchuan Lu, Chuan Yang, Ming-Hsuan Yang. IEEE International Conference on Computer Vision, 2013

598 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/7d277c97cf9d0c8a0ed671b3fb9b1e7c8e647cfc

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

In Sensory Systems

Citations in the corpus

Distilling Localization for Self-Supervised Representation Learning (2020, methodology): “All of them are found to improve performance, even the noisy traditional approaches RBD [54], MC [23] and GS [43].”
Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring (2019, unknown): “Model [8] [30] [15] [7] [31] OURS Fβ .”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, methodology): “• DUS [87] jointly learns latent saliency and noise patterns from noisy saliency maps generated by several traditional un-supervised SOD methods [34], [35], [108], [109], and produces ﬁner saliency maps for next training iteration.”
Detect Globally, Refine Locally: A Novel Approach to Saliency Detection (2018, background): “Early research [23, 12, 31, 32, 11, 19, 14, 4, 25] focuses on low-level visual features, such as center bias, contrast prior and background prior.”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, background): “In [16, 15, 53, 23, 27, 38], saliency is measured by label propagation where initial labeling is propagated from the labeled elements to the unlabeled ones based on their pairwise affinities.”
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, methodology): “which normalizes the flow by applying a saliency detection method [21] to the flow image itself.”
Deep networks for saliency detection via local estimation and global search (2015, unknown): “Saliency cues such as center and object bias [31, 22], contrast information [38] and background prior [33, 15] have been shown to be effective in previous work.”
Surface defect saliency of magnetic tile (2018, background): “At the same time, we also investigate RBD [56], FES [57], MC [58], GC [16], GU [16] and DRFI [59].”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “To highlight the whole salient object, multiscale contrast [18], [19] and multicues integration [20] techniques were used.”
Saliency detection via Cellular Automata (2015, unknown): “Many effective methods have been established to deal with saliency detection and each of them has their own superiorities [7, 17, 23, 33, 52].”
Salient Object Detection: A Benchmark (2015, unknown): “149 16 DRFI [79] CVPR 2013 C .697 17 PCA [80] CVPR 2013 M + C 4.34 18 LBI [81] CVPR 2013 M + C 251. 19 GC [82] ICCV 2013 C .037 20 CHM [83] ICCV 2013 M + C 15.4 21 DSR [84] ICCV 2013 M + C 10.2 22 MC [85] ICCV 2013 M + C .195 23 UFO [86] ICCV 2013 M + C 20.3 24 MNP [52] Vis.Comp. 2013 M + C 21.0 25 ”
Salient object detection via bootstrap learning (2015, methodology): “Salient object detection methods can be categorized as bottom-up stimulidriven [1, 8–12, 15–18, 20, 23, 28–38, 41, 43] and top-down task-driven [19, 40, 42] approaches.”
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.”
Minimum Barrier Salient Object Detection at 80 FPS (2015, methodology): “Figure 1: Sample saliency maps of several state-of-the-art methods (SO [39], AMC [15], HS [34] and SIA [6]) and methods with fast speed (HC [5], FT [1] and ours).”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “e the space, we only consider the top four models ranked in the survey [23]: SVO [51], CA [17], CB [32], and RC [15] and recently-developed methods: SF [21], LRK [78], HS [33], GMR [48], PCA [31], MC [50], DSR [49], RBD [55] that are not covered in [23]. Note that we compare our approach with the ex”
Saliency detection by multi-context deep learning (2015, background): “A large number of approaches [63, 52, 40, 39, 32, 35, 60, 57, 56, 47, 41, 31, 27, 25, 24, 23, 11, 44, 17, 8, 13, 1, 21] are proposed to capture different saliency cues.”
Learn To Pay Attention (2018, methodology): “The trained attention maps outperform other CNN-derived attention maps (Zhou et al., 2016), traditional saliency maps ( Jiang et al. (2013); Zhang & Sclaroff (2013)), and top object proposals on the task of weakly supervised segmentation of the Object Discovery dataset ( Rubinstein et al. (2013)).”
Salient object detection: A survey (2014, background): “[85] propose to formulate the saliency detection via absorbing Markov Chain where the transient and absorbing nodes are superpixels around the image center and border, respectively.”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “performing alternatives: saliency via deep feature (MD) [33], saliency via absorbing markov chain (MC) [67], space-time saliency for time-mapping (TIMP) [19], gradient-flow filed based saliency (GAFL) [3], geodesic distance based video saliency (SAGE) [17], and saliency via random walk with restart ”