Segmenting Salient Objects from Images and Videos

By Esa Rahtu, Juho Kannala, Mikko Salo, Janne Heikkilä. European Conference on Computer Vision, 2010

562 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c413d55baf1ee96df29256a879e96daf4c2cc072

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

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Ming-Ming Cheng
4. Dacheng Tao
5. Ling Shao
6. Xiaogang Wang
7. Huchuan Lu
8. Yi Yang

Citations in the corpus

• Saliency Detection via Dense and Sparse Reconstruction (2013, methodology): “We evaluate the proposed algorithm with seventeen state-of-the-art algorithms including IT98 [13], MZ03 [24], LC06 [25], GB06 [10], SR07 [11], AC08 [1], FT09 [2], CA10 [9], RA10 [18], RC11 [7], CB11 [14], SVO11 [6], DW11 [8], SF12 [17], LR12 [19], GS12 [21] and XL13 [22] on three benchmark data sets”
• Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “427 Metric SMD ULR [26] SLR [28] LRR [27] GS [24] SF [50] CB [19] CA [7] SS [15] SEG [13] FT [49] SR [14] LC [16] WF↑ 0.”
• TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification (2012, methodology): “The second approach applies a saliency map [19] as a cue.”
• Enhancing Video Summarization via Vision-Language Embedding (2017, methodology): “We concatenate these with features computed over a saliency map [31] as in [7].”
• Salient Object Detection: A Benchmark (2015, unknown): “[29] ECCV/2010 - 16 Khuwuthyakorn et al.”
• Saliency-Aware Video Object Segmentation (2018, methodology): “Utilizing both motion and appearance cues seems to be a better choice as it was adopted by many methods [4], [5], [6], [7], [8], [9].”
• 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.”
• Fast Binary Coding for the Scene Classification of High-Resolution Remote Sensing Imagery (2016, background): “…IM [59], low rank matrix recovery (LRR) [60], maximum symmetric surround (MSS) [61], rarity-based saliency (RARE) [62], salient segmentation (SEG) [63], self-resemblance (SeR) [64], spectral residual (SR) [65] and saliency using natural statistics (SUN) [66], and present detailed comparative…”
• Global Contrast Based Salient Region Detection (2015, methodology): “, FT [33], SEG [25], GrabCut [38] (initialized using five pixel wide image boundary), and CB[35] (best parameters are selected for these methods).”
• Contextual Hypergraph Modelling for Salient Object Detection (2013, methodology): “In the experiments, we qualitatively and quantitatively compare the proposed approach with twelve state-of-theart approaches, including GS SP [5], LR [12], SF [11], CB [13], SVO [15], RC [7], HC [7], RA [16], FT [4], CA [14], ICL [3], and IT [1].”
• Context-aware saliency detection (2010, background): “Results are presented for seven different state-of-the-art algorithms [1], [12], [13], [14], [16], [17], [26].”
• Salient object detection: A survey (2014, methodology): “s Elements Hypothesis Aggregation Type Code Uniqueness Prior (Optimization) 11 LC [116] MM 2006 TC PI + PA L - LN online NA 12 VA [117] ICPR 2008 TC mPI + PA + RE L CS + SD + MCO CRF offline NA 13 SEG [108] ECCV 2010 TC PA + PI CS MCO CRF offline M + C 14 RDC [118] CSVT 2013 TC RE L - - offline NA # Mo”
• Diverse Sequential Subset Selection for Supervised Video Summarization (2014, methodology): “We also add features computed from the frame saliency map [35].”
• SalientShape: group saliency in image collections (2013, methodology): “(b) Comparison of Fβ for image groups using single image saliency segmentation methods (FT [1], SEG [45], RC [15]) vs.”
• Fusing generic objectness and visual saliency for salient object detection (2011, methodology): “Experimental results on two benchmark datasets demonstrate that the proposed model can simultaneously yield a saliency map of better quality and a more meaningful objectness output for salient object detection.”
• Detecting Engagement in Egocentric Video (2016, methodology): “Finally, despite their popularity in video summarization, Saliency Map methods [1], [6], [7], [17], [19], [20] do not predict temporal ego-engagement well.”
• A Comparative Study of Sampling Analysis in the Scene Classification of Optical High-Spatial Resolution Remote Sensing Imagery (2015, methodology): “Define a random variable Z describing the distribution of pixels in W ; the saliency measure of a point x ∈ I is thus defined to be the conditional probability, SSEG(x) = pZ(Z ∈ I |F (Z) ∈ QF (x)) where F denotes the Lab color feature map, which maps every point x to a certain feature F (x), and QF ”
• Efficient Salient Region Detection with Soft Image Abstraction (2013, methodology): “(a) original (b) IM[39] (c) SeR[45] (d) SUN[52] (e) SEG[43] (f) AIM[8] (g) SWD[20] (h) RC[16] (i) CA[25] (j) MZ[37]”
• Cluster-based Co-saliency Detection (2013, unknown): “The saliency of video also conforms to the feature contrast property [7], [30], [56].”