Saliency Detection via Graph-Based Manifold Ranking

By Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2,484 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/699d4d8c8b91b1a34dd6f47d28e3fe1236f25944

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. Ling Shao
5. Dacheng Tao
6. Huchuan Lu
7. Xiaogang Wang
8. Yi Yang

In Sensory Systems

1. Huchuan Lu
2. Jianbing Shen
3. Wenguan Wang
4. Ming-Ming Cheng
5. Junwei Han
6. Deng-Ping Fan
7. Ling Shao
8. Ali Borji

Citations in the corpus

• RGBD Salient Object Detection: A Benchmark and Algorithms (2014, methodology): “We select 12 state-of-the-art RGB saliency detection approaches, including the top 4 models ranked in the survey[6]: SVO[9], CA[14], CB[20], and RC[10], and 8 recently developed prominent methods: SF[34], LR[40], HS[44], MR[45], PCA[32], TD[37], GC[11], and DSR[28].”
• Intriguing Properties of Vision Transformers (2021, background): “The receptive field of Transformer based models covers the entire input space, a property that resembles handcrafted features [25], but ViTs have higher representative capacity.”
• Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks (2019, methodology): “Implementation Details: Following [44, 55], both static data from image salient object segmentation datasets, MSRA10K [8], DUT [72], and video data from the training set of DAVIS16 are iteratively used to train our model.”
• Instance-Level Salient Object Segmentation (2017, methodology): “ected 1;388 images. To reduce the ambiguity in salient region detection results, these images were mostly selected from existing datasets for salient region detection, including ECSSD [48], DUT-OMRON [49], HKU-IS [29], and MSO datasets [51]. Two-thirds of the chosen images contain multiple occluded ”
• CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “The third class of methods proposed background priors [19], [22] to direct the saliency detection, which are based on the idea of modeling the property of background first and thereby separating salient objects from the background.”
• RGB-T Object Tracking: Benchmark and Baseline (2018, methodology): “ we simplify the setting as = . Following [63], we set f; ;;!g= f0:1;0:1;11;1g. On the other hand, and control the balance of smoothness and fitness of s. According to the setting of similar models [64, 65], we set f;g= f10;0:15g. In the structured SVM, we empirically set f;g= f0:67;0:35g[11]. All pa”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, neutral): “First, we respectively adopt a superpixel-based clustering algo-rithm [45] and a graph-based manifold ranking method [47] to segment the enhanced results using different methods and detect corresponding saliency.”
• Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking (2016, methodology): “With these definitions, the optimal ranking is derived by solving the following optimization problem [45], [46]:”
• Saliency Optimization from Robust Background Detection (2014, neutral): “In [29], saliency estimation is formulated as a ranking and retrieval problem and the boundary patches are used as background queries.”
• Minimum Barrier Salient Object Detection at 80 FPS (2015, methodology): “The Image Boundary Connectivity Cue, which assumes that background regions are usually connected to the image borders, is shown to be effective for salient object detection [39, 33, 36, 35].”
• Salient Object Detection: A Benchmark (2015, background): “2), and we can thus study the effect of center bias in model comparison.”
• Saliency Detection on Light Field (2017, neutral): “Yang et al. [27] observed that connectivity is an important characteristics of background and used a graph-based ranking scheme to measure patch similarities.”
• Reverse Attention for Salient Object Detection (2018, methodology): “We comprehensively evaluated our method on six representative datasets, including MSRA-B [36], HKU-IS [37], ECSSD [38], PASCAL-S [39], SOD [40], and DUT-OMRON [41], which contain 5000, 4447, 1000, 850, 300, 5168 well annotated images, respectively.”
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, methodology): “Dataset: For salient object detection, we train our model using the augmented DUTS training dataset [44], and testing on six other testing dataset, including the DUTS testing dataset, ECSSD [49], DUT [50], HKU-IS [27], THUR [4] and SOC testing dataset [8].”
• Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, neutral): “These datasets include DUT-OMRON [44], ECSSD [43], Judd-A [5], and PASCAL-S [26].”
• Global Context-Aware Progressive Aggregation Network for Salient Object Detection (2020, background): “Images of this dataset have one or more salient objects and relatively cluttered background, and thus salient object detection on this dataset is very challenging; • SOD (Movahedi and Elder 2010) is composed of 300 images, many of which contain multiple objects either with low contrast or touching t”