Hierarchical Saliency Detection

By Qiong Yan, Li Xu, Jianping Shi, Jiaya Jia. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

1,775 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6ce9251c7e72e93928a6bae17a6f2b4c85a8a706

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

Citations in the corpus

• Instance-Level Salient Object Segmentation (2017, methodology): “ient Region Detection To evaluate the performance of our MSRNet on salient region detection, we conduct testing on six benchmark datasets: MSRA-B [34], PASCAL-S [31], DUTOMRON[49], HKU-IS [29], ECSSD [48] and SOD [37]. As we train our network on the combined training sets of MSRA-B and HKU-IS, we ev”
• Object Detection With Deep Learning: A Review (2018, neutral): “Four representative data sets, including Evaluation on Complex Scene Saliency Dataset (ECSSD) [156], HKU-IS [146], PASCALS [157], and SOD [158], are used to evaluate several state-of-the-art methods.”
• Learning Uncertain Convolutional Features for Accurate Saliency Detection (2017, methodology): “Following existing works [48] [44] [3] [49], we set β(2) to be 0.”
• Visual saliency based on multiscale deep features (2015, methodology): “HS[37] and wCtr*[40], is comparable to ours while their recalls are often much lower.”
• A Survey on Deep Learning Technique for Video Segmentation (2021, methodology): “PASCAL VOC 2012 [103] + COCO [123] + ECSSD [118] + DAVIS17 [81]/YouTubeVOS [95] Fasttan [155] CVPR Faster RCNN Propagation-based COCO [123] + DAVIS17 [81]”
• Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, background): “ECSSD [61] contains 1, 000 semantically meaningful and complex images with pixel-accurate ground truth annotations.”
• Surface defect saliency of magnetic tile (2018, methodology): “They benchmark these models with respect to their algorithm performance using six datasets—MSRA10K [23], ECSSD [24], THUR15K [23], JuddDB [25], DUT-OMRON [26] and SED2 [27].”
• Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining (2016, neutral): “Similar to what we did in the Image Pair data set, we also compared the proposed saliency prior transfer method with the intrasaliency detection method CBCS-S [14], and another three state-of-the-art single image saliency detection algorithms HS [32], LR [33], and DRFT [46] in the iCoseg data set.”
• Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection (2020, methodology): “Meanwhile, others datasets, like SOD [25], PASCAL-S [19], ECSSD [40], HKU-IS [17] and DUT-O [41], are only employed as test sets due to their relatively small scales, which contain 300, 850, 1000, 4447 and 5168 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 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.”
• A Bi-Directional Message Passing Model for Salient Object Detection (2018, methodology): “The ECSSD dataset [32] has 1000 images with various complex scenes.”
• Progressive Attention Guided Recurrent Network for Salient Object Detection (2018, methodology): “Comparing F-measure scores, our PAGRN outperforms the second best method by 2.3%, 3.9%, 4.9%, 3.9%, 4.0%, 8.8% over ECSSD, HKU-IS, THUR15K, PASCAL-S, DUT-OMRON, DUTS respectively.”
• EGNet: Edge Guidance Network for Salient Object Detection (2019, methodology): “S-measure could be computed as: ECSSD [56] PASCAL-S [30] DUT-O [57] HKU-IS [27] SOD [36,37] DUTS-TE [46] Table 3.”
• A Simple Pooling-Based Design for Real-Time Salient Object Detection (2019, methodology): “To evaluate the performance of our proposed framework, we conduct experiments on 6 commonly used datasets, including ECSSD [41], PASCALS [21], DUT-OMRON [42], HKU-IS [18], SOD [30] and DUTS [35].”
• Rolling Guidance Filter (2014, background): “Separation of structures with respect to their scales is an important process that has been discussed in many areas, such as segmentation [3], object detection [10], and saliency detection [31].”
• Saliency Optimization from Robust Background Detection (2014, positive): “This is much more efficient than previous CRF/MRF based optimization methods [25, 15, 28].”
• PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (2017, background): “ECSSD [42] has 1,000 semantically meaningful and complex images.”