Salient Region Detection by UFO: Uniqueness, Focusness and Objectness

By Peng Jiang, Haibin Ling, Jingyi Yu, Jingliang Peng. IEEE International Conference on Computer Vision, 2013

327 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/20bdfc476336b3bda3c2b8f35a092a05a59eab03

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. Huchuan Lu
3. Ming-Hsuan Yang
4. Luc Van Gool
5. G. Wang
6. Ling Shao
7. Junwei Han
8. Dacheng Tao

In Sensory Systems

1. Huchuan Lu
2. Junwei Han
3. Nian Liu
4. Guanbin Li
5. G. Wang
6. Yizhou Yu
7. Ming-Ming Cheng
8. Ali Borji

Citations in the corpus

• Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “ts can be expected. For example, background connectivity prior [55] can be incorporated to relax the pseudo-background assumption. Additionally, spatial distribution prior [19], [21], focusness prior [52], diverse density score [53] based on generic objectness, and graph-based manifold ranking score”
• Saliency detection via Cellular Automata (2015, background): “FT[1] IT[16] CA[13] RC[8] XL[47] LR [36] HS[48] UFO [20] BSCA MCA ASD 0.”
• Deep Contrast Learning for Salient Object Detection (2016, methodology): “We compare our saliency models (DCL and DCL+) against eight recent state-of-the-art methods, including SF [38], GC [7], DRFI [20], PISA [42], BSCA [39], LEGS [43], MC [49] and MDF [25].”
• Salient Object Detection: A Benchmark (2015, unknown): “ 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 GR [87] SPL 2013 M + C 1.35 26 RB”
• SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection (2015, background): “Although learning techniques are adapted to detect salient objects (Liu et al. 2011; Jiang et al. 2013), they focus on learning the fusion scheme, i.e., saliency integration by combining saliency maps obtained from different types of features.”
• Distilling Localization for Self-Supervised Representation Learning (2020, background): “Useful priors include background priors [20], color contrast priors [5], and objectness [24].”
• Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “Besides, the objectness prior, which estimates the likelihood of a region being a complete object [2], has been employed in some other saliency models [18], [64], [65].”
• Learning Uncertain Convolutional Features for Accurate Saliency Detection (2017, methodology): “Pixel-wise annotation of salient objects was generated by [18].”
• Salient object detection: A survey (2014, background): “[89] calculate the focusness from the degree of focal blur.”
• New Contour Cue-Based Hybrid Sparse Learning for Salient Object Detection (2019, background): “Besides the above models, the boundary/center/focusness priors from photography habits [14], [32], the uniqueness/objectness properties from scene layout [33], [34], and the shape/convexity attributes of salient objects [35], [36] are also widely studied in the literatures.”
• UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, methodology): “his task, e.g. in [58], we will explore the performance of our method on those datasets in the future. We only use flipping for dataset augmentation during training. We compare to some classic methods [18,45,80] as well as more recent ones [58,83,102,112] that typically rely on deep learning. We note”
• Deep networks for saliency detection via local estimation and global search (2015, methodology): “We compare the proposed method (LEGS) with ten state-of-the-art models including SVO [4], PCA[26], DRFI [16], GC [6], HS [40], MR [41], UFO [17], wCtr [42], CPMC-GBVS [23] and HDCT [18].”
• Deep Image Deblurring: A Survey (2022, methodology): “EBMD Jiang et al. (2020) Averaging DAE An event-based motion deblurring network, introducing a new dataset, DAVIS240C.”
• Non-local Deep Features for Salient Object Detection (2017, background): “Prior efforts have tested simple features such as color and grayscale [2], edges [13] or texture [10], as well as more complex features such as objectness, focusness and backgroundness [18, 46, 9].”
• Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, background): “[69] integrated the objectness prior with focusness and objectness to keep completeness of detected salient regions for SOD.”
• RGBD Salient Object Detection: A Benchmark and Algorithms (2014, methodology): “The prior from general object detector [4] is also considered in recent works [9][22][18].”
• Saliency Detection on Light Field (2017, unknown): “First, our focusness cue is extracted directly from a complete focal stack produced by the 4D light field whereas the cue has to be inferred from a single image in [13].”