Leveraging stereopsis for saliency analysis

By Yuzhen Niu, Yujie Geng, Xue-qing Li, Feng Liu. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

583 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b718058b2a758a69147bc32ae54571057ec6694f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Salient Region Detection by UFO: Uniqueness, Focusness and Objectness (2013, methodology): “, the color contrast feature, has been effectively used for saliency detection in previous works [7, 27, 29].”
Saliency Detection on Light Field (2017, unknown): “Niu et al. [29] computed saliency based on the global disparity contrast in a pair of stereo images.”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, background): “The pioneering work for RGB-D SOD was produced by Niu et al. [43], who introduced disparity contrast and domain knowledge into stereoscopic photography to measure stereo saliency.”
Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “Considering the ways of using depth information, we divide the RGBD saliency detection model into depth feature based method [55]–[62] and depth measure based method [63]–[70].”
Salient object detection: A survey (2014, background): “18 LS [128] CVPR 2012 DP RE G DK NL stereo images NA”
RGBD Salient Object Detection: A Benchmark and Algorithms (2014, background): “[33] exploit binocular images to estimate a disparity map and only use depth data to identify salient objects.”
Depth Enhanced Saliency Detection Method (2014, methodology): “(a) Left image (b) Right image (c) Disparity map (d) Ground truth (e) STEREO result (f) DES result Figure 5: Comparison between DES and STEREO [9].”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “ection 13 Table 4: Ablation study of our BBS-Net. ‘BM’ = base model. ‘CA’ = channel attention. ‘SA’ = spatial attention. ‘PTM’ = progressively transposed module. # Settings NJU2K [34] NLPR [49] STERE [47] DES [9] LFSD [41] SSD [75] SIP [20] BM CA SA PTM S "M# S "M#S " M# S "M#S &”
Visual Saliency Transformer (2021, methodology): “The experimental results on four RGB-D SOD datasets, i.e., NJUD, DUTLF-Depth, STERE, and LFSD, are given in Table 1.”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “The stereopsis is leveraged for saliency analysis [37].”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, background): “The remaining samples and the STEREO dataset are used for testing.”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, background): “STEREO [31]: contains 797 stereoscopic images downloaded from the Internet.”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “Earlier work for SOD relies on various hand-designed feature [7, 26, 37, 41].”
Salient Object Detection via Structured Matrix Decomposition (2017, background): “The effectiveness of other complementary cues such as texture [20], depth [52], [53] or surroundedness [54] have also been considered recently.”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, background): “It is also worth noting that the performance of early fusion strategy (EF-CNN) is consistently inferior to the adopted late fusion strategy (MVCNN), especially for DES and NLPR datasets, on which the model is trained with fewer image pairs compared to the NJUD and STEREO datasets.”
Depth saliency based on anisotropic center-surround difference (2014, methodology): “We choose three state-of-the-art methods work on color images namely CNTX [9], RC [10], PCA [11] and three depth saliency methods namely CURV [16], SS [13], DP [14] for comparison.”