Depth saliency based on anisotropic center-surround difference

By Ran Ju, L. Ge, Wenjing Geng, Tongwei Ren, Gangshan Wu. International Conference on Information Photonics, 2014

522 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1a64a37af7205a7f6b208c740bd702027eadecff

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

Citations in the corpus

Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems (2020, background): “Recent years have witnessed increasing researches towards object detection among vision community by taking the advantages of multi-modal inputs, such as RGB + thermal, RGB + depth, RGB + LiDAR and so on [19,17,15,1].”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “ to investigate the aggregation strategies and different modules in the model. 4.1 Experimental Settings Datasets. We conduct our experiments on eight challenging RGB-D SOD benchmark datasets: NJU2K [67], NLPR [32], STERE [84], DES [35], LFSD [85], SSD [86], SIP [37] and DUT [19]. Tab. 1 provides an”
RGB-D salient object detection: A survey (2020, methodology): “7 F-measures under different thresholds for 24 RGB-D based models on the STERE [139], NLPR [51], LFSD [140], DES [49], SIP [38], GIT [47], SSD [85], and NJUD [56] datasets.”
RGBD Salient Object Detection via Deep Fusion (2016, methodology): “2) Performance Comparison: In this section, we compare our method with four state-of-the-art methods designed for RGB images (S-CNN [41], BSCA [16], MB+ [53], and LEGS [42]) and four RGBD saliency methods designed especially for RGBD images (LMH [12], ACSD [13], GP [14], and LBE [15]).”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “Experiments are conducted on six public RGB-D benchmark datasets: NJU2K [34] (2000 samples), NLPR [44] (1000 samples), STERE [43] (1000 samples), RGBD135 [10] (135 samples), LFSD [35] (100 samples), and SIP [18] (929 samples).”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, methodology): “comparison results of 18 SOTA RGB-D based SOD models over seven datasets, namely STERE [63], LFSD [64], DES [38], NLPR [39], NJU2K [37], SSD [66], and SIP (Ours) clearly demonstrate the robustness and efficiency of our D3Net model.”
UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, methodology): “, DES [8], and NLPR [41] datasets; or computing depth from stereo cameras, examples of such datasets are SSB [40] and NJU2K [28].”
Visual Saliency Transformer (2021, methodology): “For fair comparisons, we follow most previous methods to use the training set of DUTS to train our VST for RGB SOD and use 1,485 images from NJUD, 700 images from NLPR, and 800 images from DUTLF-Depth to train our VST for RGB-D SOD.”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, background): “There are five main RGB-D SOD datasets which are NJUD [23], RGBD135 [9] NLPR [34], SSD [74] and SIP [16].”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “4) NJUD [10]: Contains 2003 binocular image pairs col-”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “Samples from RGBD saliency datasets: NJU2000 [32], NLPR [42] and SSB [41].”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, background): “We split 1485 samples from NJUD and 700 samples from NLPR for training.”