Filters








1,143 Hits in 8.5 sec

Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection

Hao Chen, Youfu Li
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Figure 1: Traditional architectures of the CNN-based RGB-D salient object detection networks. (a) 'Early fusion' scheme adopted in [13] and (b) 'late fusion' scheme adopted in [14].  ...  How to incorporate cross-modal complementarity sufficiently is the cornerstone question for RGB-D salient object detection.  ...  Figure 2 : 2 The architecture of the proposed progressively complementarity-aware fusion network for RGB-D salient object detection.  ... 
doi:10.1109/cvpr.2018.00322 dblp:conf/cvpr/ChenL18 fatcat:4wmrj7e43vdb3irinfkilca63q

Multi-modal Weights Sharing and Hierarchical Feature Fusion for RGBD Salient Object Detection

Fen Xiao, Bin Li, Yimu Peng, Chunhong Cao, Kai Hu, Xieping Gao
2020 IEEE Access  
First, we propose a CNN-based cross-modal transfer learning, which learn knowledge from sufficient labeled RGB salient object datasets and guide the depth domain feature extraction.  ...  INDEX TERMS RGBD, salient object detection, complementary feature extraction, hierarchical fusion. 26602 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  Li and Yu [27] designed deep CNNs with multiple fully connected layers to extract multi-scale features further boost the performance for salient object detection. Yi et al.  ... 
doi:10.1109/access.2020.2971509 fatcat:aze3ddzokjcy3pn764iffcibsm

Adaptive Fusion for RGB-D Salient Object Detection [article]

Ningning Wang, Xiaojin Gong
2019 arXiv   pre-print
RGB-D salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images.  ...  Specifically, we design a two-streamed convolutional neural network (CNN), each of which extracts features and predicts a saliency map from either RGB or depth modality.  ...  [17] designed a two-streamed CNN to extract RGB and depth features separately and then fuse them with a joint representation layer. Fusion in these methods is conducted with a single path.  ... 
arXiv:1901.01369v2 fatcat:y4kj2aonovgmrdiqqlbcwdpm3u

CNN-based RGB-D Salient Object Detection: Learn, Select and Fuse [article]

Hao Chen, Youfu Li
2019 arXiv   pre-print
The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning  ...  Furthermore, a top-down fusion structure is constructed for sufficient cross-modal interactions and cross-level transmissions.  ...  RGB-D salient object detection.  ... 
arXiv:1909.09309v1 fatcat:qdg64qx6kjbpxbjpmwlzjrqhcm

Adaptive Fusion for RGB-D Salient Object Detection

Ningning Wang, Xiaojin Gong
2019 IEEE Access  
INDEX TERMS RGB-D salient object detection, switch map, edge-preserving.  ...  RGB-D (red, green, blue, and depth) salient object detection aims to identify the most visually distinctive objects in a pair of color and depth images.  ...  The overview of our framework for RGB-D salient object detection.  ... 
doi:10.1109/access.2019.2913107 fatcat:xr2foirygjezxh6b2vzmiv6ney

Visual saliency detection for RGB-D images under a Bayesian framework

Songtao Wang, Zhen Zhou, Wei Jin, Hanbing Qu
2018 IPSJ Transactions on Computer Vision and Applications  
In this paper, we propose a saliency detection model for RGB-D images based on the deep features of RGB images and depth images within a Bayesian framework.  ...  network; then, the posterior probability of the RGB-D saliency is formulated by applying Bayes' theorem.  ...  Acknowledgements This work was supported in part by the Beijing Municipal special financial project (PXM2016_278215_000013, ZLXM_2017C010) and by the Innovation Group Plan of Beijing Academy of Science  ... 
doi:10.1186/s41074-017-0037-0 fatcat:jklxzq46vrbh3mk6n7ocbqhoiu

Edge Preserving and Multi-Scale Contextual Neural Network for Salient Object Detection

Xiang Wang, Huimin Ma, Xiaozhi Chen, Shaodi You
2018 IEEE Transactions on Image Processing  
In this paper, we propose a novel edge preserving and multi-scale contextual neural network for salient object detection.  ...  Furthermore, our method can be generally applied to RGB-D saliency detection by depth refinement.  ...  RGB-D Salient Object Detection RGB-D saliency is an emerging topic and most RGB-D saliency methods are based on fusing depth priors with RGB saliency priors. Ju et al.  ... 
doi:10.1109/tip.2017.2756825 pmid:28952942 fatcat:nmt2wuf3cjeavexdadpbo6y22i

Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection

Jia-Xing Zhao, Yang Cao, Deng-Ping Fan, Ming-Ming Cheng, Xuan-Yi Li, Le Zhang
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
The large availability of depth sensors provides valuable complementary information for salient object detection (SOD) in RGBD images.  ...  The enhanced depth cues are further integrated with RGB features for SOD, using a novel fluid pyramid integration, which can make better use of multi-scale cross-modal features.  ...  This research was supported by NSFC (61572264), the national youth talent support program, the Fundamental Research Funds for the Central Universities (Nankai University, NO. 63191501) and Tianjin Natural  ... 
doi:10.1109/cvpr.2019.00405 dblp:conf/cvpr/ZhaoCFCLZ19 fatcat:jbf7qmti4rfavdojywljdhk5va

RGB-D Salient Object Detection Based on Discriminative Cross-modal Transfer Learning [article]

Hao Chen, Y.F. Li, Dan Su
2017 arXiv   pre-print
In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality  ...  In the proposed approach, we leverage the auxiliary data from the source modality effectively by training the RGB saliency detection network to obtain the task-specific pre-understanding layers for the  ...  The MCDL model, which leverages CNNs for RGB saliency detection, is among the best RGB salient object detection approaches.  ... 
arXiv:1703.00122v2 fatcat:ifzew4huvrgqxasxndqojw4pki

RGB-D salient object detection: A survey

Tao Zhou, Deng-Ping Fan, Ming-Ming Cheng, Jianbing Shen, Ling Shao
2021 Computational Visual Media  
Moreover, to investigate the ability of existing models to detect salient objects, we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection  ...  In this paper, we provide a comprehensive survey of RGB-D based salient object detection models from various perspectives, and review related benchmark datasets in detail.  ...  Acknowledgements This research was supported by a Major Project for a New Generation of AI under Grant No. 2018AAA0100400, National Natural Science Foundation of China (61922046), and Tianjin Natural Science  ... 
doi:10.1007/s41095-020-0199-z pmid:33432275 pmcid:PMC7788385 fatcat:foiz2zth4vckjfuhvh524hwdtq

MutualFormer: Multi-Modality Representation Learning via Mutual Transformer [article]

Xixi Wang, Bo Jiang, Xiao Wang, Bin Luo
2021 arXiv   pre-print
The pristine researchers generally adopt the CNN to extract features of independent modality and aggregate them with a fusion module.  ...  We successfully apply the MutualFormer to the saliency detection problem and propose a novel approach to obtain the reinforced features of RGB and Depth images.  ...  ., RGB-D salient object detection and transformer in salient object detection. A. RGB-D SOD RGB-D salient object detection aims to locate the most salient objects (or regions) from visual image(s).  ... 
arXiv:2112.01177v2 fatcat:h424ta636jhivojwe2s2atmine

RGBD Salient Object Detection via Deep Fusion

Liangqiong Qu, Shengfeng He, Jiawei Zhang, Jiandong Tian, Yandong Tang, Qingxiong Yang
2017 IEEE Transactions on Image Processing  
This can guide the training of CNN towards detecting salient object more effectively due to the reduced learning ambiguity.  ...  In this paper, we design a new convolutional neural network (CNN) to fuse different low level saliency cues into hierarchical features for automatically detecting salient objects in RGBD images.  ...  (a) RGB image. (b) Depth image. (c) Saliency probability produced by the proposed CNN. (d) Background (non-salient) probability produced by the proposed CNN.  ... 
doi:10.1109/tip.2017.2682981 pmid:28320666 fatcat:m5jdky3zzrfzbnj3mvjaybf62q

Progressive Guided Fusion Network with Multi-modal and Multi-scale Attention for RGB-D Salient Object Detection

Jiajia Wu, Guangliang Han, Haining Wang, Hang Yang, Qingqing Li, Dongxu Liu, Fangjian Ye, Peixun Liu
2021 IEEE Access  
In this article, to mitigate such issues and highlight the salient objects, we propose a progressive guided fusion network (PGFNet) with multi-modal and multi-scale attention for RGB-D salient object detection  ...  INDEX TERMS RGB-D, salient object detection, multi-modal and multi-scale attention, progressive guided fusion. PEIXUN LIU received the Ph.D. degree from Jilin University, in 2015.  ...  To achieve this goal, in this work, we present a progressive guided fusion network (PGFNet) with multi-modal and VOLUME 9, 2021 multi-scale attention for RGB-D salient object detection.  ... 
doi:10.1109/access.2021.3126338 fatcat:tv4icfm67fdn3emkkvsihkcywi

Densely Deformable Efficient Salient Object Detection Network [article]

Tanveer Hussain, Saeed Anwar, Amin Ullah, Khan Muhammad, Sung Wook Baik
2021 arXiv   pre-print
Salient Object Detection (SOD) domain using RGB-D data has lately emerged with some current models' adequately precise results.  ...  In this paper, inspired by the best background/foreground separation abilities of deformable convolutions, we employ them in our Densely Deformable Network (DDNet) to achieve efficient SOD.  ...  This work was supported by the National Research Foundation of Korea (NRF) Grant funded by the Korea government (MSIT) (2019R1A2B5B01070067).  ... 
arXiv:2102.06407v1 fatcat:kbmzqxe5tfdezhs4n2tueh26n4

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu
2019 2019 IEEE/CVF International Conference on Computer Vision (ICCV)  
RGB-D approaches.  ...  Second, depth cues with abundant spatial information are innovatively combined with multi-scale context features for accurately locating salient objects.  ...  Acknowledgment This work was supported by the National Natural Science Foundation of China(61605022 and U1708263) and the Fundamental Research Funds for the Central Universities(DUT19JC58).  ... 
doi:10.1109/iccv.2019.00735 dblp:conf/iccv/PiaoJLZL19 fatcat:onlkwdepnjhgdgc4c46ldctebq
« Previous Showing results 1 — 15 out of 1,143 results