Results 31 to 40 of about 622,575 (227)
Mutual Information Regularization for Weakly-Supervised RGB-D Salient Object Detection [PDF]
IEEE transactions on circuits and systems for video technology (Print), 2023 In this paper, we present a weakly-supervised RGB-D salient object detection model via scribble supervision. Specifically, as a multimodal learning task, we focus on effective multimodal representation learning via inter-modal mutual information ...
Aixuan Li +3 more
semanticscholar +1 more source
Salient object detection: A survey
Computational Visual Media, 2019 Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding
Ali Borji +4 more
doaj +1 more source
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection [PDF]
IEEE transactions on circuits and systems for video technology (Print), 2022 Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features.
Zhengyi Liu +3 more
semanticscholar +1 more source
Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency [PDF]
IET Image Processing, 2019, 2020 Salient object detection is evaluated using binary ground truth with the labels being salient object class and background. In this paper, we corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance. Our dataset, named SalMoN (saliency in multi-
arxiv +1 more source
Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection [PDF]
Computer Vision and Pattern Recognition, 2023 Most previous co-salient object detection works mainly focus on extracting co-salient cues via mining the consistency relations across images while ignore explicit exploration of background regions.
Long Li +7 more
semanticscholar +1 more source
RGB-D Salient Object Detection Method Based on Multi-Modal Fusion and Contour Guidance
IEEE Access, 2023 Salient object detection is a critical task in the field of computer vision. However, existing detection methods still face certain challenges, such as the inability to effectively integrate multimodal features and the blurring of detection result ...
Yanbin Peng, Mingkun Feng, Zhijun Zheng
doaj +1 more source
Memory-aided Contrastive Consensus Learning for Co-salient Object Detection [PDF]
AAAI Conference on Artificial Intelligence, 2023 Co-salient object detection (CoSOD) aims at detecting common salient objects within a group of relevant source images. Most of the latest works employ the attention mechanism for finding common objects. To achieve accurate CoSOD results with high-quality
Peng Zheng +4 more
semanticscholar +1 more source
A Fusion Underwater Salient Object Detection Based on Multi-Scale Saliency and Spatial Optimization
Journal of Marine Science and Engineering, 2023 Underwater images contain abundant information, but many challenges remain for underwater object detection tasks. Various salient object detection methods may encounter low detection precision, and the segmented map has an incomplete region of the target
Weiliang Huang, Daqi Zhu, Mingzhi Chen
doaj +1 more source
Hybrid-Attention Network for RGB-D Salient Object Detection
Applied Sciences, 2020 Depth information has been widely used to improve RGB-D salient object detection by extracting attention maps to determine the position information of objects in an image.
Yuzhen Chen, Wujie Zhou
doaj +1 more source
RGB-D Salient Object Detection Using Saliency and Edge Reverse Attention
IEEE Access, 2023 RGB-D salient object detection is a task to detect visually significant objects in an image using RGB and depth images. Although many useful CNN-based methods have been proposed in the past, there are some problems such as blurring of object boundaries ...
Tomoki Ikeda, Masaaki Ikehara
doaj +1 more source