Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMarch 2024
Progressive network based on detail scaling and texture extraction: A more general framework for image deraining
AbstractMany feature extraction components have been proposed for image deraining tasks, aiming to improve feature learning. However, few models have addressed the integration of multi-scale features from derain images. The fusion of multiple features at ...
Highlights- Introduce detail scaling module to extract generalized features from rainfall image.
- Improved Transform block was introduced to enhance the model’s generalized ability.
- Scale-mixing strategy is proposed for capturing more multi-...
- research-articleMarch 2024
Rotation-equivariant correspondence matching based on a dual-activation mixer
AbstractLearning-based correspondence matching methods have become the mainstream techniques in many computer vision and robotics applications due to their robustness to large illumination and viewpoint changes. However, it is difficult for conventional ...
- research-articleMarch 2024
Detection of dangerously approaching vehicles over onboard cameras by speed estimation from apparent size
- Iván García-Aguilar,
- Jorge García-González,
- Daniel Medina,
- Rafael Marcos Luque-Baena,
- Enrique Domínguez,
- Ezequiel López-Rubio
AbstractAutonomous driving requires information such as the velocity of other vehicles to prevent potential hazards. This work proposes a real-time deep learning-based framework to estimate vehicle speeds from image captures through an onboard camera. ...
Highlights- Use object detection and linear regression to estimate moving vehicle speeds.
- Comparison of the methodology with LIDAR-based speed estimation techniques.
- Evaluation of the methodology on the Prevention dataset.
- research-articleMarch 2024
Anchor Ball Regression Model for large-scale 3D skull landmark detection
AbstractRecent deep learning models have exhibited impressive performance in the area of 3D skull landmark detection, but most of them aimed to detect a fixed number of landmarks. This paper focuses on automatically detecting an arbitrary number of ...
- research-articleMarch 2024
Knowledge distillation for object detection based on Inconsistency-based Feature Imitation and Global Relation Imitation
AbstractKnowledge distillation (KD) is a method that transfers information from a larger network (teacher) to a smaller network (student) to obtain stronger performance without extra computational load. It has made great success in image classification, ...
-
- articleMarch 2024
Scene Graph Generation: A comprehensive survey
- Hongsheng Li,
- Guangming Zhu,
- Liang Zhang,
- Youliang Jiang,
- Yixuan Dang,
- Haoran Hou,
- Peiyi Shen,
- Xia Zhao,
- Syed Afaq Ali Shah,
- Mohammed Bennamoun
AbstractDeep learning techniques have led to remarkable breakthroughs in the field of object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful semantic ...
Graphical abstractDisplay Omitted
Highlights- A comprehensive review of 138 papers on scene graph generation is presented.
- We analyze 2D scene graph generation, focusing on feature representation.
- A review of typical datasets for 2D, spatio-temporal and 3D scene graph ...
- articleMarch 2024
A systematic review of image-level camouflaged object detection with deep learning
AbstractCamouflaged object detection (COD) aims to search and identify disguised objects that are hidden in their surrounding environment, thereby deceiving the human visual system. As an interesting and challenging task, COD has received increasing ...
- research-articleMarch 2024
SFAMNet: A scene flow attention-based micro-expression network
AbstractTremendous progress has been made in facial Micro-Expression (ME) spotting and recognition; however, most works have focused on either spotting or recognition tasks on the 2D videos. Until recently, the estimation of the 3D motion field (a.k.a ...
Highlights- First study to spot and recognize micro-expressions on the multi-modal dataset.
- A scene flow attention-based end-to-end multi-stream multi-task network is proposed.
- Scene flow is extracted to estimate the 3D motion using color and ...
- research-articleFebruary 2024
Joint learning of motion deblurring and defocus deblurring networks with a real-world dataset
AbstractWhen recovering the sharp image from a blurry observation, moving objects, e.g., people and vehicles, usually attract more perceptual attention. However, existing motion deblurring methods primarily focus on removing the global camera motion blur,...
- research-articleFebruary 2024
A multi-attention and depthwise separable convolution network for medical image segmentation
AbstractAutomatic medical image segmentation method is highly needed to help experts in lesion segmentation. The deep learning technology emerging has profoundly driven the development of medical image segmentation. While U-Net and attention mechanisms ...
- research-articleFebruary 2024
Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test
AbstractThis paper addresses the problem of analyzing the performance of 3D face alignment (3DFA), or facial landmark localization. This task is usually supervised, based on annotated datasets. Nevertheless, in the particular case of 3DFA, the annotation ...
- research-articleJanuary 2024
Enhancing glomeruli segmentation through cross-species pre-training
AbstractThe importance of kidney biopsy, a medical procedure in which a small tissue sample is extracted from the kidney for examination, is increasing due to the rising incidence of kidney disorders. This procedure helps diagnosing several kidney ...
Highlights- Train a deep neural network for the segmentation of human glomeruli.
- Explore the use of models pre-training on mice glomeruli histological images.
- Cross-species transfer learning for increased model performance and generalization.
- research-articleJanuary 2024
IEFM and IDS: Enhancing 3D environment perception via information encoding in indoor point cloud semantic segmentation
AbstractThe point cloud semantic segmentation plays a significant role in the understanding of 3D environment. However, current 3D point cloud segmentation methods pay little attention in the inevitable blurring and loss of point information within deep ...
Highlights- The loss of 3D point cloud information in deep network is inevitable.
- Introducing information encoding can effectively complement the lost information.
- Flexibly distribute information can alleviate encoding interference problem.
- research-articleJanuary 2024
ReSLAM: Reusable SLAM with heterogeneous cameras
- Francisco J. Romero-Ramirez,
- Rafael Muñoz-Salinas,
- Manuel J. Marín-Jiménez,
- Angel Carmona-Poyato,
- Rafael Medina-Carnicer
AbstractState-of-the-art SLAM methods are designed to work only with the type of camera employed to create the map, and little attention has been paid to the reusability of the maps created. In other words, the maps generated by current methods can only ...
Highlights- Proposed new SLAM system able to work with multiple and heterogeneous cameras.
- An internal bottom-up image representation allows comparing keypoints of cameras with different optics and resolutions.
- Different cameras can reuse a ...
- research-articleJanuary 2024
Progressive dual-domain-transfer cycleGAN for unsupervised MRI reconstruction
AbstractSupervised MRI reconstruction methods perform well when provided with matched undersampled and fully sampled data pairs. However, acquiring paired data can be expensive and impractical in several clinical settings, such as cine MRI. As a result, ...
- research-articleJanuary 2024
Deep unsupervised part-whole relational visual saliency
AbstractDeep Supervised Salient Object Detection (SSOD) excessively relies on large-scale annotated pixel-level labels which consume intensive labour acquiring high quality labels. In such precondition, deep Unsupervised Salient Object Detection (USOD) ...
- research-articleJanuary 2024
STF-Trans: A two-stream spatiotemporal fusion transformer for very high resolution satellites images
AbstractSpatiotemporal satellite image fusion is regarded as an effective approach to address the limitations of a single optical sensor and generate data with high spatial and temporal resolutions. Thanks to the recent advances of Deep Learning, ...
- research-articleDecember 2023
SPAR: An efficient self-attention network using Switching Partition Strategy for skeleton-based action recognition
AbstractGraph convolutional networks (GCN) have become the mainstream in skeleton-based action recognition. For further performance improvement, existing methods propose to utilize self-attention to model long-range features of joints. However, these ...
Highlights- We propose an efficient method for skeleton-based action recognition.
- We adopt self-attention to model the long-range features of joints.
- We design two partition strategies for low computational cost of self-attention.
- Our ...
- research-articleDecember 2023
GPro3D: Deriving 3D BBox from ground plane in monocular 3D object detection
AbstractConsidering the inherent ill-posed nature, monocular 3D object detection (M3OD) is extremely challenging. The ground plane prior is a highly informative geometry clue in M3OD. However, it has been neglected by most mainstream methods. This paper ...
- research-articleDecember 2023
Toward extracting and exploiting generalizable knowledge of deep 2D transformations in computer vision
AbstractExisting deep learning models suffer from out-of-distribution (o.o.d.) performance drop in computer vision tasks. In comparison, humans have a remarkable ability to interpret images, even if the scenes in the images are rare, thanks to the ...
Graphical abstractDisplay Omitted
Highlights- With our new learning methodology, a CNN model can learn generalizable knowledge.
- Even black/white noise can be used as a training dataset.
- A novel architecture “InterpretNet” is proposed to exploit generalizable knowledge.
- The ...