A5100435212- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Remote-Sensing Image Classification
- Advanced Neural Network Applications
- Video Surveillance and Tracking Methods
- Advanced Image Fusion Techniques
- Ionosphere and magnetosphere dynamics
- Image Retrieval and Classification Techniques
- Advanced Image Processing Techniques
- Multimodal Machine Learning Applications
- Robotics and Sensor-Based Localization
- Domain Adaptation and Few-Shot Learning
- Human Pose and Action Recognition
- Image Enhancement Techniques
- Medical Image Segmentation Techniques
- Image Processing Techniques and Applications
- Remote Sensing and Land Use
- Automated Road and Building Extraction
- Face and Expression Recognition
- Meteorological Phenomena and Simulations
- Remote Sensing and LiDAR Applications
- Image and Signal Denoising Methods
- Computer Graphics and Visualization Techniques
- 3D Shape Modeling and Analysis
- 3D Surveying and Cultural Heritage
École Polytechnique
2024
Institute of Automation
2015-2024
Chinese Academy of Sciences
2015-2024
University of Chinese Academy of Sciences
2018-2024
Fuzhou University
2024
Shandong Institute of Automation
2014-2024
Shanghai Children's Medical Center
2020-2024
Aerospace Information Research Institute
2024
Youjiang Medical College for Nationalities
2023
Southwest Hospital
2023
Images captured in foggy weather conditions often suffer from bad visibility. In this paper, we propose an efficient regularization method to remove hazes a single input image. Our benefits much exploration on the inherent boundary constraint transmission function. This constraint, combined with weighted L_1-norm based contextual regularization, is modeled into optimization problem estimate unknown scene transmission. A quite algorithm variable splitting also presented solve problem. The...
Point cloud analysis is very challenging, as the shape implied in irregular points difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN configuration for point analysis. The key RS-CNN learning from relation, i.e., geometric topology constraint among points. Specifically, convolutional weight local set forced learn a high-level relation expression predefined priors, between sampled and others. way, an...
Detecting small objects such as vehicles in satellite images is a difficult problem. Many features (such histogram of oriented gradient, local binary pattern, scale-invariant feature transform, etc.) have been used to improve the performance object detection, but mostly simple environments those on roads. Kembhavi et al. proposed that no satisfactory accuracy has achieved complex City San Francisco. Deep convolutional neural networks (DNNs) can learn rich from training data automatically and...
Image clustering is a crucial but challenging task in machine learning and computer vision. Existing methods often ignore the combination between feature clustering. To tackle this problem, we propose Deep Adaptive Clustering (DAC) that recasts problem into binary pairwise-classification framework to judge whether pairs of images belong same clusters. In DAC, similarities are calculated as cosine distance label features which generated by deep convolutional network (ConvNet). By introducing...
Current state-of-the-art detectors typically exploit feature pyramid to detect objects at different scales. Among them, FPN is one of the representative works that build a by multi-scale features summation. However, design defects behind prevent from being fully exploited. In this paper, we begin first analyzing in FPN, and then introduce new architecture named AugFPN address these problems. Specifically, consists three components: Consistent Supervision, Residual Feature Augmentation, Soft...
Accurate road detection and centerline extraction from very high resolution (VHR) remote sensing imagery are of central importance in a wide range applications. Due to the complex backgrounds occlusions trees cars, most methods bring heterogeneous segments; besides for task, current approaches fail extract wonderful network that appears smooth, complete, as well single-pixel width. To address above-mentioned issues, we propose novel deep model, i.e., cascaded end-to-end convolutional neural...
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable. A thorough grasp of elusive shape requires sufficiently contextual semantic information, yet few works devote to this. Here we propose DensePoint, a general architecture learn densely representation for point processing. Technically, it extends regular grid CNN configuration generalizing convolution operator, which holds permutation invariance points, and achieves...
Hyperspectral unmixing, the process of estimating a common set spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization understanding. From unsupervised learning perspective, this problem very challenging---both are unknown, making solution space too large. To reduce space, many approaches have been proposed by exploiting various priors. In practice, these priors would easily lead to some unsuitable solution....
The cross-modal feature matching has gained much attention in recent years, which many practical applications, such as the text-to-image retrieval. most difficult problem of is how to eliminate heterogeneity between modalities. existing methods (e.g., CCA and PLS) try learn a common latent subspace, where two modalities minimized so that cross-matching possible. However, these require fully paired samples suffer difficulties when dealing with unpaired data. Besides, utilizing class label...
Recently, automatic visual data understanding from drone platforms becomes highly demanding. To facilitate the study, Vision Meets Drone Object Detection in Image Challenge is held second time conjunction with 17-th International Conference on Computer (ICCV 2019), focuses image object detection drones. Results of 33 algorithms are presented. For each participating detector, a short description provided appendix. Our goal to advance state-of-the-art and provide comprehensive evaluation...
Semantic segmentation is a fundamental task in remote sensing image processing. The large appearance variations of ground objects make this quite challenging. Recently, deep convolutional neural networks (DCNNs) have shown outstanding performance task. A common strategy these methods (e.g., SegNet) for improvement to combine the feature maps learned at different DCNN layers. However, such combination usually implemented via map summation or concatenation, indicating that features are...
As an indispensable part in Intelligent Traffic System (ITS), the task of traffic forecasting inherently subjects to following three challenging aspects. First, data are physically associated with road networks, and thus should be formatted as graphs rather than regular grid-like tensors. Second, render strong spatial dependence, which implies that nodes usually have complex dynamic relationships between each other. Third, demonstrate temporal is crucial for time series modeling. To address...
Predicting traffic flow on networks is a very challenging task, due to the complicated and dynamic spatial-temporal dependencies between different nodes network. The renders two types of temporal dependencies, including short-term neighboring long-term periodic dependencies. What's more, spatial correlations over are both local non-local. To capture global correlations, we propose Global Spatial-Temporal Network (GSTNet), which consists several layers blocks. Each block contains...
Super-resolution from a single image plays an important role in many computer vision systems. However, it is still challenging task, especially preserving local edge structures. To construct high-resolution images while the sharp edges, effective edge-directed super-resolution method presented this paper. An adaptive self-interpolation algorithm first proposed to estimate gradient field directly input low-resolution image. The obtained then regarded as constraint or edge-preserving...
Building extraction from remote sensing images is of great importance in urban planning. Yet it a longstanding problem for many complicate factors such as various scales and complex backgrounds. This paper proposes novel supervised building method via deep deconvolution neural networks (DeconvNet). Our consists three steps. First, we preprocess the multi-source provided by IEEE GRSS Data Fusion Contest. A high-quality Vancouver dataset created on pansharpened whose ground-truth are obtained...
Cross-modal retrieval emphasizes understanding inter-modality semantic correlations, which is often achieved by designing a similarity function. Generally, one of the most important things considered function how to make cross-modal computable. In this paper, deep and bidirectional representation learning model proposed address issue image-text retrieval. Owing solid progress in computer vision natural language processing, it reliable extract representations from both raw image text data...
Separating an optical remote sensing image into sea and land areas is very challenging yet of great importance to coastline extraction subsequent object detection. Traditional methods based on handcrafted feature processing often face this dilemma when confronting high-resolution images for their complicated texture intensity distribution. In letter, we apply the prevalent deep convolutional neural networks sea–land segmentation problem make two innovations top traditional structure. First,...
Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of features. In this paper, we propose novel efficient deep framework to boost by distilling knowledge weakly-supervised detection without...
Sea-land segmentation and ship detection are two prevalent research domains for optical remote sensing harbor images can find many applications in supervision management. As the spatial resolution of imaging technology improves, traditional methods struggle to perform well due complicated appearance background distributions. In this paper, we unify above tasks into a single framework apply deep convolutional neural networks predict pixelwise label an input. Specifically, edge aware network...
Pixel-level classification for very high resolution (VHR) images is a crucial but challenging task in remote sensing. However, since the diverse ways of satellite image acquisition and distinct structures various regions, distributions same semantic classes among different data sets are dissimilar. Therefore, model trained on one set (source domain) may collapse, when it directly applied to another (target domain). To solve this problem, many adversarial-based domain adaptation methods have...