Search Results for author:
Found 63 papers, 23 papers with code
Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking different trajectories to users with the exploration of complex mobility patterns.
Nearest Neighbor-Based Contrastive Learning for Hyperspectral and LiDAR Data Classification
It is commonly nontrivial to build a robust self-supervised learning model for multisource data classification, due to the fact that the semantic similarities of neighborhood regions are not exploited in existing contrastive learning framework.
A Deep Learning Method for Real-time Bias Correction of Wind Field Forecasts in the Western North Pacific
In this study, we developed the Multi-Task-Double Encoder Trajectory Gated Recurrent Unit (MT-DETrajGRU) model, which uses an improved double-encoder forecaster architecture to model the spatiotemporal sequence of the U and V components of the wind field; we designed a multi-task learning loss function to correct wind speed and wind direction simultaneously using only one model.
Deep Learning Methods for Calibrated Photometric Stereo and Beyond: A Survey
We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set.
Lightweight Monocular Depth Estimation with an Edge Guided Network
In order to aggregate the context information and edge attention features, we design a transformer-based feature aggregation module (TRFA).
Multiplex Heterogeneous Graph Convolutional Network
Heterogeneous graph convolutional networks have gained great popularity in tackling various network analytical tasks on heterogeneous network data, ranging from link prediction to node classification.
Synthetic Aperture Radar Image Change Detection via Layer Attention-Based Noise-Tolerant Network
To this end, we proposed a layer attention-based noise-tolerant network, termed LANTNet.
Editing Out-of-domain GAN Inversion via Differential Activations
Consequently, in the decomposition phase, we further present a GAN prior based deghosting network for separating the final fine edited image from the coarse reconstruction.
Mutual Distillation Learning Network for Trajectory-User Linking
In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL.
Enhancing the Transferability via Feature-Momentum Adversarial Attack
However, the guidance map is fixed in existing methods, which can not consistently reflect the behavior of networks as the image is changed during iteration.
Scalable Motif Counting for Large-scale Temporal Graphs
We first categorize the temporal motifs based on their distinct properties, and then design customized algorithms that offer efficient strategies to exactly count the motif instances of each category.
Change Detection from Synthetic Aperture Radar Images via Dual Path Denoising Network
We also propose the distinctive patch convolution for feature representation learning to reduce the time consumption.
SSCU-Net: Spatial-Spectral Collaborative Unmixing Network for Hyperspectral Images
Important findings on the use of spatial and spectral information in the autoencoder framework are discussed.
Adaptive DropBlock Enhanced Generative Adversarial Networks for Hyperspectral Image Classification
Second, an adaptive DropBlock (AdapDrop) is proposed as a regularization method employed in the generator and discriminator to alleviate the mode collapse issue.
SAR Image Change Detection Based on Multiscale Capsule Network
On the one hand, the multiscale capsule module is employed to exploit the spatial relationship of features.
Change Detection from Synthetic Aperture Radar Images via Graph-Based Knowledge Supplement Network
Synthetic aperture radar (SAR) image change detection is a vital yet challenging task in the field of remote sensing image analysis.
Physics-Guided Generative Adversarial Networks for Sea Subsurface Temperature Prediction
Physical modeling methods can offer the potential for extrapolation beyond observational conditions, while data-driven methods are flexible in adapting to data and are capable of detecting unexpected patterns.
Synthetic Aperture Radar Image Change Detection via Siamese Adaptive Fusion Network
Moreover, a correlation layer is designed to further explore the correlation between multitemporal images.
SurroundNet: Towards Effective Low-Light Image Enhancement
Although Convolution Neural Networks (CNNs) has made substantial progress in the low-light image enhancement task, one critical problem of CNNs is the paradox of model complexity and performance.
LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
Ocean fronts can cause the accumulation of nutrients and affect the propagation of underwater sound, so high-precision ocean front detection is of great significance to the marine fishery and national defense fields.
Incorporating Lambertian Priors into Surface Normals Measurement
In order to address this challenge, we here propose a photometric stereo network that incorporates Lambertian priors to better measure the surface normal.
Wallpaper Texture Generation and Style Transfer Based on Multi-label Semantics
Textures contain a wealth of image information and are widely used in various fields such as computer graphics and computer vision.
Knowledge Distillation via Instance-level Sequence Learning
Recently, distillation approaches are suggested to extract general knowledge from a teacher network to guide a student network.
SAR Image Change Detection Based on Multiscale Capsule Network
On the one hand, the capsule module is employed to exploit the spatial relationship of features.
Learning the Precise Feature for Cluster Assignment
Based on this, we propose a general-purpose deep clustering framework which radically integrates representation learning and clustering into a single pipeline for the first time.
Network Embedding via Deep Prediction Model
This paper proposes a network embedding framework to capture the transfer behaviors on structured networks via deep prediction models.
Mask-ShadowNet: Towards Shadow Removal via Masked Adaptive Instance Normalization
Shadow removal is an important yet challenging task in image processing and computer vision.
Gaussian Dynamic Convolution for Efficient Single-Image Segmentation
Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation.
Change Detection in Synthetic Aperture Radar Images Using a Dual-Domain Network
In addition, we further propose a multi-region convolution module, which emphasizes the central region of each patch.
Dual Discriminator Adversarial Distillation for Data-free Model Compression
Then the generated samples are used to train the compact student network under the supervision of the teacher.
Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks
Convolutional neural networks (CNN) have made great progress for synthetic aperture radar (SAR) images change detection.
Hyperspectral and LiDAR data classification based on linear self-attention
An efficient linear self-attention fusion model is proposed in this paper for the task of hyperspectral image (HSI) and LiDAR data joint classification.
Disentangled Non-Local Network for Hyperspectral and LiDAR Data Classification
As the ground objects become increasingly complex, the classification results obtained by single source remote sensing data can hardly meet the application requirements.
Hyperspectral Image Denoising Based On Multi-Stream Denoising Network
Our network consists of the noise estimation subnetwork and denoising subnetwork.
Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator
Then, a new style discriminator is designed to improve the translation performance.
Similarity Transfer for Knowledge Distillation
The proposed approach promotes the performance of student model as the virtual sample created by multiple images produces a similar probability distribution in the teacher and student networks.
Class balanced underwater object detection dataset generated by class-wise style augmentation
CWSA is a new kind of data augmentation technique which augments the training data for the minority classes by generating various colors, textures and contrasts for the minority classes.
Multimodal Gait Recognition for Neurodegenerative Diseases
In recent years, single modality based gait recognition has been extensively explored in the analysis of medical images or other sensory data, and it is recognised that each of the established approaches has different strengths and weaknesses.
Associated Spatio-Temporal Capsule Network for Gait Recognition
It is a challenging task to identify a person based on her/his gait patterns.
Image Harmonization With Transformer
Current solutions mainly adopt an encoder-decoder architecture with convolutional neural network (CNN) to capture the context of composite images, trying to understand what it looks like in the surrounding background near the foreground.
Ranked #5 on
Image Harmonization
on iHarmony4
Multi-Modal Multi-Action Video Recognition
In this paper, we propose a novel multi-action relation model for videos, by leveraging both relational graph convolutional networks (GCNs) and video multi-modality.
Low-Rank Tensor Completion by Approximating the Tensor Average Rank
Our method is motivated by the recently proposed t-product based on any invertible linear transforms.
SWIPENET: Object detection in noisy underwater images
Moreover, inspired by the human education process that drives the learning from easy to hard concepts, we here propose the CMA training paradigm that first trains a clean detector which is free from the influence of noisy data.
Real-time 3D Facial Tracking via Cascaded Compositional Learning
We propose to learn a cascade of globally-optimized modular boosted ferns (GoMBF) to solve multi-modal facial motion regression for real-time 3D facial tracking from a monocular RGB camera.
3D Facial Geometry Recovery from a Depth View with Attention Guided Generative Adversarial Network
We present to recover the complete 3D facial geometry from a single depth view by proposing an Attention Guided Generative Adversarial Networks (AGGAN).
Perceptual underwater image enhancement with deep learning and physical priors
Underwater image enhancement, as a pre-processing step to improve the accuracy of the following object detection task, has drawn considerable attention in the field of underwater navigation and ocean exploration.
A Benchmark dataset for both underwater image enhancement and underwater object detection
To investigate how the underwater image enhancement methods influence the following underwater object detection tasks, in this paper, we provide a large-scale underwater object detection dataset with both bounding box annotations and high quality reference images, namely OUC dataset.
Progressively Unfreezing Perceptual GAN
Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details.
Underwater object detection using Invert Multi-Class Adaboost with deep learning
In addition, we propose a novel sample-weighted loss function which can model sample weights for SWIPENet, which uses a novel sample re-weighting algorithm, namely Invert Multi-Class Adaboost (IMA), to reduce the influence of noise on the proposed SWIPENet.
High-Order Paired-ASPP Networks for Semantic Segmenation
The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone.
Multi-level Similarity Learning for Low-Shot Recognition
Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence.
Few-shot Learning for Domain-specific Fine-grained Image Classification
Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications.
Highlight Every Step: Knowledge Distillation via Collaborative Teaching
Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher model.
Combining SLAM with muti-spectral photometric stereo for real-time dense 3D reconstruction
Obtaining dense 3D reconstrution with low computational cost is one of the important goals in the field of SLAM.
Prediction of Sea Surface Temperature using Long Short-Term Memory
We formulate the SST prediction problem as a time series regression problem.
Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
With the increasing demands of applications in virtual reality such as 3D films, virtual Human-Machine Interactions and virtual agents, the analysis of 3D human face analysis is considered to be more and more important as a fundamental step for those virtual reality tasks.
A Procedural Texture Generation Framework Based on Semantic Descriptions
Finally, given a set of semantic descriptions, the diverse properties of the samples in the semantic space can lead the framework to find an appropriate generation model that uses appropriate parameters to produce a desired texture.
Perception Driven Texture Generation
In this paper, we propose a joint deep network model that combines adversarial training and perceptual feature regression for texture generation, while only random noise and user-defined perceptual attributes are required as input.
Cascade one-vs-rest detection network for fine-grained recognition without part annotations
To bridge this gap, we introduce a cascaded structure to eliminate background and exploit a one-vs-rest loss to capture more minute variances among different subordinate categories.
An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
Since about 100 years ago, to learn the intrinsic structure of data, many representation learning approaches have been proposed, including both linear ones and nonlinear ones, supervised ones and unsupervised ones.
Banzhaf Random Forests
Random forests are a type of ensemble method which makes predictions by combining the results of several independent trees.
A Deep Hashing Learning Network
For most existing hashing methods, an image is first encoded as a vector of hand-crafted visual feature, followed by a hash projection and quantization step to get the compact binary vector.
A PCA-Based Convolutional Network
Particularly, each feature extraction stage includes two layers: a convolutional layer and a feature pooling layer.
