Search Results for author:
Found 26 papers, 8 papers with code
Dynamic Cross-Modal Feature Interaction Network for Hyperspectral and LiDAR Data Classification
To address these limitations, we propose a novel Dynamic Cross-Modal Feature Interaction Network (DCMNet), the first framework leveraging a dynamic routing mechanism for HSI and LiDAR classification.
Image Gradient-Aided Photometric Stereo Network
Photometric stereo (PS) endeavors to ascertain surface normals using shading clues from photometric images under various illuminations.
A Deep Semantic Segmentation Network with Semantic and Contextual Refinements
Additionally, this paper extends these modules to a lightweight segmentation network, achieving an mIoU of 82. 5% on the Cityscapes validation set with only 137. 9 GFLOPs.
A feature refinement module for light-weight semantic segmentation network
Low computational complexity and high segmentation accuracy are both essential to the real-world semantic segmentation tasks.
Superpixel Cost Volume Excitation for Stereo Matching
In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity maps.
Hierarchical Attention and Parallel Filter Fusion Network for Multi-Source Data Classification
To solve the problem, we propose a hierarchical attention and parallel filter fusion network for multi-source data classification.
Exploring Cross-Domain Few-Shot Classification via Frequency-Aware Prompting
However, most existing methods pay more attention to learning domain-adaptive inductive bias (meta-knowledge) through feature-wise manipulation or task diversity improvement while neglecting the phenomenon that deep networks tend to rely more on high-frequency cues to make the classification decision, which thus degenerates the robustness of learned inductive bias since high-frequency information is vulnerable and easy to be disturbed by noisy information.
Dual-Stream Attention Network for Hyperspectral Image Unmixing
Therefore, we adopt a "many to one" strategy to estimate the abundance of the central pixel.
Sparse Focus Network for Multi-Source Remote Sensing Data Classification
Multi-source remote sensing data classification has emerged as a prominent research topic with the advancement of various sensors.
RMAFF-PSN: A Residual Multi-Scale Attention Feature Fusion Photometric Stereo Network
Predicting accurate normal maps of objects from two-dimensional images in regions of complex structure and spatial material variations is challenging using photometric stereo methods due to the influence of surface reflection properties caused by variations in object geometry and surface materials.
CLIP-Hand3D: Exploiting 3D Hand Pose Estimation via Context-Aware Prompting
In particular, the distribution order of hand joints in various 3D space directions is derived from pose labels, forming corresponding text prompts that are subsequently encoded into text representations.
Camouflaged Object Detection with Feature Grafting and Distractor Aware
In order to better explore the advantages of the two encoders, we design a cross-attention-based Feature Grafting Module to graft features extracted from Transformer branch into CNN branch, after which the features are aggregated in the Feature Fusion Module.
Edge-Aware Mirror Network for Camouflaged Object Detection
Existing edge-aware camouflaged object detection (COD) methods normally output the edge prediction in the early stage.
SAWU-Net: Spatial Attention Weighted Unmixing Network for Hyperspectral Images
To this end, we put forward a spatial attention weighted unmixing network, dubbed as SAWU-Net, which learns a spatial attention network and a weighted unmixing network in an end-to-end manner for better spatial feature exploitation.
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.
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.
The Property of Frequency Shift in 2D-FRFT Domain with Application to Image Encryption
The Fractional Fourier Transform (FRFT) has been playing a unique and increasingly important role in signal and image processing.
Discriminative Multiple Canonical Correlation Analysis for Information Fusion
In this paper, we propose the Discriminative Multiple Canonical Correlation Analysis (DMCCA) for multimodal information analysis and fusion.
The Labeled Multiple Canonical Correlation Analysis for Information Fusion
The objective of multimodal information fusion is to mathematically analyze information carried in different sources and create a new representation which will be more effectively utilized in pattern recognition and other multimedia information processing tasks.
Online Behavioral Analysis with Application to Emotion State Identification
In this paper, we propose a novel discriminative model for online behavioral analysis with application to emotion state identification.
Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
In this paper, we proposed an edge-labeling-based directed gated graph network (DGGN) for few-shot learning, which utilizes gated recurrent units to implicitly update the similarity between nodes.
Associated Spatio-Temporal Capsule Network for Gait Recognition
It is a challenging task to identify a person based on her/his gait patterns.
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.
Infant brain MRI segmentation with dilated convolution pyramid downsampling and self-attention
In this paper, we propose a dual aggregation network to adaptively aggregate different information in infant brain MRI segmentation.
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.
Sparse hierarchical interaction learning with epigraphical projection
This work focuses on learning optimization problems with quadratical interactions between variables, which go beyond the additive models of traditional linear learning.
