Search Results for author:
Found 36 papers, 8 papers with code
A sustainable development perspective on urban-scale roof greening priorities and benefits
Greenspaces are tightly linked to human well-being.
UB-FineNet: Urban Building Fine-grained Classification Network for Open-access Satellite Images
Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy.
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm
To address this challenge, we begin by devising a smooth proximal Lagrangian value function to handle the constrained lower-level problem.
Unlocking the Potential: Multi-task Deep Learning for Spaceborne Quantitative Monitoring of Fugitive Methane Plumes
We decompose methane emission monitoring into three sub-tasks: methane concentration inversion, plume segmentation, and emission rate estimation.
Bag of Tricks to Boost Adversarial Transferability
In this work, we find that several tiny changes in the existing adversarial attacks can significantly affect the attack performance, \eg, the number of iterations and step size.
STAF: 3D Human Mesh Recovery from Video with Spatio-Temporal Alignment Fusion
This method can remarkably improve the smoothness of recovery results from video.
Ranked #45 on
3D Human Pose Estimation
on 3DPW
(using extra training data)
FG-MDM: Towards Zero-Shot Human Motion Generation via Fine-Grained Descriptions
By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation.
W-HMR: Human Mesh Recovery in World Space with Weak-supervised Camera Calibration and Orientation Correction
We propose a novel orientation correction module to allow the reconstructed human body to remain normal in world space.
Ranked #1 on
3D Human Pose Estimation
on SPEC-MTP
(using extra training data)
HiH: A Multi-modal Hierarchy in Hierarchy Network for Unconstrained Gait Recognition
Gait recognition has achieved promising advances in controlled settings, yet it significantly struggles in unconstrained environments due to challenges such as view changes, occlusions, and varying walking speeds.
Understanding Fairness Surrogate Functions in Algorithmic Fairness
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
Self-supervised Multi-task Learning Framework for Safety and Health-Oriented Connected Driving Environment Perception using Onboard Camera
Extensive experiments on the synthesized data from the KITTI and real-world data collected in Beijing demonstrate that the proposed method can (1) achieve performance competitive in depth estimation as compared with state-of-the-art methods when taking clear images as input; (2) predict vivid depth map for images contaminated by various levels of haze; and (3) accurately estimate visibility, airlight, and PM2. 5 mass concentrations.
Urban GeoBIM construction by integrating semantic LiDAR point clouds with as-designed BIM models
In this paper, we propose a complementary strategy that integrates LiDAR point clouds with as-designed BIM models for reconstructing urban scenes.
Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning fields.
Classification of Single Tree Decay Stages from Combined Airborne LiDAR Data and CIR Imagery
Finally, the classification is conducted on the two datasets (3D multispectral point clouds and 2D projected images) based on the three Machine Learning algorithms.
Fair Scratch Tickets: Finding Fair Sparse Networks Without Weight Training
We randomly initialize a dense neural network and find appropriate binary masks for the weights to obtain fair sparse subnetworks without any weight training.
AuE-IPA: An AU Engagement Based Infant Pain Assessment Method
Recent studies have found that pain in infancy has a significant impact on infant development, including psychological problems, possible brain injury, and pain sensitivity in adulthood.
One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learning
It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes.
VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection
For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.
Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields.
Information fusion approach for biomass estimation in a plateau mountainous forest using a synergistic system comprising UAS-based digital camera and LiDAR
The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve using a system that synergistically combines an unmanned aircraft system (UAS)-based digital aerial camera and LiDAR to leverage their complementary advantages.
Joint Learning of Frequency and Spatial Domains for Dense Predictions
Current artificial neural networks mainly conduct the learning process in the spatial domain but neglect the frequency domain learning.
Efficient divide-and-conquer registration of UAV and ground LiDAR point clouds through canopy shape context
Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration.
A hybrid convolutional neural network/active contour approach to segmenting dead trees in aerial imagery
This improved performance is essential to meet emerging challenges caused by climate change (and other man-made perturbations to the systems), particularly to monitor and estimate carbon stock decay rates, monitor forest health and biodiversity, and the overall effects of dead wood on and from climate change.
A new weakly supervised approach for ALS point cloud semantic segmentation
For the ISPRS 3D Labeling Vaihingen data, by using only 0. 1% of labels, our method achieves an overall accuracy of 83. 0% and an average F1 score of 70. 0%, which have increased by 6. 9% and 12. 8% respectively, compared to model trained by sparse label information only.
Double Deep Q-learning Based Real-Time Optimization Strategy for Microgrids
It is challenging to solve this kind of stochastic nonlinear optimization problem.
Self-supervised Depth Estimation Leveraging Global Perception and Geometric Smoothness Using On-board Videos
Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences.
In the Danger Zone: U-Net Driven Quantile Regression can Predict High-risk SARS-CoV-2 Regions via Pollutant Particulate Matter and Satellite Imagery
Since the outbreak of COVID-19 policy makers have been relying upon non-pharmacological interventions to control the outbreak.
Weakly Supervised Pseudo-Label assisted Learning for ALS Point Cloud Semantic Segmentation
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data.
Instance segmentation of fallen trees in aerial color infrared imagery using active multi-contour evolution with fully convolutional network-based intensity priors
In this paper, we introduce a framework for segmenting instances of a common object class by multiple active contour evolution over semantic segmentation maps of images obtained through fully convolutional networks.
Pairwise Point Cloud Registration using Graph Matching and Rotation-invariant Features
Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds.
Generalized Operating Procedure for Deep Learning: an Unconstrained Optimal Design Perspective
In this paper, we intend to address this problem by presenting a generalized operating procedure for DL from the perspective of unconstrained optimal design, which is motivated by a simple intension to remove the barrier of using DL, especially for those scientists or engineers who are new but eager to use it.
Multi-stream Convolutional Neural Network with Frequency Selection for Robust Speaker Verification
For the diversity of temporal embeddings, we consider feature augmentation with frequency selection, which is to manually segment the full-band of frequency into several sub-bands, and the feature extractor of each stream can select which sub-bands to use as target frequency domain.
Deep Clustering With Intra-class Distance Constraint for Hyperspectral Images
The high dimensionality of hyperspectral images often results in the degradation of clustering performance.
1D-Convolutional Capsule Network for Hyperspectral Image Classification
The complex structure of CNNs results in prohibitive training efforts.
Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR Data
Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field.
