Search Results for author:
Found 60 papers, 14 papers with code
Geometric Reachability for Attitude Control Systems via Contraction Theory
We model the attitude dynamics on the product manifold $\mathrm{SO}(3) \times \mathbb{R}^3$ and introduce a novel parametrized family of Riemannian metrics on this space.
VTAO-BiManip: Masked Visual-Tactile-Action Pre-training with Object Understanding for Bimanual Dexterous Manipulation
In this paper, we introduce VTAO-BiManip, a novel framework that combines visual-tactile-action pretraining with object understanding to facilitate curriculum RL to enable human-like bimanual manipulation.
Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices
Object detection is a fundamental enabler for many real-time downstream applications such as autonomous driving, augmented reality and supply chain management.
Multi-robot autonomous 3D reconstruction using Gaussian splatting with Semantic guidance
To further reduce time cost of task generation and improve reconstruction quality, we integrate online open-vocabulary semantic segmentation with surface uncertainty of 3DGS, focusing view sampling on regions with high instance uncertainty.
FairDD: Fair Dataset Distillation via Synchronized Matching
The key innovation of FairDD lies in synchronously matching synthetic datasets to PA-wise groups of original datasets, rather than indiscriminate alignment to the whole distributions in vanilla DDs, dominated by majority groups.
No-regret Exploration in Shuffle Private Reinforcement Learning
Previous work mainly focuses on two trust models of DP: the central model, where a central agent is responsible for protecting users' sensitive data, and the (stronger) local model, where the protection occurs directly on the user side.
Privacy-Preserving Resilient Vector Consensus
This paper studies privacy-preserving resilient vector consensus in multi-agent systems against faulty agents, where normal agents can achieve consensus within the convex hull of their initial states while protecting state vectors from being disclosed.
Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey
Furthermore, we provide a detailed taxonomy covering the research topics related to object detection and tracking in the context of radar and camera technologies. Finally, we discuss the emerging perspectives in the field of radar-camera fusion perception and highlight the potential areas for future research.
SoK: Dataset Copyright Auditing in Machine Learning Systems
As the implementation of machine learning (ML) systems becomes more widespread, especially with the introduction of larger ML models, we perceive a spring demand for massive data.
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
Deep learning-based feature matching has shown great superiority for point cloud registration in the absence of pose priors.
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection.
Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning
Recent innovations in autonomous drones have facilitated time-optimal flight in single-drone configurations, and enhanced maneuverability in multi-drone systems by applying optimal control and learning-based methods.
FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection
Due to the vast testing space, the increasing demand for effective and efficient testing of deep neural networks (DNNs) has led to the development of various DNN test case prioritization techniques.
Towards Weather-Robust 3D Human Body Reconstruction: Millimeter-Wave Radar-Based Dataset, Benchmark, and Multi-Modal Fusion
With this dataset, we conduct a comprehensive analysis about the limitations of single-modality reconstruction and the impact of missing points and sparsity on the reconstruction performance.
Optimizing 6G Integrated Sensing and Communications (ISAC) via Expert Networks
Integrated Sensing and Communications (ISAC) is one of the core technologies of 6G, which combines sensing and communication functions into a single system.
Frequency-Domain Refinement with Multiscale Diffusion for Super Resolution
Then FDDiff guides reverse diffusion process to progressively complement the missing high-frequency details over timesteps.
CT-NeRF: Incremental Optimizing Neural Radiance Field and Poses with Complex Trajectory
In this pipeline, we first propose a local-global bundle adjustment under a pose graph connecting neighboring frames to enforce the consistency between poses to escape the local minima caused by only pose consistency with the scene structure.
MAexp: A Generic Platform for RL-based Multi-Agent Exploration
The sim-to-real gap poses a significant challenge in RL-based multi-agent exploration due to scene quantization and action discretization.
Autonomous Implicit Indoor Scene Reconstruction with Frontier Exploration
In the paper, we propose to 1) incorporate frontier-based exploration tasks for global coverage with implicit surface uncertainty-based reconstruction tasks to achieve high-quality reconstruction.
MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels
Human activity recognition (HAR) will be an essential function of various emerging applications.
Context-Aware Integration of Language and Visual References for Natural Language Tracking
Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame.
Intention-aware Denoising Diffusion Model for Trajectory Prediction
To decrease the inference time, we reduce the variable dimensions in the intention-aware diffusion process and restrict the initial distribution of the action-aware diffusion process, which leads to fewer diffusion steps.
SAM-PD: How Far Can SAM Take Us in Tracking and Segmenting Anything in Videos by Prompt Denoising
Recently, promptable segmentation models, such as the Segment Anything Model (SAM), have demonstrated robust zero-shot generalization capabilities on static images.
Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation
Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community.
In-Hand 3D Object Reconstruction from a Monocular RGB Video
We evaluate our approach on HO3D and HOD datasets and demonstrate that it outperforms the state-of-the-art methods in terms of reconstruction surface quality, with an improvement of $52\%$ on HO3D and $20\%$ on HOD.
Inverse Reinforcement Learning with Unknown Reward Model based on Structural Risk Minimization
A simplistic model is less likely to contain the real reward function, while a model with high complexity leads to substantial computation cost and risks overfitting.
Label-Free Multivariate Time Series Anomaly Detection
In this paper, we propose MTGFlow, an unsupervised anomaly detection approach for MTS anomaly detection via dynamic Graph and entity-aware normalizing Flow.
Deep Learning Enabled Semantic Communication Systems for Video Transmission
Semantic communication has emerged as a promising approach for improving efficient transmission in the next generation of wireless networks.
Confidant: Customizing Transformer-based LLMs via Collaborative Edge Training
Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks.
AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training
Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training.
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
It is a crucial task when training data is not accessible due to various concerns, eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly.
Ranked #2 on
zero-shot anomaly detection
on MVTec AD
SAGE-ICP: Semantic Information-Assisted ICP
Robust and accurate pose estimation in unknown environments is an essential part of robotic applications.
KDD-LOAM: Jointly Learned Keypoint Detector and Descriptors Assisted LiDAR Odometry and Mapping
Sparse keypoint matching based on distinct 3D feature representations can improve the efficiency and robustness of point cloud registration.
ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning
In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL.
The Model Inversion Eavesdropping Attack in Semantic Communication Systems
In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency.
InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild
Understanding human interaction with objects is an important research topic for embodied Artificial Intelligence and identifying the objects that humans are interacting with is a primary problem for interaction understanding.
WCCNet: Wavelet-integrated CNN with Crossmodal Rearranging Fusion for Fast Multispectral Pedestrian Detection
Multispectral pedestrian detection achieves better visibility in challenging conditions and thus has a broad application in various tasks, for which both the accuracy and computational cost are of paramount importance.
Seal-3D: Interactive Pixel-Level Editing for Neural Radiance Fields
With the popularity of implicit neural representations, or neural radiance fields (NeRF), there is a pressing need for editing methods to interact with the implicit 3D models for tasks like post-processing reconstructed scenes and 3D content creation.
Enhancing Cyber-Resiliency of DER-based SmartGrid: A Survey
The overall aim of this survey is to demonstrate the development trend of CRE methods and motivate further efforts to improve the cyber-resiliency of DER-based smart grid.
Consistent and Asymptotically Efficient Localization from Range-Difference Measurements
Based on the preliminary consistent location estimate, a one-step GN iteration suffices to achieve the same asymptotic property as the ML estimator.
F&F Attack: Adversarial Attack against Multiple Object Trackers by Inducing False Negatives and False Positives
Multi-object tracking (MOT) aims to build moving trajectories for number-agnostic objects.
$α$ DARTS Once More: Enhancing Differentiable Architecture Search by Masked Image Modeling
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
Pixel-Aligned Non-parametric Hand Mesh Reconstruction
The decoder aggregate both local image features in pixels and geometric features in vertices.
Contact2Grasp: 3D Grasp Synthesis via Hand-Object Contact Constraint
To tackle the challenge, we introduce an intermediate variable for grasp contact areas to constrain the grasp generation; in other words, we factorize the mapping into two sequential stages by assuming that grasping poses are fully constrained given contact maps: 1) we first learn contact map distributions to generate the potential contact maps for grasps; 2) then learn a mapping from the contact maps to the grasping poses.
ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions
However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images.
mmBody Benchmark: 3D Body Reconstruction Dataset and Analysis for Millimeter Wave Radar
The results demonstrate that 1) despite the noise and sparsity of the generated point clouds, the mmWave radar can achieve better reconstruction accuracy than the RGB camera but worse than the depth camera; 2) the reconstruction from the mmWave radar is affected by adverse weather conditions moderately while the RGB(D) camera is severely affected.
Detecting Multivariate Time Series Anomalies with Zero Known Label
Multivariate time series anomaly detection has been extensively studied under the semi-supervised setting, where a training dataset with all normal instances is required.
NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations
In this paper, we explore for the first time the possibility of using implicit neural representations for autonomous 3D scene reconstruction by addressing two key challenges: 1) seeking a criterion to measure the quality of the candidate viewpoints for the view planning based on the new representations, and 2) learning the criterion from data that can generalize to different scenes instead of a hand-crafting one.
Stability of Weighted Majority Voting under Estimated Weights
To formally analyse the uncertainty to the decision process, we introduce and analyse two important properties of such unbiased trust values: stability of correctness and stability of optimality.
AsyncFedED: Asynchronous Federated Learning with Euclidean Distance based Adaptive Weight Aggregation
In an asynchronous federated learning framework, the server updates the global model once it receives an update from a client instead of waiting for all the updates to arrive as in the synchronous setting.
VeriFi: Towards Verifiable Federated Unlearning
One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.
Global and Asymptotically Efficient Localization from Range Measurements
In terms of whether the variance of measurement noises is known or not, we propose the Bias-Eli estimator (which involves solving a generalized trust region subproblem) and the Noise-Est estimator (which is obtained by solving a convex problem), respectively.
Wireless Transmission of Images With The Assistance of Multi-level Semantic Information
In particular, the proposed model includes a multilevel semantic feature extractor, that extracts both the highlevel semantic information, such as the text semantics and the segmentation semantics, and the low-level semantic information, such as local spatial details of the images.
Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search
The NAR explores the quality tiers of the search space globally and classifies each individual to the tier they belong to according to its global ranking.
FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
Our numerical results demonstrate that FTPipeHD is 6. 8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one.
Fairness-aware Outlier Ensemble
Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance.
PIDNet: An Efficient Network for Dynamic Pedestrian Intrusion Detection
Vision-based dynamic pedestrian intrusion detection (PID), judging whether pedestrians intrude an area-of-interest (AoI) by a moving camera, is an important task in mobile surveillance.
False Data Injection Attacks and the Distributed Countermeasure in DC Microgrids
In this paper, we consider a hierarchical control based DC microgrid (DCmG) equipped with unknown input observer (UIO) based detectors, where the potential false data injection (FDI) attacks and the distributed countermeasure are investigated.
Privacy-preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation
With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks.
Personalized Attraction Enhanced Sponsored Search with Multi-task Learning
(2) It is difficult to obtain users' explicit feedback of their preference in product features.
