Search Results for author:
Found 71 papers, 24 papers with code
Fancy123: One Image to High-Quality 3D Mesh Generation via Plug-and-Play Deformation
The fidelity enhancement module deforms the 3D mesh to match the input image.
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.
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer.
TA3: Testing Against Adversarial Attacks on Machine Learning Models
Adversarial attacks are major threats to the deployment of machine learning (ML) models in many applications.
iGAiVA: Integrated Generative AI and Visual Analytics in a Machine Learning Workflow for Text Classification
In developing machine learning (ML) models for text classification, one common challenge is that the collected data is often not ideally distributed, especially when new classes are introduced in response to changes of data and tasks.
DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training
Efficient communication can enhance the overall performance of collaborative multi-agent reinforcement learning.
STAA: Spatio-Temporal Alignment Attention for Short-Term Precipitation Forecasting
There is a great need to accurately predict short-term precipitation, which has socioeconomic effects such as agriculture and disaster prevention.
More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding
To address this task, we introduce GreenPLM, which leverages more text data to compensate for the lack of 3D data.
Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations
Traditional deep Gaussian processes model the data evolution using a discrete hierarchy, whereas differential Gaussian processes (DIFFGPs) represent the evolution as an infinitely deep Gaussian process.
Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Sampling
Bayesian Last Layer (BLL) models focus solely on uncertainty in the output layer of neural networks, demonstrating comparable performance to more complex Bayesian models.
DACB-Net: Dual Attention Guided Compact Bilinear Convolution Neural Network for Skin Disease Classification
This paper introduces the three-branch Dual Attention-Guided Compact Bilinear CNN (DACB-Net) by focusing on learning from disease-specific regions to enhance accuracy and alignment.
Multimodal Physiological Signals Representation Learning via Multiscale Contrasting for Depression Recognition
Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG.
PointDreamer: Zero-shot 3D Textured Mesh Reconstruction from Colored Point Cloud by 2D Inpainting
Addressing this, we propose PointDreamer, a novel framework for textured mesh reconstruction from colored point cloud.
Graph External Attention Enhanced Transformer
The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or positional and structural encodings.
Enhancing Interaction Modeling with Agent Selection and Physical Coefficient for Trajectory Prediction
A thorough understanding of the interaction between the target agent and surrounding agents is a prerequisite for accurate trajectory prediction.
MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors
Notably, MiniGPT-3D gains an 8. 12 increase on GPT-4 evaluation score for the challenging object captioning task compared to ShapeLLM-13B, while the latter costs 160 total GPU-hours on 8 A800.
Ranked #1 on
3D Object Captioning
on Objaverse
Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction
Multi-task reinforcement learning (MTRL) demonstrate potential for enhancing the generalization of a robot, enabling it to perform multiple tasks concurrently.
PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation
Existing point cloud semantic segmentation networks cannot identify unknown classes and update their knowledge, due to a closed-set and static perspective of the real world, which would induce the intelligent agent to make bad decisions.
Prioritized League Reinforcement Learning for Large-Scale Heterogeneous Multiagent Systems
Furthermore, we design a prioritized policy gradient approach to compensate for the gap caused by differences in the number of different types of agents.
Feature-Action Design Patterns for Storytelling Visualizations with Time Series Data
Motivated initially by the need to communicate time series data during the COVID-19 pandemic, we developed a novel computer-assisted method for meta-authoring of stories, which enables the design of storyboards that include feature-action patterns in anticipation of potential features that may appear in dynamically arrived or selected data.
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys
The cultural landscape of interactions with dialogue agents is a compelling yet relatively unexplored territory.
Image Similarity using An Ensemble of Context-Sensitive Models
In this work, we present a more intuitive approach to build and compare image similarity models based on labelled data in the form of A:R vs B:R, i. e., determining if an image A is closer to a reference image R than another image B.
Multi-task deep learning for large-scale building detail extraction from high-resolution satellite imagery
Understanding urban dynamics and promoting sustainable development requires comprehensive insights about buildings.
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.
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking
Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates, which is crucial for location-related services such as navigation maps.
LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors
Instead of directly inverting the triggers, LMSanitator aims to invert the predefined attack vectors (pretrained models' output when the input is embedded with triggers) of the task-agnostic backdoors, which achieves much better convergence performance and backdoor detection accuracy.
Point-LGMask: Local and Global Contexts Embedding for Point Cloud Pre-training with Multi-Ratio Masking
In our work, we present Point-LGMask, a novel method to embed both local and global contexts with multi-ratio masking, which is quite effective for self-supervised feature learning of point clouds but is unfortunately ignored by existing pre-training works.
Ranked #3 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 5-way (10-shot)
(using extra training data)
DPMLBench: Holistic Evaluation of Differentially Private Machine Learning
We also explore some improvements that can maintain model utility and defend against MIAs more effectively.
Pay More Attention to Relation Exploration for Knowledge Base Question Answering
In this study, we propose a novel framework, RE-KBQA, that utilizes relations in the knowledge base to enhance entity representation and introduce additional supervision.
FACE-AUDITOR: Data Auditing in Facial Recognition Systems
Few-shot-based facial recognition systems have gained increasing attention due to their scalability and ability to work with a few face images during the model deployment phase.
Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study
The recent release of ChatGPT has garnered widespread recognition for its exceptional ability to generate human-like responses in dialogue.
Boundary Unlearning
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.
Enhancing Vital Sign Estimation Performance of FMCW MIMO Radar by Prior Human Shape Recognition
Additionally, human's random body movements deteriorate the estimation of breathing and heart rates, therefore the information of the chest location and a narrow radar beam toward the chest are demanded for more accurate vital sign estimation.
Urban Visual Intelligence: Studying Cities with AI and Street-level Imagery
The visual dimension of cities has been a fundamental subject in urban studies, since the pioneering work of scholars such as Sitte, Lynch, Arnheim, and Jacobs.
Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary
In this paper, we refocus our attention from the parameter space to the decision space of the DNN model, and propose Boundary Unlearning, a rapid yet effective way to unlearn an entire class from a trained DNN model.
CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion
In our work, we present CasFusionNet, a novel cascaded network for point cloud semantic scene completion by dense feature fusion.
Background Invariance Testing According to Semantic Proximity
This ontology enables (i) efficient and meaningful search for background scenes of different semantic distances to a target image, (ii) quantitative control of the distribution and sparsity of the sampled background scenes, and (iii) quality assurance using visual representations of invariance testing results (referred to as variance matrices).
Finding MNEMON: Reviving Memories of Node Embeddings
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks.
Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data Augmentation
Sign language recognition and translation first uses a recognition module to generate glosses from sign language videos and then employs a translation module to translate glosses into spoken sentences.
Semi-Supervised Adversarial Recognition of Refined Window Structures for Inverse Procedural Façade Modeling
Unfortunately, the large amount of interactive sample labeling efforts has dramatically hindered the application of deep learning methods, especially for 3D modeling tasks, which require heterogeneous samples.
Visualizing Ensemble Predictions of Music Mood
Music mood classification has been a challenging problem in comparison with other music classification problems (e. g., genre, composer, or period).
Inference Attacks Against Graph Neural Networks
Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.
Deep Fraud Detection on Non-attributed Graph
The successes of most previous methods heavily rely on rich node features and high-fidelity labels.
ML4ML: Automated Invariance Testing for Machine Learning Models
In this paper, we show that testing the invariance qualities of ML models may result in complex visual patterns that cannot be classified using simple formulas.
A Survey on Federated Learning and its Applications for Accelerating Industrial Internet of Things
Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4. 0 on the edge computing level.
Simulation-Based Optimization of User Interfaces for Quality-Assuring Machine Learning Model Predictions
QA for ML (QA4ML) interfaces require users to view a large amount of data and perform many interactions to correct errors made by the ML model.
Graph Unlearning
In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data.
A Bounded Measure for Estimating the Benefit of Visualization: Case Studies and Empirical Evaluation
The recently-proposed information-theoretic measure for analyzing the cost-benefit ratio of visualization processes can explain such usefulness experienced in practice, and postulate that the viewers' knowledge can reduce the potential distortion (e. g., misinterpretation) due to information loss.
Human-Computer Interaction Graphics Information Theory Information Theory
A Bounded Measure for Estimating the Benefit of Visualization: Theoretical Discourse and Conceptual Evaluation
We examine a number of bounded measures that include the Jenson-Shannon divergence and a new divergence measure formulated as part of this work.
Information Theory Graphics Human-Computer Interaction Information Theory
NeRF--: Neural Radiance Fields Without Known Camera Parameters
Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses.
Study on multi-fold bunch splitting in a high-intensity medium-energy proton synchrotron
Bunch splitting is an RF manipulation method of changing the bunch structure, bunch numbers and bunch intensity in the high-intensity synchrotrons that serve as the injector for a particle collider.
Accelerator Physics
Depth-Enhanced Feature Pyramid Network for Occlusion-Aware Verification of Buildings from Oblique Images
Finally, multi-view information from both the nadir and oblique images is used in a robust voting procedure to label changes in existing buildings.
DeepNetQoE: Self-adaptive QoE Optimization Framework of Deep Networks
A self-adaptive QoE model is set up that relates the model's accuracy with the computing resources required for training which will allow the experience value of the model to improve.
When Machine Unlearning Jeopardizes Privacy
More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy.
A Bounded Measure for Estimating the Benefit of Visualization
Information theory can be used to analyze the cost-benefit of visualization processes.
HypoML: Visual Analysis for Hypothesis-based Evaluation of Machine Learning Models
In this paper, we present a visual analytics tool for enabling hypothesis-based evaluation of machine learning (ML) models.
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
We present FlowNet3D++, a deep scene flow estimation network.
Feature-level and Model-level Audiovisual Fusion for Emotion Recognition in the Wild
In this paper, we proposed two strategies to fuse information extracted from different modalities, i. e., audio and visual.
AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework
First, the wide collection of data in the close-loop information flow of user and remote medical data center is discussed.
Hierarchical Reinforcement Learning for Multi-agent MOBA Game
Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information.
Wearable Affective Robot
The learning algorithm for the life modeling embedded in Fitbot can achieve better user's experience of affective social interaction.
Electroencephalogram (EEG)
Human-Computer Interaction
Background Subtraction using Compressed Low-resolution Images
The essential first step involved in almost all the visual tasks is background subtraction with a static camera.
In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning
In order to bring more intelligence to the edge systems, compared to traditional optimization methodology, and driven by the current deep learning techniques, we propose to integrate the Deep Reinforcement Learning techniques and Federated Learning framework with the mobile edge systems, for optimizing the mobile edge computing, caching and communication.
Collimated GeV attosecond electron-positron bunches from a plasma channel driven by 10 PW lasers
High-energy positrons and bright {\gamma}-ray sources are unique both for fundamental research and practical applications.
Plasma Physics
Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning
The trust-POMDP model provides a principled approach for the robot to (i) infer the trust of a human teammate through interaction, (ii) reason about the effect of its own actions on human trust, and (iii) choose actions that maximize team performance over the long term.
Detecting Small Signs from Large Images
Experimental results on a real-world conditioned traffic sign dataset have demonstrated the effectiveness of the proposed method in terms of detection accuracy and recall, especially for those with small sizes.
Brain Intelligence: Go Beyond Artificial Intelligence
Specifically, we plan to develop an intelligent learning model called Brain Intelligence (BI) that generates new ideas about events without having experienced them by using artificial life with an imagine function.
Underwater Optical Image Processing: A Comprehensive Review
This paper aims to review the state-of-the-art techniques in underwater image processing by highlighting the contributions and challenges presented in over 40 papers.
POMDP-lite for Robust Robot Planning under Uncertainty
We show that a POMDP-lite is equivalent to a set of fully observable Markov decision processes indexed by a hidden parameter and is useful for modeling a variety of interesting robotic tasks.
Service-Oriented Architectures and Web Services: Course Tutorial and Lab Notes
This document presents a number of quick-step instructions to get started on writing mini-service-oriented web services-based applications using OpenESB 2. 31, Tomcat 6, GlassFish 2. x/3. 0. 1 with BPEL support, and Java 1. 6+ primarily in Scientific Linux 6. 6 with user quota restrictions.
Distributed, Parallel, and Cluster Computing Software Engineering 68N15, 68U35 H.3.5; C.2.4; D.1.3
