Search Results for author:
Found 109 papers, 57 papers with code
ADs: Active Data-sharing for Data Quality Assurance in Advanced Manufacturing Systems
Machine learning (ML) methods are widely used in industrial applications, which usually require a large amount of training data.
Bayesian Diffusion Models for 3D Shape Reconstruction
We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes.
VideoPrism: A Foundational Visual Encoder for Video Understanding
We introduce VideoPrism, a general-purpose video encoder that tackles diverse video understanding tasks with a single frozen model.
Sparse Anatomical Prompt Semi-Supervised Learning with Masked Image Modeling for CBCT Tooth Segmentation
To address these challenges, this study aims to propose a tasked-oriented Masked Auto-Encoder paradigm to effectively utilize large amounts of unlabeled data to achieve accurate tooth segmentation with limited labeled data.
Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities
The rise of large foundation models, trained on extensive datasets, is revolutionizing the field of AI.
Distilling Vision-Language Models on Millions of Videos
Our best model outperforms state-of-the-art methods on MSR-VTT zero-shot text-to-video retrieval by 6%.
TrustLLM: Trustworthiness in Large Language Models
This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions.
LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
In this paper, we introduce the LLM factoscope, a novel Siamese network-based model that leverages the inner states of LLMs for factual detection.
GenoCraft: A Comprehensive, User-Friendly Web-Based Platform for High-Throughput Omics Data Analysis and Visualization
With GenoCraft, researchers and data scientists have access to an array of cutting-edge bioinformatics tools under a user-friendly interface, making it a valuable resource for managing and analyzing large-scale omics data.
NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation
While AD is typically treated as an unsupervised learning task due to the high cost of label annotation, it is more practical to assume access to a small set of labeled anomaly samples from domain experts, as is the case for semi-supervised anomaly detection.
Benchmarking Machine Learning Models for Quantum Error Correction
Quantum Error Correction (QEC) is one of the fundamental problems in quantum computer systems, which aims to detect and correct errors in the data qubits within quantum computers.
What Makes for Robust Multi-Modal Models in the Face of Missing Modalities?
With the growing success of multi-modal learning, research on the robustness of multi-modal models, especially when facing situations with missing modalities, is receiving increased attention.
Improving Discriminative Multi-Modal Learning with Large-Scale Pre-Trained Models
To this end, we introduce Multi-Modal Low-Rank Adaptation learning (MMLoRA).
LEAP: Liberate Sparse-view 3D Modeling from Camera Poses
Are camera poses necessary for multi-view 3D modeling?
Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants
The capabilities of MLLMs depend on two crucial factors: the model architecture to facilitate the feature alignment of visual modules and large language models; the multimodal instruction tuning datasets for human instruction following.
Training a Large Video Model on a Single Machine in a Day
Videos are big, complex to pre-process, and slow to train on.
Ranked #1 on
Multi-Instance Retrieval
on EPIC-KITCHENS-100
ADGym: Design Choices for Deep Anomaly Detection
Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing.
Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text.
Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i. e., lack of large-scale, high-quality image-text data).
Fast Unsupervised Deep Outlier Model Selection with Hypernetworks
Outlier detection (OD) finds many applications with a rich literature of numerous techniques.
Accurate 3D Prediction of Missing Teeth in Diverse Patterns for Precise Dental Implant Planning
This study presents a novel framework for accurate prediction of missing teeth in different patterns, facilitating digital implant planning.
DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection
DSV captures the alignment between an augmentation function and the anomaly-generating mechanism with surrogate losses, which approximate the discordance and separability of test data, respectively.
Regularized Multivariate Functional Principal Component Analysis
Multivariate Functional Principal Component Analysis (MFPCA) is a valuable tool for exploring relationships and identifying shared patterns of variation in multivariate functional data.
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks
Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures.
Construction of unbiased dental template and parametric dental model for precision digital dentistry
In this study, we develop an unbiased dental template by constructing an accurate dental atlas from CBCT images with guidance of teeth segmentation.
Stabilization with Prescribed Instant via Lyapunov Method
In anothor word, the settling time under the presented controller is independent of the initial conditions and equals the prescribed time instant.
Weakly Supervised Anomaly Detection: A Survey
Anomaly detection (AD) is a crucial task in machine learning with various applications, such as detecting emerging diseases, identifying financial frauds, and detecting fake news.
Federated Sufficient Dimension Reduction Through High-Dimensional Sparse Sliced Inverse Regression
Federated learning has become a popular tool in the big data era nowadays.
Online Kernel Sliced Inverse Regression
Online dimension reduction is a common method for high-dimensional streaming data processing.
EPR-Net: Constructing non-equilibrium potential landscape via a variational force projection formulation
We present EPR-Net, a novel and effective deep learning approach that tackles a crucial challenge in biophysics: constructing potential landscapes for high-dimensional non-equilibrium steady-state (NESS) systems.
Learning Video Representations from Large Language Models
We introduce LaViLa, a new approach to learning video-language representations by leveraging Large Language Models (LLMs).
Ranked #1 on
Action Recognition
on Charades-Ego
Offline Supervised Learning V.S. Online Direct Policy Optimization: A Comparative Study and A Unified Training Paradigm for Neural Network-Based Optimal Feedback Control
We first conduct a comparative study of two prevalent approaches: offline supervised learning and online direct policy optimization.
Toward Unsupervised Outlier Model Selection
At its core, ELECT is based on meta-learning; transferring prior knowledge (e. g. model performance) on historical datasets that are similar to the new one to facilitate UOMS.
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Deep learning models have achieved excellent recognition results on large-scale video benchmarks.
Real-time Online Video Detection with Temporal Smoothing Transformers
Streaming video recognition reasons about objects and their actions in every frame of a video.
Diffusion Models: A Comprehensive Survey of Methods and Applications
This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration.
ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels
In this work, we propose a method to leverage weak/noisy labels (e. g., risk scores generated by machine rules for detecting malware) that are cheaper to obtain for anomaly detection.
Hyperparameter Optimization for Unsupervised Outlier Detection
Given an unsupervised outlier detection (OD) algorithm, how can we optimize its hyperparameter(s) (HP) on a new dataset, without any labels?
BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
To bridge this gap, we present--to the best of our knowledge--the first comprehensive benchmark for unsupervised outlier node detection on static attributed graphs called BOND, with the following highlights.
ADBench: Anomaly Detection Benchmark
Given a long list of anomaly detection algorithms developed in the last few decades, how do they perform with regard to (i) varying levels of supervision, (ii) different types of anomalies, and (iii) noisy and corrupted data?
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training
Based on the observation, we present a method, called Ensemble Logit Difference Inhibition (ELODI), to train a classification system that achieves paragon performance in both error rate and NFR, at the inference cost of a single model.
Deep Supervised Information Bottleneck Hashing for Cross-modal Retrieval based Computer-aided Diagnosis
Mapping X-ray images, radiology reports, and other medical data as binary codes in the common space, which can assist clinicians to retrieve pathology-related data from heterogeneous modalities (i. e., hashing-based cross-modal medical data retrieval), provides a new view to promot computeraided diagnosis.
A Deep Reinforcement Learning Framework for Rapid Diagnosis of Whole Slide Pathological Images
Inspired by the pathologist's clinical diagnosis process, we propose a weakly supervised deep reinforcement learning framework, which can greatly reduce the time required for network inference.
Clues Before Answers: Generation-Enhanced Multiple-Choice QA
A trending paradigm for multiple-choice question answering (MCQA) is using a text-to-text framework.
Ranked #10 on
Question Answering
on OpenBookQA
Gaussian Kernel Variance For an Adaptive Learning Method on Signals Over Graphs
To be more specific, we focus on SKG with a Gaussian kernel and specify how to find a suitable variance for the kernel.
Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation
The state-of-the-art deep learning-based methods often simply concatenate the raw geometric attributes (i. e., coordinates and normal vectors) of mesh cells to train a single-stream network for automatic intra-oral scanner image segmentation.
Combining Individual and Joint Networking Behavior for Intelligent IoT Analytics
In this work, we design a novel, scalable approach, where a general demand forecasting model is built using the combined data of all the companies with a normalization factor.
Learning Robust Representation through Graph Adversarial Contrastive Learning
Existing studies show that node representations generated by graph neural networks (GNNs) are vulnerable to adversarial attacks, such as unnoticeable perturbations of adjacent matrix and node features.
ECOD: Unsupervised Outlier Detection Using Empirical Cumulative Distribution Functions
To address these issues, we present a simple yet effective algorithm called ECOD (Empirical-Cumulative-distribution-based Outlier Detection), which is inspired by the fact that outliers are often the "rare events" that appear in the tails of a distribution.
AI-Lancet: Locating Error-inducing Neurons to Optimize Neural Networks
With the knowledge of error-inducing neurons, we propose two methods to fix the errors: the neuron-flip and the neuron-fine-tuning.
BA-Net: Bridge Attention for Deep Convolutional Neural Networks
The core idea of this design is to bridge the outputs of the previous convolution layers through skip connections for channel weights generation.
Automatic Unsupervised Outlier Model Selection
Given an unsupervised outlier detection task on a new dataset, how can we automatically select a good outlier detection algorithm and its hyperparameter(s) (collectively called a model)?
Federated Learning Based on Dynamic Regularization
We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round.
TOD: GPU-accelerated Outlier Detection via Tensor Operations
Outlier detection (OD) is a key learning task for finding rare and deviant data samples, with many time-critical applications such as fraud detection and intrusion detection.
3D Dental model segmentation with graph attentional convolution network
We have evaluated our network on a real-patient dataset of dental models acquired through 3D intraoral scanners, and experimental results show that our method outperforms state-of-the-art deep learning methods for 3D shape segmentation.
Local Patch Network with Global Attention for Infrared Small Target Detection
A local patch network (LPNet) with global attention is proposed in this paper to detect small targets by jointly considering the global and local properties of infrared small target images.
Intrinsically Motivated Self-supervised Learning in Reinforcement Learning
In vision-based reinforcement learning (RL) tasks, it is prevalent to assign auxiliary tasks with a surrogate self-supervised loss so as to obtain more semantic representations and improve sample efficiency.
TSGCNet: Discriminative Geometric Feature Learning With Two-Stream Graph Convolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
GCN-MIF: Graph Convolutional Network with Multi-Information Fusion for Low-dose CT Denoising
To address this issue, we propose a novel graph convolutional network-based LDCT denoising model, namely GCN-MIF, to explicitly perform multi-information fusion for denoising purpose.
Revisiting Skeleton-based Action Recognition
In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons.
Ranked #1 on
Action Recognition
on NTU RGB+D
A Large-scale Study on Unsupervised Outlier Model Selection: Do Internal Strategies Suffice?
These so-called internal strategies solely rely on the input data (without labels) and the output (outlier scores) of the candidate models.
PointBA: Towards Backdoor Attacks in 3D Point Cloud
We present the backdoor attacks in 3D point cloud with a unified framework that exploits the unique properties of 3D data and networks.
HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Most existing solutions embed backdoors in DNN model training such that DNN ownership can be verified by triggering distinguishable model behaviors with a set of secret inputs.
Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development
Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics.
Upper Limits on the Isotropic Gravitational-Wave Background from Advanced LIGO's and Advanced Virgo's Third Observing Run
Unlike in previous observing runs in the advanced detector era, we include Virgo in the search for the GWB.
General Relativity and Quantum Cosmology Cosmology and Nongalactic Astrophysics
Inorganic component imaging of aggregate glue droplets on spider orb webs by TOF-SIMS
A uniform element distribution is seen for suspended pristine aggregate glue droplets, and a differential spreading of aggregate glue components is seen for attached aggregate glue droplets.
Atomic and Molecular Clusters Applied Physics Instrumentation and Detectors
PyHealth: A Python Library for Health Predictive Models
PyHealth consists of data preprocessing module, predictive modeling module, and evaluation module.
Cross-Attention Guided Network for Visual Tracking
Here, the channel attention of target template is introduced to guide the feature learning for search branch, and then the self-spatial attention is used to localize the informative part location after the correlation processing.
TSGCNet: Discriminative Geometric Feature Learning with Two-Stream GraphConvolutional Network for 3D Dental Model Segmentation
State-of-the-art methods directly concatenate the raw attributes of 3D inputs, namely coordinates and normal vectors of mesh cells, to train a single-stream network for fully-automated tooth segmentation.
AutoAudit: Mining Accounting and Time-Evolving Graphs
How can we spot money laundering in large-scale graph-like accounting datasets?
Social and Information Networks
A random batch Ewald method for particle systems with Coulomb interactions
We develop a random batch Ewald (RBE) method for molecular dynamics simulations of particle systems with long-range Coulomb interactions, which achieves an $O(N)$ complexity in each step of simulating the $N$-body systems.
Computational Physics 65C35, 82M37, 65T50
Automating Outlier Detection via Meta-Learning
Given an unsupervised outlier detection (OD) task on a new dataset, how can we automatically select a good outlier detection method and its hyperparameter(s) (collectively called a model)?
COPOD: Copula-Based Outlier Detection
In this work, we make three key contributions, 1) propose a novel, parameter-free outlier detection algorithm with both great performance and interpretability, 2) perform extensive experiments on 30 benchmark datasets to show that COPOD outperforms in most cases and is also one of the fastest algorithms, and 3) release an easy-to-use Python implementation for reproducibility.
SYNC: A Copula based Framework for Generating Synthetic Data from Aggregated Sources
A synthetic dataset is a data object that is generated programmatically, and it may be valuable to creating a single dataset from multiple sources when direct collection is difficult or costly.
TODS: An Automated Time Series Outlier Detection System
We present TODS, an automated Time Series Outlier Detection System for research and industrial applications.
Actor-Action Video Classification CSC 249/449 Spring 2020 Challenge Report
This technical report summarizes submissions and compiles from Actor-Action video classification challenge held as a final project in CSC 249/449 Machine Vision course (Spring 2020) at University of Rochester
Intra- and Inter-Action Understanding via Temporal Action Parsing
Current methods for action recognition primarily rely on deep convolutional networks to derive feature embeddings of visual and motion features.
FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding
To take action recognition to a new level, we develop FineGym, a new dataset built on top of gymnastic videos.
Omni-sourced Webly-supervised Learning for Video Recognition
Then a joint-training strategy is proposed to deal with the domain gaps between multiple data sources and formats in webly-supervised learning.
Ranked #5 on
Action Recognition
on UCF101
(using extra training data)
A random-batch Monte Carlo method for many-body systems with singular kernels
The cost of the rejection step is $O(1)$ since the interaction used is of short range.
Computational Physics Numerical Analysis Numerical Analysis 82B80, 60H35, 65C05
SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection
Outlier detection (OD) is a key machine learning (ML) task for identifying abnormal objects from general samples with numerous high-stake applications including fraud detection and intrusion detection.
On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attacks
Armed with the Thompson Sampling, we develop a black-box attack with success rate over 95% on ModelNet40 data set.
SUOD: Toward Scalable Unsupervised Outlier Detection
In this study, we propose a three-module acceleration framework called SUOD to expedite the training and prediction with a large number of unsupervised detection models.
Extracting clinical concepts from user queries
Often trained on annotated clinical notes, clinical NER models tend to struggle with tagging clinical entities in user queries because of the structural differences between clinical notes and user queries.
XGBOD: Improving Supervised Outlier Detection with Unsupervised Representation Learning
A new semi-supervised ensemble algorithm called XGBOD (Extreme Gradient Boosting Outlier Detection) is proposed, described and demonstrated for the enhanced detection of outliers from normal observations in various practical datasets.
DCSO: Dynamic Combination of Detector Scores for Outlier Ensembles
Selecting and combining the outlier scores of different base detectors used within outlier ensembles can be quite challenging in the absence of ground truth.
RNN-Test: Towards Adversarial Testing for Recurrent Neural Network Systems
Compared with the neuron coverage, the proposed state coverage metrics as guidance excel with 4. 17% to 97. 22% higher success (or generation) rate.
ADA+: A GENERIC FRAMEWORK WITH MORE ADAPTIVE EXPLICIT ADJUSTMENT FOR LEARNING RATE
Although adaptive algorithms have achieved significant success in training deep neural networks with faster training speed, they tend to have poor generalization performance compared to SGD with Momentum(SGDM).
Combining Machine Learning Models using combo Library
Model combination, often regarded as a key sub-field of ensemble learning, has been widely used in both academic research and industry applications.
Learning to Recover Sparse Signals
In compressed sensing, a primary problem to solve is to reconstruct a high dimensional sparse signal from a small number of observations.
SynC: A Unified Framework for Generating Synthetic Population with Gaussian Copula
Synthetic population generation is the process of combining multiple socioeconomic and demographic datasets from different sources and/or granularity levels, and downscaling them to an individual level.
Music Artist Classification with Convolutional Recurrent Neural Networks
To this end, an established classification architecture, a Convolutional Recurrent Neural Network (CRNN), is applied to the artist20 music artist identification dataset under a comprehensive set of conditions.
PyOD: A Python Toolbox for Scalable Outlier Detection
PyOD is an open-source Python toolbox for performing scalable outlier detection on multivariate data.
Seeing isn't Believing: Practical Adversarial Attack Against Object Detectors
In this paper, we presented systematic solutions to build robust and practical AEs against real world object detectors.
LSCP: Locally Selective Combination in Parallel Outlier Ensembles
The top-performing base detectors in this local region are selected and combined as the model's final output.
Trajectory Convolution for Action Recognition
How to leverage the temporal dimension is a key question in video analysis.
Find and Focus: Retrieve and Localize Video Events with Natural Language Queries
The thriving of video sharing services brings new challenges to video retrieval, e. g. the rapid growth in video duration and content diversity.
DLFuzz: Differential Fuzzing Testing of Deep Learning Systems
Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars.
Software Engineering
Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention
Document-level information is very important for event detection even at sentence level.
Federated Learning with Non-IID Data
Experiments show that accuracy can be increased by 30% for the CIFAR-10 dataset with only 5% globally shared data.
Recognize Actions by Disentangling Components of Dynamics
Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness.
PM-GANs: Discriminative Representation Learning for Action Recognition Using Partial-modalities
As a result, using partial data channels to build a full representation of multi-modalities is clearly desired.
CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition
For this purpose, we developed novel techniques that address a key technical challenge: integrating the commands into a song in a way that can be effectively recognized by ASR through the air, in the presence of background noise, while not being detected by a human listener.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification
Identifying a potentially large number of simultaneous line outages in power transmission networks in real time is a computationally hard problem.
Temporal Action Detection with Structured Segment Networks
Detecting actions in untrimmed videos is an important yet challenging task.
Ranked #6 on
Action Recognition
on THUMOS’14
A Pursuit of Temporal Accuracy in General Activity Detection
Detecting activities in untrimmed videos is an important but challenging task.
Ranked #29 on
Temporal Action Localization
on ActivityNet-1.3
3D Automatic Segmentation Method for Retinal Optical Coherence Tomography Volume Data Using Boundary Surface Enhancement
We present here a novel 3D automatic segmentation method for retinal OCT volume data.
Adaptive estimation of the copula correlation matrix for semiparametric elliptical copulas
Then we study a factor model of $\Sigma$, for which we propose a refined estimator $\widetilde{\Sigma}$ by fitting a low-rank matrix plus a diagonal matrix to $\hat{\Sigma}$ using least squares with a nuclear norm penalty on the low-rank matrix.
