Papers
Mon 28 Jun 2021
153 papers
- Data Poisoning Won't Save You From Facial RecognitionLLM safety and security → Backdoor and data poisoning attacks
- A Rational Entailment for Expressive Description Logics via Description Logic Programs
- Priority prediction of Asian Hornet sighting report using machine learning methods
- CVEH: A Dynamic Framework To Profile Vehicle Movements To Mitigate Hit And Run Cases Using Crowdsourcing
- Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction
- Physics-Informed Neural Networks for Minimising Worst-Case Violations in DC Optimal Power Flow
- Recent Advances in Fibrosis and Scar Segmentation from Cardiac MRI: A State-of-the-Art Review and Future Perspectives
- High-dimensional separability for one- and few-shot learning
- An Efficient Batch Constrained Bayesian Optimization Approach for Analog Circuit Synthesis via Multi-objective Acquisition Ensemble
- Explaining the Performance of Multi-label Classification Methods with Data Set Properties
- Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization
- Learning complex dependency structure of gene regulatory networks from high dimensional micro-array data with Gaussian Bayesian networks
- Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent
- Early Mobility Recognition for Intensive Care Unit Patients Using Accelerometers
- Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
- Are conditional GANs explicitly conditional?
- Understanding Cognitive Fatigue from fMRI Scans with Self-supervised Learning
- An Uncertainty Estimation Framework for Probabilistic Object Detection
- Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
- Characterization of the Variation Spaces Corresponding to Shallow Neural Networks
- Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation
- Sharp Lower Bounds on the Approximation Rate of Shallow Neural Networks
- Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment
- Object Detection Based Handwriting Localization
- Online Estimation and Coverage Control with Heterogeneous Sensing Information
- Fast Bayesian Variable Selection in Binomial and Negative Binomial Regression
- On component interactions in two-stage recommender systems
- The Food Recognition Benchmark: Using DeepLearning to Recognize Food on Images
- Federated Dynamic Spectrum Access
- Robust Distributed Optimization With Randomly Corrupted Gradients
- Adversarial Robustness of Streaming Algorithms through Importance Sampling
- Deep Learning for Face Anti-Spoofing: A Survey
- Data augmentation for deep learning based accelerated MRI reconstruction with limited data
- Achieving Real-Time Object Detection on MobileDevices with Neural Pruning Search
- Fast Training of Neural Lumigraph Representations using Meta Learning
- Feature selection for intrusion detection systems
- Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit
- Striking the Right Balance: Recall Loss for Semantic Segmentation
- Overview of BioASQ 2021: The ninth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
- Rethinking Token-Mixing MLP for MLP-based Vision Backbone
- Early Convolutions Help Transformers See Better
- HDMapGen: A Hierarchical Graph Generative Model of High Definition Maps
- Modeling Clothing as a Separate Layer for an Animatable Human Avatar
- Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft
- Learning from an Exploring Demonstrator: Optimal Reward Estimation for Bandits
- Doing good by fighting fraud: Ethical anti-fraud systems for mobile payments
- Bootstrapping the error of Oja's algorithm
- K-Net: Towards Unified Image Segmentation
- Iris Presentation Attack Detection by Attention-based and Deep Pixel-wise Binary Supervision Network
- Progressive Joint Low-light Enhancement and Noise Removal for Raw Images
- CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoders
- Gaussian Process Regression for Active Sensing Probabilistic Structural Health Monitoring: Experimental Assessment Across Multiple Damage and Loading Scenarios
- Improving Prediction of Low-Prior Clinical Events with Simultaneous General Patient-State Representation Learning
- Understanding Dynamics of Nonlinear Representation Learning and Its Application
- Virtual Agents in Live Coding: A Short Review
- Dataset Bias Mitigation Through Analysis of CNN Training Scores
- Feature Importance Guided Attack: A Model Agnostic Adversarial Attack
- Offline Planning and Online Learning under Recovering Rewards
- A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques
- Laplace Redux -- Effortless Bayesian Deep Learning
- Hyperspectral Remote Sensing Image Classification Based on Multi-scale Cross Graphic Convolution
- Reasoning on textitDL-Litecal R with Defeasibility in ASP
- PhysiNet: A Combination of Physics-based Model and Neural Network Model for Digital Twins
- Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
- HALF: Holistic Auto Machine Learning for FPGAs
- Training Massive Deep Neural Networks in a Smart Contract: A New Hope
- A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning
- One-Shot Affordance Detection
- TENT: Tensorized Encoder Transformer for Temperature Forecasting
- Real-Time Human Pose Estimation on a Smart Walker using Convolutional Neural Networks
- Speech2Properties2Gestures: Gesture-Property Prediction as a Tool for Generating Representational Gestures from Speech
- Unsupervised Discovery of Actions in Instructional Videos
- Real-Time Multi-View 3D Human Pose Estimation using Semantic Feedback to Smart Edge Sensors
- Keyphrase Generation for Scientific Document Retrieval
- Tiled sparse coding in eigenspaces for the COVID-19 diagnosis in chest X-ray images
- What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval
- Weighted multi-level deep learning analysis and framework for processing breast cancer WSIs
- Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis
- Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos
- Scalable Optimal Classifiers for Adversarial Settings under Uncertainty
- Fast computation of mutual information in the frequency domain with applications to global multimodal image alignment
- Fractal Pyramid Networks
- Robust Learning-Augmented Caching: An Experimental Study
- Evolutionary Dynamics and Phi-Regret Minimization in Games
- Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples
- Improved Prediction and Network Estimation Using the Monotone Single Index Multi-variate Autoregressive Model
- Overview of BioASQ 2020: The eighth BioASQ challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
- Ensembling Shift Detectors: an Extensive Empirical Evaluation
- Dataset and Benchmarking of Real-Time Embedded Object Detection for RoboCup SSL
- Integrate-and-Fire Neurons for Low-Powered Pattern Recognition
- ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
- The Convergence Rate of SGD's Final Iterate: Analysis on Dimension Dependence
- Topos and Stacks of Deep Neural Networks
- Privacy-Preserving Image Acquisition Using Trainable Optical Kernel
- Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics
- Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
- Modeling and Reasoning in Event Calculus using Goal-Directed Constraint Answer Set Programming
- Variance Reduction for Matrix Computations with Applications to Gaussian Processes
- Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach
- Contrastive Counterfactual Visual Explanations With Overdetermination
All 153
- A Diffeomorphic Aging Model for Adult Human Brain from Cross-Sectional Data
- Weight Divergence Driven Divide-and-Conquer Approach for Optimal Federated Learning from non-IID Data
- R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network
- LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction
- Making Images Real Again: A Comprehensive Survey on Deep Image Composition
- Cheating Detection Pipeline for Online Interviews and Exams
- Complexity-based partitioning of CSFI problem instances with Transformers
- Adventurer's Treasure Hunt: A Transparent System for Visually Grounded Compositional Visual Question Answering based on Scene Graphs
- A More Compact Object Detector Head Network with Feature Enhancement and Relational Reasoning
- False Negative Reduction in Video Instance Segmentation using Uncertainty Estimates
- Error analysis for physics informed neural networks (PINNs) approximating Kolmogorov PDEs
- Hyperbolic Busemann Learning with Ideal Prototypes
- Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learning
- Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images
- Enhancing the Generalization for Intent Classification and Out-of-Domain Detection in SLU
- RadGraph: Extracting Clinical Entities and Relations from Radiology Reports
- Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition
- R-Drop: Regularized Dropout for Neural Networks
- Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection
- A Knowledge-Grounded Dialog System Based on Pre-Trained Language Models
- VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects
- Prior-Induced Information Alignment for Image Matting
- Traditional Machine Learning and Deep Learning Models for Argumentation Mining in Russian Texts
- Current Landscape of the Russian Sentiment Corpora
- Efficient Dialogue State Tracking by Masked Hierarchical Transformer
- Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations
- Modelling Monotonic and Non-Monotonic Attribute Dependencies with Embeddings: A Theoretical Analysis
- Causal Reinforcement Learning using Observational and Interventional Data
- Capturing the temporal constraints of gradual patterns
- Co2L: Contrastive Continual Learning
- Progressive Class-based Expansion Learning For Image Classification
- Poisoning the Search Space in Neural Architecture Search
- Habitat 2.0: Training Home Assistants to Rearrange their Habitat
- A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images
- Single RGB-D Camera Teleoperation for General Robotic Manipulation
- Political Ideology and Polarization of Policy Positions: A Multi-dimensional Approach
- Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems
- Multi-Compound Transformer for Accurate Biomedical Image Segmentation
- Towards Model-informed Precision Dosing with Expert-in-the-loop Machine Learning
- A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition
- Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits
- Domain Adaptation Broad Learning System Based on Locally Linear Embedding
- Rail-5k: a Real-World Dataset for Rail Surface Defects Detection
- Integrating topic modeling and word embedding to characterize violent deaths
- Word2Box: Capturing Set-Theoretic Semantics of Words using Box Embeddings
- Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning
- Deep Learning Image Recognition for Non-images
- PNet -- A Deep Learning Based Photometry and Astrometry Bayesian Framework
- Revelio: ML-Generated Debugging Queries for Distributed Systems
- Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks
- High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails
- Stabilizing Equilibrium Models by Jacobian Regularization
- Reducing numerical precision preserves classification accuracy in Mondrian Forests