Papers
Fri 18 Jun 2021
163 papers
- Sample Efficient Social Navigation Using Inverse Reinforcement LearningOffline RL and imitation learning from data → Social robot navigation
- Deep Learning for Multi-View Stereo via Plane Sweep: A Survey
- Patch-Based Image Restoration using Expectation Propagation
- Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
- Interval and fuzzy physics-informed neural networks for uncertain fields
- A Declarative Goal-oriented Framework for Smart Environments with LPaaS
- Analysis and Tuning of a Voice Assistant System for Dysfluent Speech
- Reliability and Validity of Image-Based and Self-Reported Skin Phenotype Metrics
- α-Stable convergence of heavy-tailed infinitely-wide neural networks
- QuaPy: A Python-Based Framework for Quantification
- Paradigm selection for Data Fusion of SAR and Multispectral Sentinel data applied to Land-Cover Classification
- Performance Evaluation of Classification Models for Household Income, Consumption and Expenditure Data Set
- Leveraging Language to Learn Program Abstractions and Search Heuristics
- Dynamical Deep Generative Latent Modeling of 3D Skeletal Motion
- The Animal ID Problem: Continual Curation
- Towards a Query-Optimal and Time-Efficient Algorithm for Clustering with a Faulty Oracle
- On the benefits of maximum likelihood estimation for Regression and Forecasting
- Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments
- Prediction-Free, Real-Time Flexible Control of Tidal Lagoons through Proximal Policy Optimisation: A Case Study for the Swansea Lagoon
- Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior
- Liquid Sensing Using WiFi Signals
- High-level Features for Resource Economy and Fast Learning in Skill Transfer
- Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
- The Perils of Learning Before Optimizing
- Single View Physical Distance Estimation using Human Pose
- Non-parametric Differentially Private Confidence Intervals for the Median
- Exoskeleton-Based Multimodal Action and Movement Recognition: Identifying and Developing the Optimal Boosted Learning Approach
- Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets
- Group-Structured Adversarial Training
- A system of vision sensor based deep neural networks for complex driving scene analysis in support of crash risk assessment and prevention
- Proper Value Equivalence
- Differentiable Particle Filtering without Modifying the Forward Pass
- Universal Rate-Distortion-Perception Representations for Lossy Compression
- Towards Single Stage Weakly Supervised Semantic Segmentation
- Multi-Task Learning for User Engagement and Adoption in Live Video Streaming Events
- Dependency Structure Misspecification in Multi-Source Weak Supervision Models
- Riemannian Convex Potential Maps
- End-to-end Temporal Action Detection with Transformer
- How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
- MADE: Exploration via Maximizing Deviation from Explored Regions
- A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization
- On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
- Bridging the Gap Between Object Detection and User Intent via Query-Modulation
- An Empirical Investigation into Deep and Shallow Rule Learning
- Less is More: Feature Selection for Adversarial Robustness with Compressive Counter-Adversarial Attacks
- Active Offline Policy Selection
- VSAC: Efficient and Accurate Estimator for H and F
- Nonparametric Hamiltonian Monte Carlo
- A Coarse-to-Fine Instance Segmentation Network with Learning Boundary Representation
- Residual Error: a New Performance Measure for Adversarial Robustness
- Combining Pseudo-Point and State Space Approximations for Sum-Separable Gaussian Processes
- Distributed Deep Learning in Open Collaborations
- An Investigation into Mini-Batch Rule Learning
- BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models
- A Dynamic Spatial-temporal Attention Network for Early Anticipation of Traffic Accidents
- Federated Robustness Propagation: Sharing Robustness in Heterogeneous Federated Learning
- Non-Iterative Phase Retrieval With Cascaded Neural Networks
- Equilibrium Design for Concurrent Games
- Rational Shapley Values
- Adversarial Training Helps Transfer Learning via Better Representations
- Deterministic Gibbs Sampling via Ordinary Differential Equations
- NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weights
- Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detection
- Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition
- Problem Dependent View on Structured Thresholding Bandit Problems
- The Principles of Deep Learning Theory
- Steerable Partial Differential Operators for Equivariant Neural Networks
- Toward Fault Detection in Industrial Welding Processes with Deep Learning and Data Augmentation
- FinGAT: Financial Graph Attention Networks for Recommending Top-K Profitable Stocks
- Learning to Complete Code with Sketches
- pyWATTS: Python Workflow Automation Tool for Time Series
- Predicting Gender by First Name Using Character-level Machine Learning
- World-GAN: a Generative Model for Minecraft Worlds
- All You Can Embed: Natural Language based Vehicle Retrieval with Spatio-Temporal Transformers
- The Dimpled Manifold Model of Adversarial Examples in Machine Learning
- Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks
- Classical Planning as QBF without Grounding (extended version)
- Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting
- VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion
- Enhancing user creativity: Semantic measures for idea generation
- Unsupervised Domain Adaptation for Dysarthric Speech Detection via Domain Adversarial Training and Mutual Information Minimization
- Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
- Challenges and Limitations with the Metrics Measuring the Complexity of Code-Mixed Text
- ScoreGrad: Multivariate Probabilistic Time Series Forecasting with Continuous Energy-based Generative Models
- Virtual Temporal Samples for Recurrent Neural Networks: applied to semantic segmentation in agriculture
- Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result
- Towards Distraction-Robust Active Visual Tracking
- Boolean Matrix Factorization with SAT and MaxSAT
- hSMAL: Detailed Horse Shape and Pose Reconstruction for Motion Pattern Recognition
- Discerning Generic Event Boundaries in Long-Form Wild Videos
- It's FLAN time! Summing feature-wise latent representations for interpretability
- Subjective Bias in Abstractive Summarization
- Debiased Subjective Assessment of Real-World Image Enhancement
- Combined Person Classification with Airborne Optical Sectioning
- Label prompt for multi-label text classification
- Learning to Plan via a Multi-Step Policy Regression Method
- Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images
- Being a Bit Frequentist Improves Bayesian Neural Networks
- Fitting summary statistics of neural data with a differentiable spiking network simulator
- Contrastive Learning of Generalized Game Representations
All 163
- A Vertical Federated Learning Framework for Horizontally Partitioned Labels
- On Contrastive Representations of Stochastic Processes
- Light Pollution Reduction in Nighttime Photography
- Synchronising speech segments with musical beats in Mandarin and English singing
- Training or Architecture? How to Incorporate Invariance in Neural Networks
- Learning and Meshing from Deep Implicit Surface Networks Using an Efficient Implementation of Analytic Marching
- EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2021: Team M3EM Technical Report
- Local AdaGrad-Type Algorithm for Stochastic Convex-Concave Optimization
- Zero-Shot Federated Learning with New Classes for Audio Classification
- Meta-control of social learning strategies
- Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection
- Towards Financial Sentiment Analysis in a South African Landscape
- Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation
- Improved Radar Localization on Lidar Maps Using Shared Embedding
- SPBERT: An Efficient Pre-training BERT on SPARQL Queries for Question Answering over Knowledge Graphs
- Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
- A Note on Optimizing Distributions using Kernel Mean Embeddings
- Accumulative Poisoning Attacks on Real-time Data
- Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
- BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detection
- Advanced Hough-based method for on-device document localization
- Weakly Supervised Pre-Training for Multi-Hop Retriever
- Towards interpreting computer vision based on transformation invariant optimization
- How COVID-19 Has Changed Crowdfunding: Evidence From GoFundMe
- The Curse of Passive Data Collection in Batch Reinforcement Learning
- HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
- Multi-Granularity Network with Modal Attention for Dense Affective Understanding
- Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System
- Novelty Detection via Contrastive Learning with Negative Data Augmentation
- Labelling Drifts in a Fault Detection System for Wind Turbine Maintenance
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
- Universum GANs: Improving GANs through contradictions
- Investigating the Role of Negatives in Contrastive Representation Learning
- Goal-Directed Planning by Reinforcement Learning and Active Inference
- A Framework for Real-time Traffic Trajectory Tracking, Speed Estimation, and Driver Behavior Calibration at Urban Intersections Using Virtual Traffic Lanes
- Graph-based Joint Pandemic Concern and Relation Extraction on Twitter
- Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
- Being Properly Improper
- A Unified Generative Adversarial Network Training via Self-Labeling and Self-Attention
- Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
- Message Passing in Graph Convolution Networks via Adaptive Filter Banks
- Light Lies: Optical Adversarial Attack
- A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction
- Bad Characters: Imperceptible NLP Attacks
- Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations
- PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
- Development of a conversing and body temperature scanning autonomously navigating robot to help screen for COVID-19
- Gradual Domain Adaptation via Self-Training of Auxiliary Models
- GEM: A General Evaluation Benchmark for Multimodal Tasks
- Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
- Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
- An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognition
- Batch Multi-Fidelity Bayesian Optimization with Deep Auto-Regressive Networks
- Anomaly Detection in Dynamic Graphs via Transformer
- Smoothed Multi-View Subspace Clustering
- Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
- Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective
- Heuristic Stopping Rules For Technology-Assisted Review
- Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review
- RSG: A Simple but Effective Module for Learning Imbalanced Datasets
- Effective Model Sparsification by Scheduled Grow-and-Prune Methods
- LSEC: Large-scale spectral ensemble clustering
- Machining Cycle Time Prediction: Data-driven Modelling of Machine Tool Feedrate Behavior with Neural Networks