Papers
Mon 1 Aug 2022
140 papers
- A Maintenance Planning Framework using Online and Offline Deep Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Safe Policy Improvement Approaches and their LimitationsOffline RL and imitation learning from data → Safe offline RL
- A System for Imitation Learning of Contact-Rich Bimanual Manipulation PoliciesOffline RL and imitation learning from data → Robot manipulation imitation learning
- Learning Transfer Operators by Kernel Density Estimation
- Choose, not Hoard: Information-to-Model Matching for Artificial Intelligence in O-RAN
- A Case for Dataset Specific Profiling
- Towards Psychologically-Grounded Dynamic Preference Models
- Unsupervised machine learning framework for discriminating major variants of concern during COVID-19
- Predicting Future Mosquito Larval Habitats Using Time Series Climate Forecasting and Deep Learning
- Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network
- A Deep Generative Model for Feasible and Diverse Population Synthesis
- TextWorldExpress: Simulating Text Games at One Million Steps Per Second
- MV6D: Multi-View 6D Pose Estimation on RGB-D Frames Using a Deep Point-wise Voting Network
- Patents Phrase to Phrase Semantic Matching Dataset
- A Modified PINN Approach for Identifiable Compartmental Models in Epidemiology with Applications to COVID-19
- Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
- Pose Uncertainty Aware Movement Synchrony Estimation via Spatial-Temporal Graph Transformer
- Hierarchical Reinforcement Learning for Precise Soccer Shooting Skills using a Quadrupedal Robot
- BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
- Global Performance Disparities Between English-Language Accents in Automatic Speech Recognition
- Interpretable Time Series Clustering Using Local Explanations
- Mitigating Shadows in Lidar Scan Matching using Spherical Voxels
- A Feasibility Study on Image Inpainting for Non-cleft Lip Generation from Patients with Cleft Lip
- Boosted Off-Policy Learning
- Short-term Load Forecasting with Distributed Long Short-Term Memory
- SampleMatch: Drum Sample Retrieval by Musical Context
- Exploring the GLIDE model for Human Action-effect Prediction
- Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization
- Accelerated and interpretable oblique random survival forests
- Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning
- On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel
- VacciNet: Towards a Smart Framework for Learning the Distribution Chain Optimization of Vaccines for a Pandemic
- Dyadic Movement Synchrony Estimation Under Privacy-preserving Conditions
- Parsimonious Argument Annotations for Hate Speech Counter-narratives
- Efficient Personalized Learning for Wearable Health Applications using HyperDimensional Computing
- EBOCA: Evidences for BiOmedical Concepts Association Ontology
- A knee cannot have lung disease: out-of-distribution detection with in-distribution voting using the medical example of chest X-ray classification
- What Can Transformers Learn In-Context? A Case Study of Simple Function Classes
- ASTA: Learning Analytical Semantics over Tables for Intelligent Data Analysis and Visualization
- Voice Analysis for Stress Detection and Application in Virtual Reality to Improve Public Speaking in Real-time: A Review
- CircuitNet: An Open-Source Dataset for Machine Learning Applications in Electronic Design Automation (EDA)
- SMART: Sentences as Basic Units for Text Evaluation
- On the Limitations of Sociodemographic Adaptation with Transformers
- Massively Multilingual Lexical Specialization of Multilingual Transformers
- Robust Change Detection Based on Neural Descriptor Fields
- Few-shot Adaptation Works with UnpredicTable Data
- Multi-Document Summarization with Centroid-Based Pretraining
- What Can Be Learnt With Wide Convolutional Neural Networks?
- MULTIPAR: Supervised Irregular Tensor Factorization with Multi-task Learning
- Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning
- Information Gain Sampling for Active Learning in Medical Image Classification
- A penalized two-pass regression to predict stock returns with time-varying risk premia
- Probabilistic forecasts of extreme heatwaves using convolutional neural networks in a regime of lack of data
- Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification
- FrOoDo: Framework for Out-of-Distribution Detection
- An adjoint-free algorithm for conditional nonlinear optimal perturbations (CNOPs) via sampling
- Large-Scale Product Retrieval with Weakly Supervised Representation Learning
- Visual Interpretable and Explainable Deep Learning Models for Brain Tumor MRI and COVID-19 Chest X-ray Images
- Fast Two-step Blind Optical Aberration Correction
- VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations
- Motion-aware Memory Network for Fast Video Salient Object Detection
- DoF-NeRF: Depth-of-Field Meets Neural Radiance Fields
- Video Question Answering with Iterative Video-Text Co-Tokenization
- Masader Plus: A New Interface for Exploring +500 Arabic NLP Datasets
- giMLPs: Gate with Inhibition Mechanism in MLPs
- OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images
- Graphical Representations for Algebraic Constraints of Linear Structural Equations Models
- AdaWCT: Adaptive Whitening and Coloring Style Injection
- Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
- Effective Gesture Based Framework for Capturing User Input
- Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem
- Revisiting Information Cascades in Online Social Networks
- Retrieval of surgical phase transitions using reinforcement learning
- Joint covariate-alignment and concept-alignment: a framework for domain generalization
- Towards Computing an Optimal Abstraction for Structural Causal Models
- Computer vision-based analysis of buildings and built environments: A systematic review of current approaches
- Physics-informed Machine Learning of Parameterized Fundamental Diagrams
- S2Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning
- Suggestion Lists vs. Continuous Generation: Interaction Design for Writing with Generative Models on Mobile Devices Affect Text Length, Wording and Perceived Authorship
- Attacking Adversarial Defences by Smoothing the Loss Landscape
- Learning from flowsheets: A generative transformer model for autocompletion of flowsheets
- ATCA: an Arc Trajectory Based Model with Curvature Attention for Video Frame Interpolation
- DeFL: Decentralized Weight Aggregation for Cross-silo Federated Learning
- MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild
- Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards
- Safe Perception -- A Hierarchical Monitor Approach
- Locally Supervised Learning with Periodic Global Guidance
- Learning to Grasp on the Moon from 3D Octree Observations with Deep Reinforcement Learning
- DSLA: Dynamic smooth label assignment for efficient anchor-free object detection
- Dynamic Batch Adaptation
- Gradient-descent quantum process tomography by learning Kraus operators
- Neural network layers as parametric spans
- GANDSE: Generative Adversarial Network based Design Space Exploration for Neural Network Accelerator Design
- Jazz Contrafact Detection
- Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search
- See What the Robot Can't See: Learning Cooperative Perception for Visual Navigation
- Mitigating Off-Policy Bias in Actor-Critic Methods with One-Step Q-learning: A Novel Correction Approach
- Data Collection and Analysis of French Dialects
- CSDN: Cross-modal Shape-transfer Dual-refinement Network for Point Cloud Completion
- Efficient Long-Text Understanding with Short-Text Models
All 140
- e-Genia3 An AgentSpeak extension for empathic agents
- Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling
- Fair Division of Multi-layered Cakes
- Fashion Recommendation Based on Style and Social Events
- Graph Neural Network with Local Frame for Molecular Potential Energy Surface
- TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation
- Cross Attention Based Style Distribution for Controllable Person Image Synthesis
- Generative Bias for Robust Visual Question Answering
- Local Perception-Aware Transformer for Aerial Tracking
- Model-based graph reinforcement learning for inductive traffic signal control
- SiamixFormer: a fully-transformer Siamese network with temporal Fusion for accurate building detection and change detection in bi-temporal remote sensing images
- De-biased Representation Learning for Fairness with Unreliable Labels
- UniToBrain dataset: a Brain Perfusion Dataset
- An Evidential Neural Network Model for Regression Based on Random Fuzzy Numbers
- Lung nodules segmentation from CT with DeepHealth toolkit
- Dress Well via Fashion Cognitive Learning
- Composable Text Controls in Latent Space with ODEs
- Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing
- DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learning
- Multi-spectral Vehicle Re-identification with Cross-directional Consistency Network and a High-quality Benchmark
- XOOD: Extreme Value Based Out-Of-Distribution Detection For Image Classification
- A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and Retrieval
- Quality Evaluation of Arbitrary Style Transfer: Subjective Study and Objective Metric
- Software Package for Automated Analysis of Lung Ultrasound Videos
- Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism
- Accurate Polygonal Mapping of Buildings in Satellite Imagery
- Beyond kNN: Adaptive, Sparse Neighborhood Graphs via Optimal Transport
- Weighted Scaling Approach for Metabolomics Data Analysis
- A Real-time Edge-AI System for Reef Surveys
- Breast Cancer Classification Based on Histopathological Images Using a Deep Learning Capsule Network
- Long Short-Term Preference Modeling for Continuous-Time Sequential Recommendation
- A Particle-Based Algorithm for Distributional Optimization on textitConstrained Domains via Variational Transport and Mirror Descent
- An Enhanced Deep Learning Technique for Prostate Cancer Identification Based on MRI Scans
- Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization
- CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation
- Quantum Adaptive Fourier Features for Neural Density Estimation
- AvatarGen: a 3D Generative Model for Animatable Human Avatars
- Evo* 2022 -- Late-Breaking Abstracts Volume
- Search for or Navigate to? Dual Adaptive Thinking for Object Navigation
- Unifying Approaches in Active Learning and Active Sampling via Fisher Information and Information-Theoretic Quantities