Papers
Thu 29 Apr 2021
167 papers
- Adversarial Inverse Reinforcement Learning for Mean Field GamesOffline RL and imitation learning from data → Inverse reinforcement learning
- Using Transformers to Provide Teachers with Personalized Feedback on their Classroom Discourse: The TalkMoves Application
- Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks
- Learning Models for Suicide Prediction from Social Media Posts
- Recognition and Processing of NATOM
- Regularizing Explanations in Bayesian Convolutional Neural Networks
- A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations
- A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features
- Complex-valued Convolutional Neural Networks for Enhanced Radar Signal Denoising and Interference Mitigation
- Hyperspherically Regularized Networks for Self-Supervision
- Transfer Learning on Multi-Fidelity Data
- Emotional Contagion-Aware Deep Reinforcement Learning for Antagonistic Crowd Simulation
- A comparative study of neural network techniques for automatic software vulnerability detection
- Linear Convergence of the Subspace Constrained Mean Shift Algorithm: From Euclidean to Directional Data
- Pyramid Medical Transformer for Medical Image Segmentation
- The Zero Resource Speech Challenge 2021: Spoken language modelling
- Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
- Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses
- Entailment as Few-Shot Learner
- Analysis of Manual and Automated Skin Tone Assignments for Face Recognition Applications
- EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
- Physically Feasible Vehicle Trajectory Prediction
- Search Algorithms for Automated Hyper-Parameter Tuning
- AMR Parsing with Action-Pointer Transformer
- Analytical bounds on the local Lipschitz constants of ReLU networks
- SYNFIX: Automatically Fixing Syntax Errors using Compiler Diagnostics
- Using Meta Reinforcement Learning to Bridge the Gap between Simulation and Experiment in Energy Demand Response
- Lung Cancer Diagnosis Using Deep Attention Based on Multiple Instance Learning and Radiomics
- Turing Completeness and Sid Meier's Civilization
- What is Going on Inside Recurrent Meta Reinforcement Learning Agents?
- AGORA: Avatars in Geography Optimized for Regression Analysis
- Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation
- Modelling Urban Dynamics with Multi-Modal Graph Convolutional Networks
- Text2Video: Text-driven Talking-head Video Synthesis with Personalized Phoneme-Pose Dictionary
- Scalable Semi-supervised Landmark Localization for X-ray Images using Few-shot Deep Adaptive Graph
- Cluster-driven Graph Federated Learning over Multiple Domains
- The Logic of Graph Neural Networks
- AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge
- Learning in Feedforward Neural Networks Accelerated by Transfer Entropy
- D-VAL: An automatic functional equivalence validation tool for planning domain models
- Crack Semantic Segmentation using the U-Net with Full Attention Strategy
- MuyGPs: Scalable Gaussian Process Hyperparameter Estimation Using Local Cross-Validation
- LIDAR and Position-Aided mmWave Beam Selection with Non-local CNNs and Curriculum Training
- Unsupervised Layered Image Decomposition into Object Prototypes
- Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses
- Exemplar-Based 3D Portrait Stylization
- A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
- Learned Spatial Representations for Few-shot Talking-Head Synthesis
- Discover the Unknown Biased Attribute of an Image Classifier
- MongeNet: Efficient Sampler for Geometric Deep Learning
- MarioNette: Self-Supervised Sprite Learning
- Ensembling with Deep Generative Views
- Medium Access using Distributed Reinforcement Learning for IoTs with Low-Complexity Wireless Transceivers
- With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
- NURBS-Diff: A Differentiable Programming Module for NURBS
- Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines
- LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
- AutoFlow: Learning a Better Training Set for Optical Flow
- Optimal training of variational quantum algorithms without barren plateaus
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
- Distributed Multigrid Neural Solvers on Megavoxel Domains
- Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features
- A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection
- On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning
- GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection
- Online certification of preference-based fairness for personalized recommender systems
- Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements
- Brain-inspired computing: We need a master plan
- Constructions in combinatorics via neural networks
- A General Katsuno-Mendelzon-Style Characterization of AGM Belief Base Revision for Arbitrary Monotonic Logics
- An Axiomatic Theory of Provably-Fair Welfare-Centric Machine Learning
- Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation
- Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation
- Towards a practical lip-to-speech conversion system using deep neural networks and mobile application frontend
- 3D Human Action Representation Learning via Cross-View Consistency Pursuit
- Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentation
- MUSE: Multi-faceted Attention for Signed Network Embedding
- Trakhtenbrot's Theorem in Coq: Finite Model Theory through the Constructive Lens
- Improving Simulations with Symmetry Control Neural Networks
- Discriminative-Generative Dual Memory Video Anomaly Detection
- Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra
- Predicate Invention by Learning From Failures
- What Are Bayesian Neural Network Posteriors Really Like?
- Genotype-Guided Radiomics Signatures for Recurrence Prediction of Non-Small-Cell Lung Cancer
- Pre-training of Deep RL Agents for Improved Learning under Domain Randomization
- Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
- Privacy-Preserving Federated Learning on Partitioned Attributes
- PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
- Learning Robust Variational Information Bottleneck with Reference
- MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
- Thermal Infrared Image Colorization for Nighttime Driving Scenes with Top-Down Guided Attention
- A neural anisotropic view of underspecification in deep learning
- Generalized Linear Models with Structured Sparsity Estimators
- Graph-Embedded Subspace Support Vector Data Description
- From Distributed Machine Learning to Federated Learning: A Survey
- Video Salient Object Detection via Adaptive Local-Global Refinement
- Hand Gesture Recognition Based on a Nonconvex Regularization
- ELF-VC: Efficient Learned Flexible-Rate Video Coding
- Hypernetwork Dismantling via Deep Reinforcement Learning
- Adversarial Multi-task Learning Enhanced Physics-informed Neural Networks for Solving Partial Differential Equations
All 167
- MOROCCO: Model Resource Comparison Framework
- Differentiable model-based adaptive optics for two-photon microscopy
- End-to-End Speech Recognition from Federated Acoustic Models
- Emerging Properties in Self-Supervised Vision Transformers
- Meta-learning using privileged information for dynamics
- Uncertainty Principles in Risk-Aware Statistical Estimation
- VIRDOCD: a VIRtual DOCtor to Predict Dengue Fatality
- Leveraging Online Shopping Behaviors as a Proxy for Personal Lifestyle Choices: New Insights into Chronic Disease Prevention Literacy
- Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization
- How (Non-)Optimal is the Lexicon?
- ReLearn: A Robust Machine Learning Framework in Presence of Missing Data for Multimodal Stress Detection from Physiological Signals
- A Rigid Registration Method in TEVAR
- Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks
- A block-sparse Tensor Train Format for sample-efficient high-dimensional Polynomial Regression
- TabAug: Data Driven Augmentation for Enhanced Table Structure Recognition
- Learning Multi-Attention Context Graph for Group-Based Re-Identification
- Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
- A Study into patient similarity through representation learning from medical records
- InsertionNet -- A Scalable Solution for Insertion
- Privacy-Preserving Portrait Matting
- FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
- Using Fisher's Exact Test to Evaluate Association Measures for N-grams
- Segmentation-grounded Scene Graph Generation
- ELSD: Efficient Line Segment Detector and Descriptor
- Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation
- Bayesian Deep Neural Networks for Supervised Learning of Single-View Depth
- Learning Heterogeneous Temporal Patterns of User Preference for Timely Recommendation
- Variable-Length Codes Independent or Closed with respect to Edit Relations
- Fine-grained Generalization Analysis of Vector-valued Learning
- Using Adaptive Gradient for Texture Learning in Single-View 3D Reconstruction
- Radar-based Automotive Localization using Landmarks in a Multimodal Sensor Graph-based Approach
- RECKONition: a NLP-based system for Industrial Accidents at Work Prevention
- Adapting to Reward Progressivity via Spectral Reinforcement Learning
- Action Unit Memory Network for Weakly Supervised Temporal Action Localization
- Stable Online Control of Linear Time-Varying Systems
- Text-to-Text Multi-view Learning for Passage Re-ranking
- Generalization Guarantees for Neural Architecture Search with Train-Validation Split
- Actor-centered Representations for Action Localization in Streaming Videos
- Locality Constrained Analysis Dictionary Learning via K-SVD Algorithm
- ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
- CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications
- Hardware Architecture of Embedded Inference Accelerator and Analysis of Algorithms for Depthwise and Large-Kernel Convolutions
- Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps
- An efficient scheme based on graph centrality to select nodes for training for effective learning
- Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling
- REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter
- An Automated Approach for Timely Diagnosis and Prognosis of Coronavirus Disease
- Regret Bounds for Gaussian-Process Optimization in Large Domains
- Decoupled Dynamic Filter Networks
- Comparing Visual Reasoning in Humans and AI
- Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners
- A Normal Form Characterization for Efficient Boolean Skolem Function Synthesis
- Analyzing the Nuances of Transformers' Polynomial Simplification Abilities
- Feasibility-based Fixed Point Networks
- Collaborative Human-Agent Planning for Resilience
- Connecting AI Learning and Blockchain Mining in 6G Systems
- Bridge to Answer: Structure-aware Graph Interaction Network for Video Question Answering
- Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection
- Maneuver-Aware Pooling for Vehicle Trajectory Prediction
- Statistical Inference with M-Estimators on Adaptively Collected Data
- Applications of Artificial Intelligence to aid detection of dementia: a narrative review on current capabilities and future directions
- Nonlinear Level Set Learning for Function Approximation on Sparse Data with Applications to Parametric Differential Equations
- Improving Fairness in Speaker Recognition
- Objects as Extreme Points
- WGCN: Graph Convolutional Networks with Weighted Structural Features
- Machine Learning Techniques for Software Quality Assurance: A Survey
- Continuous Decoding of Daily-Life Hand Movements from Forearm Muscle Activity for Enhanced Myoelectric Control of Hand Prostheses