Papers
Thu 1 Jul 2021
180 papers
- Inverse Reinforcement Learning Based Stochastic Driver Behavior LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
- Variational Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-EnsembleOffline RL and imitation learning from data → Offline RL algorithms
- Knowledge Distillation for Quality EstimationKnowledge distillation → Knowledge distillation for LLMs
- Social Coordination and Altruism in Autonomous DrivingEnd-to-end autonomous driving → Cooperative and V2X driving
- Revisiting Knowledge Distillation: An Inheritance and Exploration FrameworkKnowledge distillation → General knowledge distillation methods
- Elbert: Fast Albert with Confidence-Window Based Early ExitEfficient LLM inference and serving → Early exit and edge inference
- Deep Learning for Breast Cancer Classification: Enhanced Tangent Function
- Prediction of the final rank of Players in PUBG with the optimal number of features
- Machine Learning-Based Analysis of Free-Text Keystroke Dynamics
- Free-Text Keystroke Dynamics for User Authentication
- A Review on Edge Analytics: Issues, Challenges, Opportunities, Promises, Future Directions, and Applications
- Modelling Neuronal Behaviour with Time Series Regression: Recurrent Neural Networks on C. Elegans Data
- Forecasting Thermoacoustic Instabilities in Liquid Propellant Rocket Engines Using Multimodal Bayesian Deep Learning
- Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction
- A Decision Support System for Safer Airplane Landings: Predicting Runway Conditions Using XGBoost and Explainable AI
- Strategy Complexity of Mean Payoff, Total Payoff and Point Payoff Objectives in Countable MDPs
- Bi-Level Poisoning Attack Model and Countermeasure for Appliance Consumption Data of Smart Homes
- Quality Metrics for Transparent Machine Learning With and Without Humans In the Loop Are Not Correlated
- Tackling COVID-19 Infodemic using Deep Learning
- Interactive Causal Structure Discovery in Earth System Sciences
- Molecular distance matrix prediction based on graph convolutional networks
- Microgrid management with weather-based forecasting of energy generation, consumption and prices
- Design and implementation of an islanded hybrid microgrid system for a large resort center for Penang Island with the proper application of excess energy
- Almost Tight Approximation Algorithms for Explainable Clustering
- Autonomous Navigation for Quadrupedal Robots with Optimized Jumping through Constrained Obstacles
- Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking
- Enhancing Multi-Robot Perception via Learned Data Association
- On the Bike Spreading Problem
- The Spotlight: A General Method for Discovering Systematic Errors in Deep Learning Models
- An Investigation of the (In)effectiveness of Counterfactually Augmented Data
- Proof of the impossibility of probabilistic induction
- q-Paths: Generalizing the Geometric Annealing Path using Power Means
- Flow-based sampling for multimodal and extended-mode distributions in lattice field theory
- EMG-Based Feature Extraction and Classification for Prosthetic Hand Control
- Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
- Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation
- Neural Task Success Classifiers for Robotic Manipulation from Few Real Demonstrations
- SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
- Passing a Non-verbal Turing Test: Evaluating Gesture Animations Generated from Speech
- Long-Short Ensemble Network for Bipolar Manic-Euthymic State Recognition Based on Wrist-worn Sensors
- Blind Image Super-Resolution via Contrastive Representation Learning
- Intrinsic Image Transfer for Illumination Manipulation
- Distilling Reinforcement Learning Tricks for Video Games
- Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows
- Inter-Beat Interval Estimation with Tiramisu Model: A Novel Approach with Reduced Error
- Interactive decoding of words from visual speech recognition models
- Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization
- Aerial Map-Based Navigation Using Semantic Segmentation and Pattern Matching
- Gap-Dependent Bounds for Two-Player Markov Games
- Active Learning of Abstract Plan Feasibility
- A Map of Bandits for E-commerce
- A Primer on Pretrained Multilingual Language Models
- Shared Data and Algorithms for Deep Learning in Fundamental Physics
- CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
- AutoFormer: Searching Transformers for Visual Recognition
- CLIP-It! Language-Guided Video Summarization
- On the Practicality of Deterministic Epistemic Uncertainty
- Deep Orthogonal Fusion: Multimodal Prognostic Biomarker Discovery Integrating Radiology, Pathology, Genomic, and Clinical Data
- Learning to See before Learning to Act: Visual Pre-training for Manipulation
- Global Filter Networks for Image Classification
- Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
- Mandoline: Model Evaluation under Distribution Shift
- Focal Self-attention for Local-Global Interactions in Vision Transformers
- Generalization and Robustness Implications in Object-Centric Learning
- ESPnet-ST IWSLT 2021 Offline Speech Translation System
- StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR
- Semi-Sparsity for Smoothing Filters
- Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks
- Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
- A Unified Framework of Bundle Adjustment and Feature Matching for High-Resolution Satellite Images
- Multimodal Graph-based Transformer Framework for Biomedical Relation Extraction
- Fast Margin Maximization via Dual Acceleration
- Pretext Tasks selection for multitask self-supervised speech representation learning
- Disaggregated Interventions to Reduce Inequality
- Individual Tree Detection and Crown Delineation with 3D Information from Multi-view Satellite Images
- 3D Iterative Spatiotemporal Filtering for Classification of Multitemporal Satellite Data Sets
- Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation
- Learning Large DAGs by Combining Continuous Optimization and Feedback Arc Set Heuristics
- Hippocampal Spatial Mapping As Fast Graph Learning
- Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
- Improving Human Motion Prediction Through Continual Learning
- Goal-Conditioned Reinforcement Learning with Imagined Subgoals
- The Limit Order Book Recreation Model (LOBRM): An Extended Analysis
- Towards a fairer reimbursement system for burn patients using cost-sensitive classification
- Visualising Argumentation Graphs with Graph Embeddings and t-SNE
- Automatic Metadata Extraction Incorporating Visual Features from Scanned Electronic Theses and Dissertations
- Machine Learning and Deep Learning for Fixed-Text Keystroke Dynamics
- Secure Quantized Training for Deep Learning
- On the detection-to-track association for online multi-object tracking
- Differentiable Particle Filters through Conditional Normalizing Flow
- VideoLightFormer: Lightweight Action Recognition using Transformers
- CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding
- What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis
- Overhead-MNIST: Machine Learning Baselines for Image Classification
- Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation
- Language-Level Semantics Conditioned 3D Point Cloud Segmentation
- Neural Network Training with Highly Incomplete Datasets
- Online learning of windmill time series using Long Short-term Cognitive Networks
- Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction
All 180
- Machine learning based iterative learning control for non-repetitive time-varying systems
- CBNet: A Composite Backbone Network Architecture for Object Detection
- Supervised Segmentation with Domain Adaptation for Small Sampled Orbital CT Images
- DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks
- MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label setting
- CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor
- Lossless Coding of Point Cloud Geometry using a Deep Generative Model
- MIDV-2020: A Comprehensive Benchmark Dataset for Identity Document Analysis
- GlyphCRM: Bidirectional Encoder Representation for Chinese Character with its Glyph
- Explainable nonlinear modelling of multiple time series with invertible neural networks
- Morphological classification of compact and extended radio galaxies using convolutional neural networks and data augmentation techniques
- SSC: Semantic Scan Context for Large-Scale Place Recognition
- On the Expected Complexity of Maxout Networks
- Evidence for Long-Tails in SLS Algorithms
- PlanSys2: A Planning System Framework for ROS2
- Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring
- Sparse GCA and Thresholded Gradient Descent
- Computing CQ lower-bounds over OWL 2 through approximation to RSA
- Ensemble Learning-Based Approach for Improving Generalization Capability of Machine Reading Comprehension Systems
- A Consistency-Based Loss for Deep Odometry Through Uncertainty Propagation
- Implicit Acceleration and Feature Learning in Infinitely Wide Neural Networks with Bottlenecks
- Valid prediction intervals for regression problems
- Drone swarm patrolling with uneven coverage requirements
- Towards Measuring Bias in Image Classification
- Model Mediated Teleoperation with a Hand-Arm Exoskeleton in Long Time Delays Using Reinforcement Learning
- Cross-domain Few-shot Learning with Task-specific Adapters
- Reparameterized Sampling for Generative Adversarial Networks
- MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding
- Policy Transfer across Visual and Dynamics Domain Gaps via Iterative Grounding
- PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
- Modeling Target-side Inflection in Placeholder Translation
- Multilingual Central Repository: a Cross-lingual Framework for Developing Wordnets
- End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization
- Orthonormal Product Quantization Network for Scalable Face Image Retrieval
- Combining Feature and Instance Attribution to Detect Artifacts
- Zero-pronoun Data Augmentation for Japanese-to-English Translation
- Towards Utilitarian Combinatorial Assignment with Deep Neural Networks and Heuristic Algorithms
- Leveraging Domain Agnostic and Specific Knowledge for Acronym Disambiguation
- Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems
- Adversarial Sample Detection for Speaker Verification by Neural Vocoders
- An Objective Evaluation Framework for Pathological Speech Synthesis
- MHER: Model-based Hindsight Experience Replay
- Explainable Diabetic Retinopathy Detection and Retinal Image Generation
- iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis
- SA-MATD3:Self-attention-based multi-agent continuous control method in cooperative environments
- DivergentNets: Medical Image Segmentation by Network Ensemble
- Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation
- The USTC-NELSLIP Systems for Simultaneous Speech Translation Task at IWSLT 2021
- A Survey on Graph-Based Deep Learning for Computational Histopathology
- AdaXpert: Adapting Neural Architecture for Growing Data
- OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
- The Interplay between Distribution Parameters and the Accuracy-Robustness Tradeoff in Classification
- Preconditioning for Scalable Gaussian Process Hyperparameter Optimization
- Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
- Optimal Power Allocation for Rate Splitting Communications with Deep Reinforcement Learning
- Feasibility of Haralick's Texture Features for the Classification of Chromogenic In-situ Hybridization Images
- FedMix: Approximation of Mixup under Mean Augmented Federated Learning
- Audiovisual Singing Voice Separation
- Boosting Certified ℓ_∞ Robustness with EMA Method and Ensemble Model
- E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth Perception
- Scalable Certified Segmentation via Randomized Smoothing
- Exponential Lower Bounds for Threshold Circuits of Sub-Linear Depth and Energy
- Deep auxiliary learning for visual localization using colorization task
- ControlBurn: Feature Selection by Sparse Forests
- Multi-modal Graph Learning for Disease Prediction
- Markov Decision Process modeled with Bandits for Sequential Decision Making in Linear-flow
- Few-Shot Learning with a Strong Teacher
- Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
- Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection
- Capturing Event Argument Interaction via A Bi-Directional Entity-Level Recurrent Decoder
- Context-aware Execution Migration Tool for Data Science Jupyter Notebooks on Hybrid Clouds
- Word-Free Spoken Language Understanding for Mandarin-Chinese
- Bilinear Scoring Function Search for Knowledge Graph Learning
- Distributed Nonparametric Function Estimation: Optimal Rate of Convergence and Cost of Adaptation
- Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards
- Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
- The Use of Bandit Algorithms in Intelligent Interactive Recommender Systems
- Cross-Lingual Transfer Learning for Statistical Type Inference
- A Study of the Quality of Wikidata
- Controllable Open-ended Question Generation with A New Question Type Ontology