Papers
Wed 4 Aug 2021
127 papers
- Online Knowledge Distillation for Efficient Pose EstimationKnowledge distillation → Detection and dense prediction distillation
- A Pragmatic Look at Deep Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks
- With One Voice: Composing a Travel Voice Assistant from Re-purposed Models
- Fake News and Phishing Detection Using a Machine Learning Trained Expert System
- SOME/IP Intrusion Detection using Deep Learning-based Sequential Models in Automotive Ethernet Networks
- Combating Informational Denial-of-Service (IDoS) Attacks: Modeling and Mitigation of Attentional Human Vulnerability
- Mitigating harm in language models with conditional-likelihood filtration
- A Machine-Learning-Ready Dataset Prepared from the Solar and Heliospheric Observatory Mission
- A data-driven peridynamic continuum model for upscaling molecular dynamics
- Fairness in Algorithmic Profiling: A German Case Study
- Reproducible Performance Optimization of Complex Applications on the Edge-to-Cloud Continuum
- Operational Learning-based Boundary Estimation in Electromagnetic Medical Imaging
- Incremental learning of LSTM framework for sensor fusion in attitude estimation
- Generalized Tensor Summation Compressive Sensing Network (GTSNET): An Easy to Learn Compressive Sensing Operation
- Stochastic Deep Model Reference Adaptive Control
- Unsupervised Domain Adaptation in Speech Recognition using Phonetic Features
- Optimal Transport for Unsupervised Denoising Learning
- Predicting Post-Concussion Syndrome Outcomes with Machine Learning
- VBridge: Connecting the Dots Between Features and Data to Explain Healthcare Models
- Automatic Detection of COVID-19 Vaccine Misinformation with Graph Link Prediction
- BEANNA: A Binary-Enabled Architecture for Neural Network Acceleration
- Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function
- Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity
- High dimensional Bayesian Optimization Algorithm for Complex System in Time Series
- Machine Learning Classification and Portfolio Construction: Does the Loss Function Matter?
- Pan-Cancer Integrative Histology-Genomic Analysis via Interpretable Multimodal Deep Learning
- Boosting Few-shot Semantic Segmentation with Transformers
- Indoor Localization Under Limited Measurements: A Cross-Environment Joint Semi-Supervised and Transfer Learning Approach
- An Empirical Study of UMLS Concept Extraction from Clinical Notes using Boolean Combination Ensembles
- Attentive Cross-modal Connections for Deep Multimodal Wearable-based Emotion Recognition
- The Impact of Machine Learning on 2D/3D Registration for Image-guided Interventions: A Systematic Review and Perspective
- Dynamic Relevance Learning for Few-Shot Object Detection
- Multi-Branch with Attention Network for Hand-Based Person Recognition
- Unsupervised Detection of Lung Nodules in Chest Radiography Using Generative Adversarial Networks
- Growing an architecture for a neural network
- Terabyte-scale supervised 3D training and benchmarking dataset of the mouse kidney
- Adversarial learning of cancer tissue representations
- Deep multi-task mining Calabi-Yau four-folds
- A FAIR and AI-ready Higgs boson decay dataset
- Spacetime Neural Network for High Dimensional Quantum Dynamics
- Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000× Compression and 3.1× Faster Inference
- A Biologically Plausible Parser
- Enhancing Self-supervised Video Representation Learning via Multi-level Feature Optimization
- Ordered Attention for Coherent Visual Storytelling
- Curriculum learning for language modeling
- Acyclic and Cyclic Reversing Computations in Petri Nets
- Localized Shape Modelling with Global Coherence: An Inverse Spectral Approach
- MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease
- Physics-based Noise Modeling for Extreme Low-light Photography
- Improving Aleatoric Uncertainty Quantification in Multi-Annotated Medical Image Segmentation with Normalizing Flows
- Pervasive Hand Gesture Recognition for Smartphones using Non-audible Sound and Deep Learning
- Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers
- Under the Radar -- Auditing Fairness in ML for Humanitarian Mapping
- Parallelized Reverse Curriculum Generation
- Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus Images
- Deep Portrait Lighting Enhancement with 3D Guidance
- Statistical Analysis of Wasserstein Distributionally Robust Estimators
- FedJAX: Federated learning simulation with JAX
- Hyperparameter-free and Explainable Whole Graph Embedding
- Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
- Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
- Policy Gradients Incorporating the Future
- Human-In-The-Loop Document Layout Analysis
- Free Lunch for Co-Saliency Detection: Context Adjustment
- Auto-encoder based Model for High-dimensional Imbalanced Industrial Data
- The Potential of Using Vision Videos for CrowdRE: Video Comments as a Source of Feedback
- Multi-Round Parsing-based Multiword Rules for Scientific OpenIE
- Stochastic Subgradient Descent Escapes Active Strict Saddles on Weakly Convex Functions
- Discovering outliers in the Mars Express thermal power consumption patterns
- Question-controlled Text-aware Image Captioning
- ICECAP: Information Concentrated Entity-aware Image Captioning
- Convergence of gradient descent for learning linear neural networks
- Random Convolution Kernels with Multi-Scale Decomposition for Preterm EEG Inter-burst Detection
- The MIT Supercloud Dataset
- Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
- Dyn-ASR: Compact, Multilingual Speech Recognition via Spoken Language and Accent Identification
- Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators
- Signature Verification using Geometrical Features and Artificial Neural Network Classifier
- Staged trees and asymmetry-labeled DAGs
- Lung Sound Classification Using Co-tuning and Stochastic Normalization
- Sparse Continuous Distributions and Fenchel-Young Losses
- Core-Stable Committees under Restricted Domains
- Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D
- Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement
- Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection
- Graph Attention Network For Microwave Imaging of Brain Anomaly
- Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning
- Learning Compatible Embeddings
- Log-based Anomaly Detection Without Log Parsing
- MRCpy: A Library for Minimax Risk Classifiers
- Using Interaction Data to Predict Engagement with Interactive Media
- Automatic cerebral hemisphere segmentation in rat MRI with lesions via attention-based convolutional neural networks
- PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
- How to Query Language Models?
- TextCNN with Attention for Text Classification
- An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications to Surface Smoothing and Imaging
- Secure and Privacy-Preserving Federated Learning via Co-Utility
- Internal Video Inpainting by Implicit Long-range Propagation
- Personalized Federated Learning with Clustering: Non-IID Heart Rate Variability Data Application
All 127
- FPB: Feature Pyramid Branch for Person Re-Identification
- Generic Neural Architecture Search via Regression
- High Performance Across Two Atari Paddle Games Using the Same Perceptual Control Architecture Without Training
- A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain
- PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining
- Adaptive Path Planning for UAV-based Multi-Resolution Semantic Segmentation
- Summary Explorer: Visualizing the State of the Art in Text Summarization
- Learning Task Agnostic Skills with Data-driven Guidance
- Specialize and Fuse: Pyramidal Output Representation for Semantic Segmentation
- Reconstructing a dynamical system and forecasting time series by self-consistent deep learning
- Quality Evaluation of the Low-Resource Synthetically Generated Code-Mixed Hinglish Text
- Efficient Neural Architecture Search with Performance Prediction
- Risk Conditioned Neural Motion Planning
- Controlled Text Generation as Continuous Optimization with Multiple Constraints
- Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
- Model-Based Opponent Modeling
- Offline Decentralized Multi-Agent Reinforcement Learning
- Emergent Discrete Communication in Semantic Spaces
- Combining Attention with Flow for Person Image Synthesis
- Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
- Transfer Learning for Pose Estimation of Illustrated Characters
- Video Similarity and Alignment Learning on Partial Video Copy Detection
- Improving Distinction between ASR Errors and Speech Disfluencies with Feature Space Interpolation
- Deep Learning Chromatic and Clique Numbers of Graphs
- Leaf Recognition Using Convolutional Neural Networks Based Features
- On the Robustness of Domain Adaption to Adversarial Attacks
- Neural Scene Decoration from a Single Photograph