Papers
Tue 21 Dec 2021
139 papers
- Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research DirectionsEnd-to-end autonomous driving → End-to-end system architecture
- Data driven design of optical resonators
- Multimodal Entity Tagging with Multimodal Knowledge Base
- Validation and Transparency in AI systems for pharmacovigilance: a case study applied to the medical literature monitoring of adverse events
- CausalMTA: Eliminating the User Confounding Bias for Causal Multi-touch Attribution
- A Survey on Using Gaze Behaviour for Natural Language Processing
- An Ontological Knowledge Representation for Smart Agriculture
- Explainable Medical Imaging AI Needs Human-Centered Design: Guidelines and Evidence from a Systematic Review
- Preprocessing in Inductive Logic Programming
- Combining Minkowski and Chebyshev: New distance proposal and survey of distance metrics using k-nearest neighbours classifier
- Crash Data Augmentation Using Conditional Generative Adversarial Networks (CGAN) for Improving Safety Performance Functions
- Morphological classifiers
- Input-Specific Robustness Certification for Randomized Smoothing
- Faster Convergence in Multi-Objective Optimization Algorithms Based on Decomposition
- Learning Positional Embeddings for Coordinate-MLPs
- Anomaly Clustering: Grouping Images into Coherent Clusters of Anomaly Types
- Practical Active Learning with Model Selection for Small Data
- Distribution-aware Margin Calibration for Semantic Segmentation in Images
- Decompose the Sounds and Pixels, Recompose the Events
- Real-time Street Human Motion Capture
- MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation
- Teacher-Student Architecture for Mixed Supervised Lung Tumor Segmentation
- Noise-injected analog Ising machines enable ultrafast statistical sampling and machine learning
- Off Environment Evaluation Using Convex Risk Minimization
- The Phonetic Footprint of Parkinson's Disease
- Multiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
- Sentence Embeddings and High-speed Similarity Search for Fast Computer Assisted Annotation of Legal Documents
- Adversarial Neural Networks for Error Correcting Codes
- Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
- On-the-fly Resource-Aware Model Aggregation for Federated Learning in Heterogeneous Edge
- Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies
- GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping
- Max-Margin Contrastive Learning
- Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confounding
- Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix
- Learned Queries for Efficient Local Attention
- Machine Learning Emulation of Urban Land Surface Processes
- StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation
- Covert Communications via Adversarial Machine Learning and Reconfigurable Intelligent Surfaces
- Offloading Algorithms for Maximizing Inference Accuracy on Edge Device Under a Time Constraint
- Toward Explainable AI for Regression Models
- ADJUST: A Dictionary-Based Joint Reconstruction and Unmixing Method for Spectral Tomography
- NN2Poly: A polynomial representation for deep feed-forward artificial neural networks
- Voice Quality and Pitch Features in Transformer-Based Speech Recognition
- Supervised Graph Contrastive Pretraining for Text Classification
- A novel approach for the automated segmentation and volume quantification of cardiac fats on computed tomography
- Shape from Polarization for Complex Scenes in the Wild
- Deep Learning and Earth Observation to Support the Sustainable Development Goals
- Contrastive Object Detection Using Knowledge Graph Embeddings
- Reasoning About Causal Models With Infinitely Many Variables
- Multigoal-oriented dual-weighted-residual error estimation using deep neural networks
- Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects
- Transferable End-to-end Room Layout Estimation via Implicit Encoding
- Deep Learning Based 3D Point Cloud Regression for Estimating Forest Biomass
- PrimSeq: a deep learning-based pipeline to quantitate rehabilitation training
- Multispectral image fusion based on super pixel segmentation
- iSegFormer: Interactive Segmentation via Transformers with Application to 3D Knee MR Images
- Physics-informed neural network method for modelling beam-wall interactions
- Deep Learning Based Cloud Cover Parameterization for ICON
- On the Adversarial Robustness of Causal Algorithmic Recourse
- Implicit Neural Video Compression
- Extending CLIP for Category-to-image Retrieval in E-commerce
- Review of Face Presentation Attack Detection Competitions
- VW-SDK: Efficient Convolutional Weight Mapping Using Variable Windows for Processing-In-Memory Architectures
- Differential Parity: Relative Fairness Between Two Sets of Decisions
- High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling
- PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing
- Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling
- Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems
- An ASP-based Approach to Answering Natural Language Questions for Texts
- Preserving gauge invariance in neural networks
- Improving Robustness with Image Filtering
- A next-generation platform for Cyber Range-as-a-Service
- Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients
- Discrete fully probabilistic design: towards a control pipeline for the synthesis of policies from examples
- Contrast and Generation Make BART a Good Dialogue Emotion Recognizer
- Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization
- Task-oriented Dialogue Systems: performance vs. quality-optima, a review
- AutoCTS: Automated Correlated Time Series Forecasting -- Extended Version
- Dynamically Stable Poincar'e Embeddings for Neural Manifolds
- Hierarchical Over-the-Air Federated Edge Learning
- PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
- Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
- FedPOIRec: Privacy Preserving Federated POI Recommendation with Social Influence
- Cloud Sphere: A 3D Shape Representation via Progressive Deformation
- Learning Human Motion Prediction via Stochastic Differential Equations
- GlobalMatch: Registration of Forest Terrestrial Point Clouds by Global Matching of Relative Stem Positions
- Soft Actor-Critic with Cross-Entropy Policy Optimization
- Developing and Validating Semi-Markov Occupancy Generative Models: A Technical Report
- High pressure hydrogen by machine learning and quantum Monte Carlo
- Aerial Base Station Positioning and Power Control for Securing Communications: A Deep Q-Network Approach
- EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection
- Can We Use Neural Regularization to Solve Depth Super-Resolution?
- RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
- Data fission: splitting a single data point
- RC-Net: A Convolutional Neural Network for Retinal Vessel Segmentation
- Explanation of Machine Learning Models Using Shapley Additive Explanation and Application for Real Data in Hospital
- An Inference Approach To Question Answering Over Knowledge Graphs
- Leveraging Image Complexity in Macro-Level Neural Network Design for Medical Image Segmentation
- A Scalable Deep Reinforcement Learning Model for Online Scheduling Coflows of Multi-Stage Jobs for High Performance Computing
All 139
- Predicting Job Titles from Job Descriptions with Multi-label Text Classification
- Geometry-Aware Unsupervised Domain Adaptation
- Distributed Machine Learning and the Semblance of Trust
- SOIT: Segmenting Objects with Instance-Aware Transformers
- ANUBIS: A Provenance Graph-Based Framework for Advanced Persistent Threat Detection
- On Cross-Lingual Retrieval with Multilingual Text Encoders
- More is Less: Inducing Sparsity via Overparameterization
- Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors
- Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions
- Mining Drifting Data Streams on a Budget: Combining Active Learning with Self-Labeling
- A Theoretical View of Linear Backpropagation and Its Convergence
- fMRI Neurofeedback Learning Patterns are Predictive of Personal and Clinical Traits
- MPViT: Multi-Path Vision Transformer for Dense Prediction
- Point spread function estimation for blind image deblurring problems based on framelet transform
- Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition
- Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement
- Mapping industrial poultry operations at scale with deep learning and aerial imagery
- Learned ISTA with Error-based Thresholding for Adaptive Sparse Coding
- Generalized Few-Shot Semantic Segmentation: All You Need is Fine-Tuning
- ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization
- What are Attackers after on IoT Devices? An approach based on a multi-phased multi-faceted IoT honeypot ecosystem and data clustering
- Differentiated uniformization: A new method for inferring Markov chains on combinatorial state spaces including stochastic epidemic models
- Generalizing Interactive Backpropagating Refinement for Dense Prediction
- DRPN: Making CNN Dynamically Handle Scale Variation
- Nonlinear Transform Source-Channel Coding for Semantic Communications
- Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE
- Joint Learning of Linear Time-Invariant Dynamical Systems
- An adaptation of InfoMap to absorbing random walks using absorption-scaled graphs
- Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations
- Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems
- The entropic barrier is n-self-concordant
- Pixel-Stega: Generative Image Steganography Based on Autoregressive Models
- Reinforcement Learning based Sequential Batch-sampling for Bayesian Optimal Experimental Design
- Structured Semantic Transfer for Multi-Label Recognition with Partial Labels
- Watch Those Words: Video Falsification Detection Using Word-Conditioned Facial Motion
- Nearly Optimal Policy Optimization with Stable at Any Time Guarantee
- Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
- DB-BERT: a Database Tuning Tool that "Reads the Manual"
- Provable Hierarchical Lifelong Learning with a Sketch-based Modular Architecture