Papers
Wed 19 Jan 2022
126 papers
- Hybrid Reinforcement Learning-Based Eco-Driving Strategy for Connected and Automated Vehicles at Signalized IntersectionsEnd-to-end autonomous driving → Cooperative and V2X driving
- Improving Behavioural Cloning with Human-Driven Dynamic Dataset AugmentationOffline RL and imitation learning from data → Imitation learning methods
- Battle royale optimizer with a new movement strategy
- Artificial Intelligence Powered Material Search Engine
- Introduction to The Dynamic Pickup and Delivery Problem Benchmark -- ICAPS 2021 Competition
- Predicting The Stock Trend Using News Sentiment Analysis and Technical Indicators in Spark
- Online POI Recommendation: Learning Dynamic Geo-Human Interactions in Streams
- Roadmap for Cybersecurity in Autonomous Vehicles
- Bayesian Inference with Nonlinear Generative Models: Comments on Secure Learning
- Reinforcement Learning Textbook
- A Review of Deep Transfer Learning and Recent Advancements
- Analyzing Multispectral Satellite Imagery of South American Wildfires Using Deep Learning
- An Ensemble Model for Face Liveness Detection
- Signal Strength and Noise Drive Feature Preference in CNN Image Classifiers
- GAP-Gen: Guided Automatic Python Code Generation
- Towards Energy Efficient Distributed Federated Learning for 6G Networks
- Similarity search on neighbor's graphs with automatic Pareto optimal performance and minimum expected quality setups based on hyperparameter optimization
- PROMPT: Learning Dynamic Resource Allocation Policies for Network Applications
- Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization
- The Role of Facial Expressions and Emotion in ASL
- CPTAM: Constituency Parse Tree Aggregation Method
- Evaluating Machine Common Sense via Cloze Testing
- ASL Video Corpora & Sign Bank: Resources Available through the American Sign Language Linguistic Research Project (ASLLRP)
- Enhanced Performance of Pre-Trained Networks by Matched Augmentation Distributions
- PDE-Based Optimal Strategy for Unconstrained Online Learning
- Unsupervised Personalization of an Emotion Recognition System: The Unique Properties of the Externalization of Valence in Speech
- ROS georegistration: Aerial Multi-spectral Image Simulator for the Robot Operating System
- Decoupling the Depth and Scope of Graph Neural Networks
- Potential sources of dataset bias complicate investigation of underdiagnosis by machine learning algorithms
- Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework
- Critic Algorithms using Cooperative Networks
- Correlated-informed neural networks: a new machine learning framework to predict pressure drop in micro-channels
- BLINC: Lightweight Bimodal Learning for Low-Complexity VVC Intra Coding
- Building a Performance Model for Deep Learning Recommendation Model Training on GPUs
- A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts
- ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
- Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation
- Towards a General Deep Feature Extractor for Facial Expression Recognition
- Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation
- Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
- When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Data
- A pipeline for automated processing of Corona KH-4 (1962-1972) stereo imagery
- Deep Capsule Encoder-Decoder Network for Surrogate Modeling and Uncertainty Quantification
- Improving Biomedical Information Retrieval with Neural Retrievers
- SCOTCH: An Efficient Secure Computation Framework for Secure Aggregation
- Data-to-Value: An Evaluation-First Methodology for Natural Language Projects
- Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets
- Enhancing the Security & Privacy of Wearable Brain-Computer Interfaces
- Debiased Graph Neural Networks with Agnostic Label Selection Bias
- Object Detection in Autonomous Vehicles: Status and Open Challenges
- GEMEL: Model Merging for Memory-Efficient, Real-Time Video Analytics at the Edge
- Q-ViT: Fully Differentiable Quantization for Vision Transformer
- Anytime PSRO for Two-Player Zero-Sum Games
- Visualization and Analysis of Wearable Health Data From COVID-19 Patients
- GroupGazer: A Tool to Compute the Gaze per Participant in Groups with integrated Calibration to Map the Gaze Online to a Screen or Beamer Projection
- On the Complexity of a Practical Primal-Dual Coordinate Method
- Coupled Support Tensor Machine Classification for Multimodal Neuroimaging Data
- Learning to Rank For Push Notifications Using Pairwise Expected Regret
- Tiny, always-on and fragile: Bias propagation through design choices in on-device machine learning workflows
- Code Sophistication: From Code Recommendation to Logic Recommendation
- Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts
- Semi-automatic 3D Object Keypoint Annotation and Detection for the Masses
- Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning
- Multiblock ADMM for nonsmooth nonconvex optimization with nonlinear coupling constraints
- A Survey on Training Challenges in Generative Adversarial Networks for Biomedical Image Analysis
- Problem examination for AI methods in product design
- FAT: An In-Memory Accelerator with Fast Addition for Ternary Weight Neural Networks
- CAST: Character labeling in Animation using Self-supervision by Tracking
- Uncovering More Shallow Heuristics: Probing the Natural Language Inference Capacities of Transformer-Based Pre-Trained Language Models Using Syllogistic Patterns
- ReGNL: Rapid Prediction of GDP during Disruptive Events using Nightlights
- Nonlinear Unknown Input Observability and Unknown Input Reconstruction: The General Analytical Solution
- A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo
- Near-Optimal Sparse Allreduce for Distributed Deep Learning
- Real-time Recognition of Yoga Poses using computer Vision for Smart Health Care
- RAMANMETRIX: a delightful way to analyze Raman spectra
- DMF-Net: Dual-Branch Multi-Scale Feature Fusion Network for copy forgery identification of anti-counterfeiting QR code
- Models for information propagation on graphs
- Superpixel Pre-Segmentation of HER2 Slides for Efficient Annotation
- Batch versus Sequential Active Learning for Recommender Systems
- Stability of Deep Neural Networks via discrete rough paths
- Learned Cone-Beam CT Reconstruction Using Neural Ordinary Differential Equations
- Simpler is better: spectral regularization and up-sampling techniques for variational autoencoders
- Virtual Coil Augmentation Technology for MR Coil Extrapolation via Deep Learning
- Writing about COVID-19 vaccines: Emotional profiling unravels how mainstream and alternative press framed AstraZeneca, Pfizer and vaccination campaigns
- Graph Neural Network-based Android Malware Classification with Jumping Knowledge
- Educational Timetabling: Problems, Benchmarks, and State-of-the-Art Results
- CM3: A Causal Masked Multimodal Model of the Internet
- Privacy-Aware Human Mobility Prediction via Adversarial Networks
- Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
- Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree Species Classification Based on Explanation Methods
- POPPINS : A Population-Based Digital Spiking Neuromorphic Processor with Integer Quadratic Integrate-and-Fire Neurons
- Development of Fake News Model using Machine Learning through Natural Language Processing
- High-fidelity 3D Model Compression based on Key Spheres
- Mixed Nondeterministic-Probabilistic Automata: Blending graphical probabilistic models with nondeterminism
- Cortical lesions, central vein sign, and paramagnetic rim lesions in multiple sclerosis: emerging machine learning techniques and future avenues
- PT4AL: Using Self-Supervised Pretext Tasks for Active Learning
- Interpretable Learned Emergent Communication for Human-Agent Teams
- TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning
- TourBERT: A pretrained language model for the tourism industry
- Hiding Data in Colors: Secure and Lossless Deep Image Steganography via Conditional Invertible Neural Networks
All 126
- On the Convergence Rates of Policy Gradient Methods
- Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
- Interpreting Arabic Transformer Models
- Variable Augmented Network for Invertible MR Coil Compression
- Lifted Primal-Dual Method for Bilinearly Coupled Smooth Minimax Optimization
- WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking
- Many Ways to Be Lonely: Fine-Grained Characterization of Loneliness and Its Potential Changes in COVID-19
- Self-Supervised Deep Blind Video Super-Resolution
- Cross-Language Binary-Source Code Matching with Intermediate Representations
- Poseur: Direct Human Pose Regression with Transformers
- Dual Space Graph Contrastive Learning
- Fooling MOSS Detection with Pretrained Language Models
- Compressed Smooth Sparse Decomposition
- Flexible Parallel Learning in Edge Scenarios: Communication, Computational and Energy Cost
- Multiway Spherical Clustering via Degree-Corrected Tensor Block Models
- Ordinal Causal Discovery
- Overview frequency principle/spectral bias in deep learning
- KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition
- Variational Autoencoder Generative Adversarial Network for Synthetic Data Generation in Smart Home
- Swin-Pose: Swin Transformer Based Human Pose Estimation
- Online Deep Learning based on Auto-Encoder
- Unveiling Project-Specific Bias in Neural Code Models
- Prospective Learning: Principled Extrapolation to the Future
- The Role of Pleura and Adipose in Lung Ultrasound AI
- TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval
- Improving Neural Machine Translation by Denoising Training