Papers
Thu 3 Mar 2022
203 papers
- Reasoning about Counterfactuals to Improve Human Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical EfficiencyOffline RL and imitation learning from data → Offline RL algorithms
- Testing Stationarity and Change Point Detection in Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Fail-Safe Adversarial Generative Imitation LearningOffline RL and imitation learning from data → Imitation learning methods
- A Simple Hash-Based Early Exiting Approach For Language Understanding and GenerationEfficient LLM inference and serving → Early exit and edge inference
- Distantly Supervised Named Entity Recognition via Confidence-Based Multi-Class Positive and Unlabeled Learning
- Automatic Text Summarization Methods: A Comprehensive Review
- Optical Flow Based Motion Detection for Autonomous Driving
- Panoptic segmentation with highly imbalanced semantic labels
- Transfer Dynamics in Emergent Evolutionary Curricula
- Uncertainty with UAV Search of Multiple Goal-oriented Targets
- Polar Transformation Based Multiple Instance Learning Assisting Weakly Supervised Image Segmentation With Loose Bounding Box Annotations
- Bilateral Deep Reinforcement Learning Approach for Better-than-human Car Following Model
- SIERRA: A Modular Framework for Research Automation
- A New Era: Intelligent Tutoring Systems Will Transform Online Learning for Millions
- Automated Single-Label Patent Classification using Ensemble Classifiers
- Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey
- Attention-based Region of Interest (ROI) Detection for Speech Emotion Recognition
- Improvements to Gradient Descent Methods for Quantum Tensor Network Machine Learning
- Evolving symbolic density functionals
- ARM 4-BIT PQ: SIMD-based Acceleration for Approximate Nearest Neighbor Search on ARM
- Intrinsically-Motivated Reinforcement Learning: A Brief Introduction
- A photonic chip-based machine learning approach for the prediction of molecular properties
- Nuclei instance segmentation and classification in histopathology images with StarDist
- A Comprehensive Review of Computer Vision in Sports: Open Issues, Future Trends and Research Directions
- Sim2Real Instance-Level Style Transfer for 6D Pose Estimation
- Interpretable Latent Variables in Deep State Space Models
- Symmetry Structured Convolutional Neural Networks
- Deep Latent-Variable Models for Text Generation
- Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
- Compressed Predictive Information Coding
- Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
- Automatic Detection and Segmentation of Postoperative Cerebellar Damage Based on Normalization
- Data-Efficient and Interpretable Tabular Anomaly Detection
- Provable and Efficient Continual Representation Learning
- Nonlinear predictive models computation in ADPCM schemes
- Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks
- Interventions, Where and How? Experimental Design for Causal Models at Scale
- DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations
- Why adversarial training can hurt robust accuracy
- On consistency of constrained spectral clustering under representation-aware stochastic block model
- Counting Molecules: Python based scheme for automated enumeration and categorization of molecules in scanning tunneling microscopy images
- Multi-objective robust optimization using adaptive surrogate models for problems with mixed continuous-categorical parameters
- Fast Neural Architecture Search for Lightweight Dense Prediction Networks
- Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values
- Enhanced physics-constrained deep neural networks for modeling vanadium redox flow battery
- Region-of-Interest Based Neural Video Compression
- Audio-Visual Object Classification for Human-Robot Collaboration
- Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages
- Towards Rich, Portable, and Large-Scale Pedestrian Data Collection
- Robust Segmentation of Brain MRI in the Wild with Hierarchical CNNs and no Retraining
- Learning Time-optimized Path Tracking with or without Sensory Feedback
- A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images
- Autoregressive Image Generation using Residual Quantization
- Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification
- BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
- Comparison of LSTM autoencoder based deep learning enabled Bayesian inference using two time series reconstruction approaches
- E-CIR: Event-Enhanced Continuous Intensity Recovery
- Quality or Quantity: Toward a Unified Approach for Multi-organ Segmentation in Body CT
- CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation
- Label-Free Explainability for Unsupervised Models
- As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning
- Label-Only Model Inversion Attacks via Boundary Repulsion
- Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning
- Recovering 3D Human Mesh from Monocular Images: A Survey
- Vision-Language Intelligence: Tasks, Representation Learning, and Large Models
- NUQ: A Noise Metric for Diffusion MRI via Uncertainty Discrepancy Quantification
- Investigating the limited performance of a deep-learning-based SPECT denoising approach: An observer-study-based characterization
- Playable Environments: Video Manipulation in Space and Time
- NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
- Bayesian Spillover Graphs for Dynamic Networks
- An Adaptive Human Driver Model for Realistic Race Car Simulations
- Computer Vision Aided Blockage Prediction in Real-World Millimeter Wave Deployments
- Pay Attention to Relations: Multi-embeddings for Attributed Multiplex Networks
- Instance Segmentation for Autonomous Log Grasping in Forestry Operations
- Sparse Bayesian Optimization
- Improving Health Mentioning Classification of Tweets using Contrastive Adversarial Training
- Reconstruction of univariate functions from directional persistence diagrams
- Quantum Reinforcement Learning via Policy Iteration
- TCTrack: Temporal Contexts for Aerial Tracking
- Graph Neural Networks for Multimodal Single-Cell Data Integration
- ROCT-Net: A new ensemble deep convolutional model with improved spatial resolution learning for detecting common diseases from retinal OCT images
- DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae
- Measuring Self-Supervised Representation Quality for Downstream Classification using Discriminative Features
- LatentFormer: Multi-Agent Transformer-Based Interaction Modeling and Trajectory Prediction
- Query Processing on Tensor Computation Runtimes
- Thermodynamics-informed graph neural networks
- KamNet: An Integrated Spatiotemporal Deep Neural Network for Rare Event Search in KamLAND-Zen
- Robustness and Adaptation to Hidden Factors of Variation
- The world seems different in a social context: a neural network analysis of human experimental data
- Robust PACm: Training Ensemble Models Under Misspecification and Outliers
- A study on the distribution of social biases in self-supervised learning visual models
- Efficient Video Instance Segmentation via Tracklet Query and Proposal
- Identification in Tree-shaped Linear Structural Causal Models
- STUN: Self-Teaching Uncertainty Estimation for Place Recognition
- T-Cal: An optimal test for the calibration of predictive models
- Context Enhanced Short Text Matching using Clickthrough Data
- Local Constraint-Based Causal Discovery under Selection Bias
- LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network
- Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph
All 203
- Intensity Image-based LiDAR Fiducial Marker System
- Automatic Facial Paralysis Estimation with Facial Action Units
- Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows
- On Learning Contrastive Representations for Learning with Noisy Labels
- Revisiting Click-based Interactive Video Object Segmentation
- PeerSum: A Peer Review Dataset for Abstractive Multi-document Summarization
- Random Quantum Neural Networks (RQNN) for Noisy Image Recognition
- NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields
- PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequence
- Vertical Federated Principal Component Analysis and Its Kernel Extension on Feature-wise Distributed Data
- Accelerated SGD for Non-Strongly-Convex Least Squares
- Machine learning model to project the impact of Ukraine crisis
- Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
- Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds
- Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
- Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
- Topological data analysis of truncated contagion maps
- Practitioner Motives to Use Different Hyperparameter Optimization Methods
- Detecting High-Quality GAN-Generated Face Images using Neural Networks
- Weakly Supervised Object Localization as Domain Adaption
- Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D Reconstruction
- Unfolding-Aided Bootstrapped Phase Retrieval in Optical Imaging
- Learning Neural Set Functions Under the Optimal Subset Oracle
- Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection
- Anomaly Detection in Big Data
- Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains
- Quantity over Quality: Training an AV Motion Planner with Large Scale Commodity Vision Data
- Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
- Cross-Modality Earth Mover's Distance for Visible Thermal Person Re-Identification
- Constrained unsupervised anomaly segmentation
- Translational Lung Imaging Analysis Through Disentangled Representations
- Joint Probability Estimation Using Tensor Decomposition and Dictionaries
- Correlation-Aware Deep Tracking
- β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search
- Monitoring Diversity of AI Conferences: Lessons Learnt and Future Challenges in the DivinAI Project
- On partitioning of an SHM problem and parallels with transfer learning
- Optimized cost function for demand response coordination of multiple EV charging stations using reinforcement learning
- On an application of graph neural networks in population based SHM
- Selective Residual M-Net for Real Image Denoising
- UDAAN: Machine Learning based Post-Editing tool for Document Translation
- Improving X-ray Diagnostics through Eye-Tracking and XR
- Adaptive Path Planning for UAVs for Multi-Resolution Semantic Segmentation
- On generating parametrised structural data using conditional generative adversarial networks
- Risk-aware Stochastic Shortest Path
- Parallel feature selection based on the trace ratio criterion
- Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis
- Learning Group Importance using the Differentiable Hypergeometric Distribution
- Early Time-Series Classification Algorithms: An Empirical Comparison
- Physics-Data Driven Machine Learning Based Model: A Hybrid Way for Nonlinear, Dynamic, and Open-loop Identification of IPMC Soft Artificial Muscles
- Nanopublication-Based Semantic Publishing and Reviewing: A Field Study with Formalization Papers
- Ensemble Methods for Robust Support Vector Machines using Integer Programming
- Curvature Graph Generative Adversarial Networks
- AdaFamily: A family of Adam-like adaptive gradient methods
- Syntax-Aware Network for Handwritten Mathematical Expression Recognition
- Uniform Approximations for Randomized Hadamard Transforms with Applications
- Neural Graph Matching for Pre-training Graph Neural Networks
- A Deep Neural Framework for Image Caption Generation Using GRU-Based Attention Mechanism
- 3D Human Motion Prediction: A Survey
- Multi-Tailed Vision Transformer for Efficient Inference
- Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models
- Towards Universal Backward-Compatible Representation Learning
- A shallow physics-informed neural network for solving partial differential equations on surfaces
- HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
- Occlusion-Aware Cost Constructor for Light Field Depth Estimation
- Data Augmentation as Feature Manipulation
- Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
- Graph Representation Learning Beyond Node and Homophily
- ViTransPAD: Video Transformer using convolution and self-attention for Face Presentation Attack Detection
- Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth
- DareFightingICE Competition: A Fighting Game Sound Design and AI Competition
- Addressing the Shape-Radiance Ambiguity in View-Dependent Radiance Fields
- Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking
- A Characterization of Multiclass Learnability
- Automated clustering of COVID-19 anti-vaccine discourse on Twitter
- Rethinking the role of normalization and residual blocks for spiking neural networks
- QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition
- SegTAD: Precise Temporal Action Detection via Semantic Segmentation
- Curriculum-style Local-to-global Adaptation for Cross-domain Remote Sensing Image Segmentation
- Self-supervised Transparent Liquid Segmentation for Robotic Pouring
- Private High-Dimensional Hypothesis Testing
- Recent Advances in Vision Transformer: A Survey and Outlook of Recent Work
- Kernel Density Estimation by Genetic Algorithm
- Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks
- CAFE: Learning to Condense Dataset by Aligning Features
- Semi-supervised Learning using Robust Loss
- BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
- An Open Challenge for Inductive Link Prediction on Knowledge Graphs
- Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
- Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking
- Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding
- Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media
- SoftGroup for 3D Instance Segmentation on Point Clouds
- Large-scale Optimization of Partial AUC in a Range of False Positive Rates
- NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
- The Best of Both Worlds: Reinforcement Learning with Logarithmic Regret and Policy Switches
- PetsGAN: Rethinking Priors for Single Image Generation
- MetaDT: Meta Decision Tree with Class Hierarchy for Interpretable Few-Shot Learning
- Modularity of the ABCD Random Graph Model with Community Structure
- Weightless Neural Networks for Efficient Edge Inference
- CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision
- Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction
- Successful Recovery of an Observed Meteorite Fall Using Drones and Machine Learning
- Deep Q-network using reservoir computing with multi-layered readout