Papers
Wed 7 Jul 2021
173 papers
- CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series ImputationDiffusion models → Flow matching, time series and science
- Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Categorical Relation-Preserving Contrastive Knowledge Distillation for Medical Image ClassificationKnowledge distillation → Distillation for medical imaging
- Learning Time-Invariant Reward Functions through Model-Based Inverse Reinforcement LearningOffline RL and imitation learning from data → Inverse reinforcement learning
- WeClick: Weakly-Supervised Video Semantic Segmentation with Click AnnotationsKnowledge distillation → Detection and dense prediction distillation
- Maintaining a Reliable World Model using Action-aware Perceptual AnchoringWorld models → Embodied and robot world models
- Structured Denoising Diffusion Models in Discrete State-SpacesWorld models → Video-generation world models and simulators +1
- Pragmatic Image Compression for Human-in-the-Loop Decision-Making
- eRAKI: Fast Robust Artificial neural networks for K-space Interpolation (RAKI) with Coil Combination and Joint Reconstruction
- Deep Learning for Embodied Vision Navigation: A Survey
- Day-to-day and seasonal regularity of network passenger delay for metro networks
- A Decision Model for Decentralized Autonomous Organization Platform Selection: Three Industry Case Studies
- A Simplified Framework for Air Route Clustering Based on ADS-B Data
- On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit
- Anomaly Detection Based on Multiple-Hypothesis Autoencoder
- Prediction of Blood Lactate Values in Critically Ill Patients: A Retrospective Multi-center Cohort Study
- A Fixed Version of Quadratic Program in Gradient Episodic Memory
- Short-term Hourly Streamflow Prediction with Graph Convolutional GRU Networks
- WeightScale: Interpreting Weight Change in Neural Networks
- Challenges for machine learning in clinical translation of big data imaging studies
- Tropical cyclone intensity estimations over the Indian ocean using Machine Learning
- Predicting Risk-adjusted Returns using an Asset Independent Regime-switching Model
- Identifying Hijacked Reviews
- Not Quite 'Ask a Librarian': AI on the Nature, Value, and Future of LIS
- End-to-End Rich Transcription-Style Automatic Speech Recognition with Semi-Supervised Learning
- Can Evolutionary Computation Help us to Crib the Voynich Manuscript ?
- DISCO : efficient unsupervised decoding for discrete natural language problems via convex relaxation
- Scopeformer: n-CNN-ViT Hybrid Model for Intracranial Hemorrhage Classification
- Measuring Financial Time Series Similarity With a View to Identifying Profitable Stock Market Opportunities
- Federated Learning for Multi-Center Imaging Diagnostics: A Study in Cardiovascular Disease
- POSLAN: Disentangling Chat with Positional and Language encoded Post Embeddings
- Energy Efficient Federated Learning in Integrated Fog-Cloud Computing Enabled Internet-of-Things Networks
- Federated Learning with Downlink Device Selection
- Impossibility results for fair representations
- Differentiable Random Access Memory using Lattices
- A repeated-measures study on emotional responses after a year in the pandemic
- An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild
- Comparing Machine Learning based Segmentation Models on Jet Fire Radiation Zones
- Model Selection for Generic Contextual Bandits
- S3: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
- Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling
- Handling Heavily Abbreviated Manuscripts: HTR engines vs text normalisation approaches
- Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test
- Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text
- BumbleBee: A Transformer for Music
- Modality Completion via Gaussian Process Prior Variational Autoencoders for Multi-Modal Glioma Segmentation
- LanguageRefer: Spatial-Language Model for 3D Visual Grounding
- Tensor Methods in Computer Vision and Deep Learning
- In-Network Learning: Distributed Training and Inference in Networks
- IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation
- Management of Resource at the Network Edge for Federated Learning
- Deep Learning for Two-Sided Matching
- Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classification
- A Graph-based Approach for Mitigating Multi-sided Exposure Bias in Recommender Systems
- Self-organized criticality in neural networks
- Sleep syndromes onset detection based on automatic sleep staging algorithm
- Rating and aspect-based opinion graph embeddings for explainable recommendations
- Long Short-Term Transformer for Online Action Detection
- Differentiable Architecture Pruning for Transfer Learning
- Evaluating Large Language Models Trained on Code
- Partial 3D Object Retrieval using Local Binary QUICCI Descriptors and Dissimilarity Tree Indexing
- A comparative study of various Deep Learning techniques for spatio-temporal Super-Resolution reconstruction of Forced Isotropic Turbulent flows
- M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
- Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions
- IntraLoss: Further Margin via Gradient-Enhancing Term for Deep Face Recognition
- A Survey of Uncertainty in Deep Neural Networks
- Samplets: A new paradigm for data compression
- Regularization-based Continual Learning for Fault Prediction in Lithium-Ion Batteries
- SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation
- KOALA: A Kalman Optimization Algorithm with Loss Adaptivity
- Robust Variable Selection and Estimation Via Adaptive Elastic Net S-Estimators for Linear Regression
- Enhancing an Intelligent Digital Twin with a Self-organized Reconfiguration Management based on Adaptive Process Models
- AGD-Autoencoder: Attention Gated Deep Convolutional Autoencoder for Brain Tumor Segmentation
- An algorithmic view of ℓ2 regularization and some path-following algorithms
- Probabilistic semi-nonnegative matrix factorization: a Skellam-based framework
- Predicting with Confidence on Unseen Distributions
- SoundStream: An End-to-End Neural Audio Codec
- RoFL: Robustness of Secure Federated Learning
- Bone Surface Reconstruction and Clinical Features Estimation from Sparse Landmarks and Statistical Shape Models: A feasibility study on the femur
- DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context
- MD-split+: Practical Local Conformal Inference in High Dimensions
- Introducing the structural bases of typicality effects in deep learning
- Linear-time calculation of the expected sum of edge lengths in random projective linearizations of trees
- Lemmatization of Historical Old Literary Finnish Texts in Modern Orthography
- Contrastive Explanations for Argumentation-Based Conclusions
- Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes
- "Are you sure?": Preliminary Insights from Scaling Product Comparisons to Multiple Shops
- Understanding Intrinsic Robustness Using Label Uncertainty
- DER Forecast using Privacy Preserving Federated Learning
- Robustifying Multi-hop QA through Pseudo-Evidentiality Training
- Coastal water quality prediction based on machine learning with feature interpretation and spatio-temporal analysis
- Scalable Data Balancing for Unlabeled Satellite Imagery
- Graphing else matters: exploiting aspect opinions and ratings in explainable graph-based recommendations
- Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis
- Combined Global and Local Search for Optimization with Gaussian Process Models
- MuVAM: A Multi-View Attention-based Model for Medical Visual Question Answering
- FasterPose: A Faster Simple Baseline for Human Pose Estimation
- Hierarchical Semantic Segmentation using Psychometric Learning
- Bias-Tolerant Fair Classification
- Nested Counterfactual Identification from Arbitrary Surrogate Experiments
All 173
- Intensity Prediction of Tropical Cyclones using Long Short-Term Memory Network
- A Closed-Form Approximation to the Conjugate Prior of the Dirichlet and Beta Distributions
- Urban Tree Species Classification Using Aerial Imagery
- HIDA: Towards Holistic Indoor Understanding for the Visually Impaired via Semantic Instance Segmentation with a Wearable Solid-State LiDAR Sensor
- Time-Aware Ancient Chinese Text Translation and Inference
- Levels of explainable artificial intelligence for human-aligned conversational explanations
- On Training Instance Selection for Few-Shot Neural Text Generation
- A Survey on Dialogue Summarization: Recent Advances and New Frontiers
- Trans4Trans: Efficient Transformer for Transparent Object Segmentation to Help Visually Impaired People Navigate in the Real World
- FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition
- Mitigating Generation Shifts for Generalized Zero-Shot Learning
- A Survey on Data Augmentation for Text Classification
- A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolution
- Neural Contextual Bandits without Regret
- Action Units Recognition Using Improved Pairwise Deep Architecture
- Hierarchical Text Classification of Urdu News using Deep Neural Network
- MedGPT: Medical Concept Prediction from Clinical Narratives
- Cross-View Exocentric to Egocentric Video Synthesis
- Egocentric Videoconferencing
- Learning Vision Transformer with Squeeze and Excitation for Facial Expression Recognition
- Self-supervised Outdoor Scene Relighting
- Rotation Transformation Network: Learning View-Invariant Point Cloud for Classification and Segmentation
- MACCIF-TDNN: Multi aspect aggregation of channel and context interdependence features in TDNN-based speaker verification
- GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
- Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation
- R2F: A Remote Retraining Framework for AIoT Processors with Computing Errors
- RISAN: Robust Instance Specific Abstention Network
- Discriminative Mutual Information Estimators for Channel Capacity Learning
- Hub and Spoke Logistics Network Design for Urban Region with Clustering-Based Approach
- Android Security using NLP Techniques: A Review
- Learning Stixel-based Instance Segmentation
- Efficient Transformer for Direct Speech Translation
- Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction
- Distributed adaptive algorithm based on the asymmetric cost of error functions
- Probabilistic partition of unity networks: clustering based deep approximation
- Blind Image Super-Resolution: A Survey and Beyond
- EchoEA: Echo Information between Entities and Relations for Entity Alignment
- Controlled Caption Generation for Images Through Adversarial Attacks
- ADAPT : Awesome Domain Adaptation Python Toolbox
- Transformer Network for Significant Stenosis Detection in CCTA of Coronary Arteries
- A convolutional neural network for teeth margin detection on 3-dimensional dental meshes
- Rethinking Sampling Strategies for Unsupervised Person Re-identification
- Reconstructing Test Labels from Noisy Loss Functions
- Bi-level Feature Alignment for Versatile Image Translation and Manipulation
- SelfCF: A Simple Framework for Self-supervised Collaborative Filtering
- Exact Learning Augmented Naive Bayes Classifier
- Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research
- Visual Odometry with an Event Camera Using Continuous Ray Warping and Volumetric Contrast Maximization
- Multi-modal Affect Analysis using standardized data within subjects in the Wild
- Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer
- Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers
- Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling
- PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation
- Keiki: Towards Realistic Danmaku Generation via Sequential GANs
- Test for non-negligible adverse shifts
- SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers
- Deep Convolutional Correlation Iterative Particle Filter for Visual Tracking
- SinSpell: A Comprehensive Spelling Checker for Sinhala
- VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidars
- RoboCup@Home Education 2020 Best Performance: RoboBreizh, a modular approach
- Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review
- RAM-VO: Less is more in Visual Odometry
- Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes
- GAN-based Data Augmentation for Chest X-ray Classification
- Deep Extrapolation for Attribute-Enhanced Generation
- Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
- E-PixelHop: An Enhanced PixelHop Method for Object Classification
- Disentangle Your Dense Object Detector
- Immunization of Pruning Attack in DNN Watermarking Using Constant Weight Code
- GLiT: Neural Architecture Search for Global and Local Image Transformer
- End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Data
- Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learning
- Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows