Papers
Mon 14 Nov 2022
214 papers
- Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D DetectionKnowledge distillation → Detection and dense prediction distillation
- Diffusion Models for Medical Image Analysis: A Comprehensive SurveyDiffusion models → Medical imaging and segmentation
- Extreme Generative Image Compression by Learning Text Embedding from Diffusion ModelsDiffusion models → Diffusion for compression and wireless
- Arbitrary Style Guidance for Enhanced Diffusion-Based Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- Denoising diffusion models for out-of-distribution detectionDiffusion models → Medical imaging and segmentation
- Logical Tasks for Measuring Extrapolation and Rule ComprehensionLLM reasoning → Mathematical reasoning
- An Interpretable Neuron Embedding for Static Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Advancing the State-of-the-Art for ECG Analysis through Structured State Space ModelsState-space sequence models (S4, Mamba) → Physiological signal modeling
- NeurIPS 2022 Competition: Driving SMARTSEnd-to-end autonomous driving → Reinforcement learning for driving
- Follow the Clairvoyant: an Imitation Learning Approach to Optimal ControlOffline RL and imitation learning from data → Imitation learning methods
- Cross-Modality Knowledge Distillation Network for Monocular 3D Object DetectionKnowledge distillation → Detection and dense prediction distillation
- FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning ModelLLM safety and security → Federated unlearning and poisoning
- Retrieval-Augmented Generative Question Answering for Event Argument ExtractionRetrieval-augmented generation → RAG robustness and adaptive retrieval
- Hope Speech Detection on Social Media Platforms
- Semantic Decomposition Improves Learning of Large Language Models on EHR Data
- Technological taxonomies for hypernym and hyponym retrieval in patent texts
- From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems
- Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks
- ML framework for global river flood predictions based on the Caravan dataset
- Understanding the Energy Consumption of HPC Scale Artificial Intelligence
- An Interpretable Hybrid Predictive Model of COVID-19 Cases using Autoregressive Model and LSTM
- LSA-T: The first continuous Argentinian Sign Language dataset for Sign Language Translation
- Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation
- LAPTNet: LiDAR-Aided Perspective Transform Network
- Quality-diversity in dissimilarity spaces
- Un discours et un public "Gilets Jaunes" au coeur du Grand D'ebat National? Combinaison des approches IA et textom'etriques pour l'analyse de discours des plateformes "Grand D'ebat National" et "Vrai d'ebat"
- Improving ECG-based COVID-19 diagnosis and mortality predictions using pre-pandemic medical records at population-scale
- Sample-efficient Quantum Born Machine through Coding Rate Reduction
- Tire-road friction estimation and uncertainty assessment to improve electric aircraft braking system
- Renewing Iterative Self-labeling Domain Adaptation with Application to the Spine Motion Prediction
- Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates
- A Rigorous Study Of The Deep Taylor Decomposition
- Pruning Very Deep Neural Network Channels for Efficient Inference
- Contrastive learning for regression in multi-site brain age prediction
- Artificial Intelligence for Automatic Detection and Classification Disease on the X-Ray Images
- Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition
- On counterfactual inference with unobserved confounding
- Energy Storage Price Arbitrage via Opportunity Value Function Prediction
- On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
- Interpreting Bias in the Neural Networks: A Peek Into Representational Similarity
- Robust Deep Learning for Autonomous Driving
- Edge2Vec: A High Quality Embedding for the Jigsaw Puzzle Problem
- Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech Representations
- Meta-Learning of Neural State-Space Models Using Data From Similar Systems
- Learning to Optimize with Stochastic Dominance Constraints
- 3D Reconstruction-Based Seed Counting of Sorghum Panicles for Agricultural Inspection
- Generative Aspect-Based Sentiment Analysis with Contrastive Learning and Expressive Structure
- Describing emotions with acoustic property prompts for speech emotion recognition
- Monte Carlo Planning in Hybrid Belief POMDPs
- Speaking Multiple Languages Affects the Moral Bias of Language Models
- QueryForm: A Simple Zero-shot Form Entity Query Framework
- Hierarchically Structured Task-Agnostic Continual Learning
- An online algorithm for contrastive Principal Component Analysis
- (When) Are Contrastive Explanations of Reinforcement Learning Helpful?
- Disentangling Variational Autoencoders
- Do Neural Networks Trained with Topological Features Learn Different Internal Representations?
- Supervised Fine-tuning Evaluation for Long-term Visual Place Recognition
- Self-training of Machine Learning Models for Liver Histopathology: Generalization under Clinical Shifts
- Uncovering the Portability Limitation of Deep Learning-Based Wireless Device Fingerprints
- On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
- Machine Learning Performance Analysis to Predict Stroke Based on Imbalanced Medical Dataset
- Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations
- Removing fluid lensing effects from spatial images
- Evaluating Distribution System Reliability with Hyperstructures Graph Convolutional Nets
- Legged Locomotion in Challenging Terrains using Egocentric Vision
- EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
- Learnable Spatio-Temporal Map Embeddings for Deep Inertial Localization
- Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding
- Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns
- Redeeming Intrinsic Rewards via Constrained Optimization
- What Images are More Memorable to Machines?
- Semantic Similarity Models for Depression Severity Estimation
- Alternating minimization algorithm with initialization analysis for r-local and k-sparse unlabeled sensing
- Federated Learning for Autoencoder-based Condition Monitoring in the Industrial Internet of Things
- UGIF: UI Grounded Instruction Following
- Towards Data-Driven Offline Simulations for Online Reinforcement Learning
- PiPa: Pixel- and Patch-wise Self-supervised Learning for Domain Adaptative Semantic Segmentation
- Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
- Towards Abstractive Timeline Summarisation using Preference-based Reinforcement Learning
- Imagination is All You Need! Curved Contrastive Learning for Abstract Sequence Modeling Utilized on Long Short-Term Dialogue Planning
- Stain-invariant self supervised learning for histopathology image analysis
- Row Conditional-TGAN for generating synthetic relational databases
- AttenFace: A Real Time Attendance System using Face Recognition
- Millimeter Wave Drones with Cameras: Computer Vision Aided Wireless Beam Prediction
- Self-distillation with Online Diffusion on Batch Manifolds Improves Deep Metric Learning
- Utilizing Synthetic Data in Supervised Learning for Robust 5-DoF Magnetic Marker Localization
- Phenotype Detection in Real World Data via Online MixEHR Algorithm
- Vision meets algae: A novel way for microalgae recognization and health monitor
- Aspects of scaling and scalability for flow-based sampling of lattice QCD
- High-Resource Methodological Bias in Low-Resource Investigations
- Generalized Balancing Weights via Deep Neural Networks
- A Survey on Preserving Fairness Guarantees in Changing Environments
- Towards a Mathematics Formalisation Assistant using Large Language Models
- Learning to Answer Multilingual and Code-Mixed Questions
- PKCAM: Previous Knowledge Channel Attention Module
- Adaptive search space decomposition method for pre- and post- buckling analyses of space truss structures
- Heterogeneous Graph Sparsification for Efficient Representation Learning
- Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations
- Why Did the Chicken Cross the Road? Rephrasing and Analyzing Ambiguous Questions in VQA
- CST5: Data Augmentation for Code-Switched Semantic Parsing
All 214
- High-Accuracy Machine Learning Techniques for Functional Connectome Fingerprinting and Cognitive State Decoding
- On Analyzing the Role of Image for Visual-enhanced Relation Extraction
- Discovering A Variety of Objects in Spatio-Temporal Human-Object Interactions
- AdaptKeyBERT: An Attention-Based approach towards Few-Shot & Zero-Shot Domain Adaptation of KeyBERT
- Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images
- Contextual Bandits with Packing and Covering Constraints: A Modular Lagrangian Approach via Regression
- Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection
- Unifying O(3) Equivariant Neural Networks Design with Tensor-Network Formalism
- Cracking Double-Blind Review: Authorship Attribution with Deep Learning
- Reinforcement Learning Based Resource Allocation for Network Slices in O-RAN Midhaul
- Findings of the Covid-19 MLIA Machine Translation Task
- An Analytics of Culture: Modeling Subjectivity, Scalability, Contextuality, and Temporality
- Self-Aligning Depth-regularized Radiance Fields for Asynchronous RGB-D Sequences
- Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems
- LGN-Net: Local-Global Normality Network for Video Anomaly Detection
- Additive Covariance Matrix Models: Modelling Regional Electricity Net-Demand in Great Britain
- Neural Regression For Scale-Varying Targets
- Calibrated Interpretation: Confidence Estimation in Semantic Parsing
- Multi-VQG: Generating Engaging Questions for Multiple Images
- Leveraging Automatic Personalised Nutrition: Food Image Recognition Benchmark and Dataset based on Nutrition Taxonomy
- Parallel Automatic History Matching Algorithm Using Reinforcement Learning
- Seeded iterative clustering for histology region identification
- Linear Reinforcement Learning with Ball Structure Action Space
- MR-NOM: Multi-scale Resolution of Neuronal cells in Nissl-stained histological slices via deliberate Over-segmentation and Merging
- Implications of Regret on Stability of Linear Dynamical Systems
- Multi-center anatomical segmentation with heterogeneous labels via landmark-based models
- Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
- Temporal patterns in insulin needs for Type 1 diabetes
- Hypothesis Transfer in Bandits by Weighted Models
- Unsupervised Method for Intra-patient Registration of Brain Magnetic Resonance Images based on Objective Function Weighting by Inverse Consistency: Contribution to the BraTS-Reg Challenge
- Language models are good pathologists: using attention-based sequence reduction and text-pretrained transformers for efficient WSI classification
- Attacking Face Recognition with T-shirts: Database, Vulnerability Assessment and Detection
- FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection
- Physics-Guided, Physics-Informed, and Physics-Encoded Neural Networks in Scientific Computing
- Unsupervised Face Recognition using Unlabeled Synthetic Data
- A deep learning framework to generate realistic population and mobility data
- Detecting Line Segments in Motion-blurred Images with Events
- Feature Correlation-guided Knowledge Transfer for Federated Self-supervised Learning
- Does Debiasing Inevitably Degrade the Model Performance
- Finding Skill Neurons in Pre-trained Transformer-based Language Models
- On Parsing as Tagging
- Replacing Language Model for Style Transfer
- MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction
- An Inter-observer consistent deep adversarial training for visual scanpath prediction
- Higher degree sum-of-squares relaxations robust against oblivious outliers
- MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets
- Self-Supervised Image Restoration with Blurry and Noisy Pairs
- Bayesian Layer Graph Convolutioanl Network for Hyperspetral Image Classification
- Sentiment recognition of Italian elderly through domain adaptation on cross-corpus speech dataset
- Adaptive Federated Minimax Optimization with Lower Complexities
- MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation
- SVS: Adversarial refinement for sparse novel view synthesis
- Universal EHR Federated Learning Framework
- A Novel Sampling Scheme for Text- and Image-Conditional Image Synthesis in Quantized Latent Spaces
- Learning to Model Multimodal Semantic Alignment for Story Visualization
- CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser
- A taxonomic system for failure cause analysis of open source AI incidents
- Robustifying Deep Vision Models Through Shape Sensitization
- Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment
- MLIC: Multi-Reference Entropy Model for Learned Image Compression
- The Best Path Algorithm automatic variables selection via High Dimensional Graphical Models
- Partial counterfactual identification and uplift modeling: theoretical results and real-world assessment
- Efficient Adversarial Training with Robust Early-Bird Tickets
- The Role of Local Alignment and Uniformity in Image-Text Contrastive Learning on Medical Images
- Exploiting Device and Audio Data to Tag Music with User-Aware Listening Contexts
- FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity
- Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
- Shared Loss between Generators of GANs
- SA-DPSGD: Differentially Private Stochastic Gradient Descent based on Simulated Annealing
- Robust Collaborative 3D Object Detection in Presence of Pose Errors
- Grafting Pre-trained Models for Multimodal Headline Generation
- Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice
- Fcaformer: Forward Cross Attention in Hybrid Vision Transformer
- Controllable GAN Synthesis Using Non-Rigid Structure-from-Motion
- TriDoNet: A Triple Domain Model-driven Network for CT Metal Artifact Reduction
- SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes
- Optimal Privacy Preserving for Federated Learning in Mobile Edge Computing
- Model Evaluation in Medical Datasets Over Time
- Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention
- ParCNetV2: Oversized Kernel with Enhanced Attention
- Towards Generalization on Real Domain for Single Image Dehazing via Meta-Learning
- Towards Understanding Omission in Dialogue Summarization
- WSC-Trans: A 3D network model for automatic multi-structural segmentation of temporal bone CT
- Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring
- DroneNet: Crowd Density Estimation using Self-ONNs for Drones
- C3: Cross-instance guided Contrastive Clustering
- YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion Annotations
- Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge
- Discharge Summary Hospital Course Summarisation of In Patient Electronic Health Record Text with Clinical Concept Guided Deep Pre-Trained Transformer Models
- Global Performance Guarantees for Neural Network Models of AC Power Flow
- ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations
- Information-guided pixel augmentation for pixel-wise contrastive learning
- Few-shot Metric Learning: Online Adaptation of Embedding for Retrieval
- Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations
- Bayesian Reconstruction and Differential Testing of Excised mRNA
- Knowledge Base Completion using Web-Based Question Answering and Multimodal Fusion
- Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization
- Easy Guided Decoding in Providing Suggestions for Interactive Machine Translation
- Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity
- BiViT: Extremely Compressed Binary Vision Transformer
- Hand gesture recognition using 802.11ad mmWave sensor in the mobile device
- PMR: Prototypical Modal Rebalance for Multimodal Learning
- Recognition of Cardiac MRI Orientation via Deep Neural Networks and a Method to Improve Prediction Accuracy
- Boosting Semi-Supervised 3D Object Detection with Semi-Sampling
- Learning Latent Part-Whole Hierarchies for Point Clouds
- Designing Efficient Pair-Trading Strategies Using Cointegration for the Indian Stock Market
- SPE: Symmetrical Prompt Enhancement for Fact Probing
- IFQA: Interpretable Face Quality Assessment
- Learning predictive checklists from continuous medical data
- Controllable Citation Sentence Generation with Language Models
- ALBERT with Knowledge Graph Encoder Utilizing Semantic Similarity for Commonsense Question Answering
- Dealing with missing data using attention and latent space regularization
- An Invitation to Distributed Quantum Neural Networks
- Treatment-RSPN: Recurrent Sum-Product Networks for Sequential Treatment Regimes