Papers
Mon 1 Mar 2021
191 papers
- There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal KnowledgeKnowledge distillation → Speech and audio distillation
- Embedded Knowledge Distillation in Depth-Level Dynamic Neural NetworkKnowledge distillation → General knowledge distillation methods
- Unbiased Sentence Encoder For Large-Scale Multi-lingual Search Engines
- CLPVG: Circular limited penetrable visibility graph as a new network model for time series
- A Machine Learning Approach for Predicting Human Preference for Graph Layouts
- From Quantifying Vagueness To Pan-niftyism
- Interpretable Artificial Intelligence through the Lens of Feature Interaction
- Accounting for Variance in Machine Learning Benchmarks
- Operator inference of non-Markovian terms for learning reduced models from partially observed state trajectories
- Multiclass Burn Wound Image Classification Using Deep Convolutional Neural Networks
- Brain Programming is Immune to Adversarial Attacks: Towards Accurate and Robust Image Classification using Symbolic Learning
- Statistical learning and cross-validation for point processes
- Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph
- Roosterize: Suggesting Lemma Names for Coq Verification Projects Using Deep Learning
- Emotion Dynamics in Movie Dialogues
- Reinforcement Learning for Adaptive Mesh Refinement
- Acceleration via Fractal Learning Rate Schedules
- Deep Bag-of-Sub-Emotions for Depression Detection in Social Media
- ToxCCIn: Toxic Content Classification with Interpretability
- A practical tutorial on Variational Bayes
- Adversarial training in communication constrained federated learning
- Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
- UCB Momentum Q-learning: Correcting the bias without forgetting
- SWIS -- Shared Weight bIt Sparsity for Efficient Neural Network Acceleration
- Scalable Scene Flow from Point Clouds in the Real World
- Exploring the high dimensional geometry of HSI features
- Coarse-Fine Networks for Temporal Activity Detection in Videos
- Multi-Objective Evolutionary Design of Composite Data-Driven Models
- Understanding & Predicting User Lifetime with Machine Learning in an Anonymous Location-Based Social Network
- Robust 3D U-Net Segmentation of Macular Holes
- Wide Network Learning with Differential Privacy
- Maximal function pooling with applications
- Generative Particle Variational Inference via Estimation of Functional Gradients
- DEUS: A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues
- Performance Variability in Zero-Shot Classification
- Dynamic covariate balancing: estimating treatment effects over time with potential local projections
- Non-Euclidean Differentially Private Stochastic Convex Optimization: Optimal Rates in Linear Time
- A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness
- On the Effectiveness of Dataset Embeddings in Mono-lingual,Multi-lingual and Zero-shot Conditions
- Geometry-Based Grasping of Vine Tomatoes
- Deep Unfolded Recovery of Sub-Nyquist Sampled Ultrasound Image
- A Deep Emulator for Secondary Motion of 3D Characters
- Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurements
- Auto-Exposure Fusion for Single-Image Shadow Removal
- Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in Language
- Offshore Software Maintenance Outsourcing Predicting Clients Proposal using Supervised Learning
- Multiple Convolutional Features in Siamese Networks for Object Tracking
- Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
- Generative Adversarial Transformers
- Mind the box: l1-APGD for sparse adversarial attacks on image classifiers
- Gradient Coding with Dynamic Clustering for Straggler-Tolerant Distributed Learning
- Statistically Significant Stopping of Neural Network Training
- Generating Probabilistic Safety Guarantees for Neural Network Controllers
- Can Machine Learning Catch the COVID-19 Recession?
- Coordination Among Neural Modules Through a Shared Global Workspace
- Sentiment Analysis of Users' Reviews on COVID-19 Contact Tracing Apps with a Benchmark Dataset
- Learners' Languages
- Noncoding RNAs and deep learning neural network discriminate multi-cancer types
- Unsupervised Classification of Voiced Speech and Pitch Tracking Using Forward-Backward Kalman Filtering
- Expected Value of Communication for Planning in Ad Hoc Teamwork
- The Healthy States of America: Creating a Health Taxonomy with Social Media
- E2CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
- Assessing deep learning methods for the identification of kidney stones in endoscopic images
- Domain Generalization via Inference-time Label-Preserving Target Projections
- Posterior Meta-Replay for Continual Learning
- InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring
- BERT based patent novelty search by training claims to their own description
- Automated data-driven approach for gap filling in the time series using evolutionary learning
- Extreme Volatility Prediction in Stock Market: When GameStop meets Long Short-Term Memory Networks
- DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification
- Deep Learning with a Classifier System: Initial Results
- Blockchain-Based Federated Learning in Mobile Edge Networks with Application in Internet of Vehicles
- Deep Perceptual Image Quality Assessment for Compression
- Optimal Linear Combination of Classifiers
- Measuring Inconsistency over Sequences of Business Rule Cases
- Categorical Depth Distribution Network for Monocular 3D Object Detection
- Counterfactual Explanations for Oblique Decision Trees: Exact, Efficient Algorithms
- Systematic Analysis and Removal of Circular Artifacts for StyleGAN
- A Biased Graph Neural Network Sampler with Near-Optimal Regret
- Challenges and Opportunities in High-dimensional Variational Inference
- Universal-Prototype Enhancing for Few-Shot Object Detection
- OmniNet: Omnidirectional Representations from Transformers
- A survey on Variational Autoencoders from a GreenAI perspective
- Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task
- A Hybrid Quantum-Classical Hamiltonian Learning Algorithm
- P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
- Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World
- Diversifying Sample Generation for Accurate Data-Free Quantization
- Computing the Information Content of Trained Neural Networks
- Predictive Maintenance Tool for Non-Intrusive Inspection Systems
- Persistent Message Passing
- Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
- Information Discrepancy in Strategic Learning
- Visualizing Rule Sets: Exploration and Validation of a Design Space
- Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
- Error Estimates for the Deep Ritz Method with Boundary Penalty
- Machine learning on small size samples: A synthetic knowledge synthesis
- AdaSpeech: Adaptive Text to Speech for Custom Voice
- Few-Shot Lifelong Learning
- Moment-Based Variational Inference for Stochastic Differential Equations
All 191
- Listening to the city, attentively: A Spatio-Temporal Attention Boosted Autoencoder for the Short-Term Flow Prediction Problem
- CogDL: A Comprehensive Library for Graph Deep Learning
- Secure Bilevel Asynchronous Vertical Federated Learning with Backward Updating
- Adversarial Reciprocal Points Learning for Open Set Recognition
- On the Fairness of Generative Adversarial Networks (GANs)
- Explainable AI in Credit Risk Management
- Cross Modal Focal Loss for RGBD Face Anti-Spoofing
- Collaborative Recognition of Feasible Region with Aerial and Ground Robots through DPCN
- Automatic Stockpile Volume Monitoring using Multi-view Stereo from SkySat Imagery
- A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network
- LADMM-Net: An Unrolled Deep Network For Spectral Image Fusion From Compressive Data
- OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration
- DF-VO: What Should Be Learnt for Visual Odometry?
- Unsupervised dynamic modeling of medical image transformation
- Anticipation Next -- System-sensitive technology development and integration in work contexts
- Diverse Critical Interaction Generation for Planning and Planner Evaluation
- STUDD: A Student-Teacher Method for Unsupervised Concept Drift Detection
- Manifold optimization for non-linear optimal transport problems
- Computationally Efficient Wasserstein Loss for Structured Labels
- Using contrastive learning to improve the performance of steganalysis schemes
- Counterfactual Zero-Shot and Open-Set Visual Recognition
- Deep learning based geometric registration for medical images: How accurate can we get without visual features?
- DR-TANet: Dynamic Receptive Temporal Attention Network for Street Scene Change Detection
- FineNet: Frame Interpolation and Enhancement for Face Video Deblurring
- Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning
- Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning
- Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
- CARMI: A Cache-Aware Learned Index with a Cost-based Construction Algorithm
- A Bioinspired Approach-Sensitive Neural Network for Collision Detection in Cluttered and Dynamic Backgrounds
- Vy=akarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages
- ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation
- CrossMap Transformer: A Crossmodal Masked Path Transformer Using Double Back-Translation for Vision-and-Language Navigation
- A Bioinspired Retinal Neural Network for Accurately Extracting Small-Target Motion Information in Cluttered Backgrounds
- Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attack
- A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning
- Emotion pattern detection on facial videos using functional statistics
- Learning Frequency Domain Approximation for Binary Neural Networks
- Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning
- Self-supervised Low Light Image Enhancement and Denoising
- Online anomaly detection using statistical leverage for streaming business process events
- M6: A Chinese Multimodal Pretrainer
- Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues
- Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation
- Contrastive Separative Coding for Self-supervised Representation Learning
- DST: Data Selection and joint Training for Learning with Noisy Labels
- MFST: Multi-Features Siamese Tracker
- Over-sampling De-occlusion Attention Network for Prohibited Items Detection in Noisy X-ray Images
- Representation Learning for Event-based Visuomotor Policies
- A 3D model-based approach for fitting masks to faces in the wild
- A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN
- Query Rewriting via Cycle-Consistent Translation for E-Commerce Search
- Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets
- Knowledge-Guided Dynamic Systems Modeling: A Case Study on Modeling River Water Quality
- RAGA: Relation-aware Graph Attention Networks for Global Entity Alignment
- Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations
- Detection and Rectification of Arbitrary Shaped Scene Texts by using Text Keypoints and Links
- PENet: Towards Precise and Efficient Image Guided Depth Completion
- Towards Unbiased COVID-19 Lesion Localisation and Segmentation via Weakly Supervised Learning
- Explaining Adversarial Vulnerability with a Data Sparsity Hypothesis
- Single-Shot Motion Completion with Transformer
- Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
- Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
- NeuTex: Neural Texture Mapping for Volumetric Neural Rendering
- Self-Supervised Depth and Ego-Motion Estimation for Monocular Thermal Video Using Multi-Spectral Consistency Loss
- Adaptive Sampling for Minimax Fair Classification
- Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence
- Long Document Summarization in a Low Resource Setting using Pretrained Language Models
- SmartON: Just-in-Time Active Event Detection on Energy Harvesting Systems
- Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models
- Automated Machine Learning on Graphs: A Survey
- FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
- Meta-Learning an Inference Algorithm for Probabilistic Programs
- The Mathematics Behind Spectral Clustering And The Equivalence To PCA
- BERT-based knowledge extraction method of unstructured domain text
- LocalDrop: A Hybrid Regularization for Deep Neural Networks
- Autonomous Navigation of an Ultrasound Probe Towards Standard Scan Planes with Deep Reinforcement Learning
- Panel semiparametric quantile regression neural network for electricity consumption forecasting
- Towards Personalized Federated Learning
- FedPower: Privacy-Preserving Distributed Eigenspace Estimation
- Heterogeneity for the Win: One-Shot Federated Clustering
- Federated Learning without Revealing the Decision Boundaries
- Meta-learning representations for clustering with infinite Gaussian mixture models
- Accelerating Recommendation System Training by Leveraging Popular Choices
- Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
- Decision Making in Monopoly using a Hybrid Deep Reinforcement Learning Approach
- Token-Modification Adversarial Attacks for Natural Language Processing: A Survey
- BEAUTY Powered BEAST
- Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
- Robust learning under clean-label attack
- Learning Proposals for Probabilistic Programs with Inference Combinators
- Model-Agnostic Defense for Lane Detection against Adversarial Attack