Papers
Mon 10 May 2021
177 papers
- KDExplainer: A Task-oriented Attention Model for Explaining Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Voice activity detection in the wild: A data-driven approach using teacher-student trainingKnowledge distillation → Speech and audio distillation
- A Survey of Performance Optimization in Neural Network-Based Video Analytics Systems
- Grey-box models for wave loading prediction
- Quantum Uncertainty in Decision Theory
- The challenges and realities of retailing in a COVID-19 world: Identifying trending and Vital During Crisis keywords during Covid-19 using Machine Learning (Austria as a case study)
- Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design
- Learning Weakly Convex Sets in Metric Spaces
- DEEMD: Drug Efficacy Estimation against SARS-CoV-2 based on cell Morphology with Deep multiple instance learning
- Semi-Supervised Metric Learning: A Deep Resurrection
- Estimating the State of Epidemics Spreading with Graph Neural Networks
- Adversarial examples attack based on random warm restart mechanism and improved Nesterov momentum
- Rethinking and Reweighting the Univariate Losses for Multi-Label Ranking: Consistency and Generalization
- Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speech
- Sample and Computation Redistribution for Efficient Face Detection
- Personalized Popular Music Generation Using Imitation and Structure
- Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines
- Accountable Error Characterization
- Adaptive Policy Transfer in Reinforcement Learning
- Budget-Constrained Coalition Strategies with Discounting
- Assessing the Syntactic Capabilities of Transformer-based Multilingual Language Models
- Deep Bandits Show-Off: Simple and Efficient Exploration with Deep Networks
- Value Iteration in Continuous Actions, States and Time
- Sample selection for efficient image annotation
- What shall we do with an hour of data? Speech recognition for the un- and under-served languages of Common Voice
- HuMoR: 3D Human Motion Model for Robust Pose Estimation
- The Influence of Memory in Multi-Agent Consensus
- GSPMD: General and Scalable Parallelization for ML Computation Graphs
- Multi-Objective Controller Synthesis with Uncertain Human Preferences
- Distribution-free calibration guarantees for histogram binning without sample splitting
- Causal Inference in medicine and in health policy, a summary
- GroupLink: An End-to-end Multitask Method for Word Grouping and Relation Extraction in Form Understanding
- Deeply-Debiased Off-Policy Interval Estimation
- R2D2: Relational Text Decoding with Transformers
- SUPR-GAN: SUrgical PRediction GAN for Event Anticipation in Laparoscopic and Robotic Surgery
- Local Frequency Domain Transformer Networks for Video Prediction
- Language Acquisition is Embodied, Interactive, Emotive: a Research Proposal
- Measuring Economic Policy Uncertainty Using an Unsupervised Word Embedding-based Method
- Improving Factual Consistency of Abstractive Summarization via Question Answering
- A Description Logic for Analogical Reasoning
- Enhancing Photorealism Enhancement
- Automatic Classification of Human Translation and Machine Translation: A Study from the Perspective of Lexical Diversity
- Differentially Private Transferrable Deep Learning with Membership-Mappings
- Analog Neural Computing with Super-resolution Memristor Crossbars
- Efficient Self-Supervised Data Collection for Offline Robot Learning
- TransPose: Real-time 3D Human Translation and Pose Estimation with Six Inertial Sensors
- A Deep Dive into Conflict Generating Decisions
- Towards Discovery and Attribution of Open-world GAN Generated Images
- Customized Monte Carlo Tree Search for LLVM/Polly's Composable Loop Optimization Transformations
- Self-Supervised Learning with Swin Transformers
- Stochastic Image-to-Video Synthesis using cINNs
- Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
- Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction
- Learning High-Dimensional Distributions with Latent Neural Fokker-Planck Kernels
- Improving Fairness of AI Systems with Lossless De-biasing
- Improved Simultaneous Multi-Slice Functional MRI Using Self-supervised Deep Learning
- Identification of the nonlinear steering dynamics of an autonomous vehicle
- Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
- Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels
- An end-to-end Optical Character Recognition approach for ultra-low-resolution printed text images
- End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021
- MDA-Net: Multi-Dimensional Attention-Based Neural Network for 3D Image Segmentation
- Towards Benchmarking the Utility of Explanations for Model Debugging
- Deep Neural Networks as Point Estimates for Deep Gaussian Processes
- Graph Feature Gating Networks
- Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions
- A Deep Reinforcement Learning Approach to Audio-Based Navigation in a Multi-Speaker Environment
- Towards Robust One-shot Task Execution using Knowledge Graph Embeddings
- Self-Guided Curriculum Learning for Neural Machine Translation
- Safety of the Intended Driving Behavior Using Rulebooks
- Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions
- Galois/monodromy groups for decomposing minimal problems in 3D reconstruction
- ICON: Learning Regular Maps Through Inverse Consistency
- Learning Robust Latent Representations for Controllable Speech Synthesis
- Scaffolding Simulations with Deep Learning for High-dimensional Deconvolution
- SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
- Continual Learning via Bit-Level Information Preserving
- Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction
- Boosting Semi-Supervised Face Recognition with Noise Robustness
- An Enhanced Randomly Initialized Convolutional Neural Network for Columnar Cactus Recognition in Unmanned Aerial Vehicle Imagery
- MTNet: A Multi-Task Neural Network for On-Field Calibration of Low-Cost Air Monitoring Sensors
- On projection methods for functional time series forecasting
- Stability Constrained Mobile Manipulation Planning on Rough Terrain
- Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey
- A framework for the automation of testing computer vision systems
- Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds
- Combinatorial Multi-armed Bandits for Resource Allocation
- Poolingformer: Long Document Modeling with Pooling Attention
- Coconut trees detection and segmentation in aerial imagery using mask region-based convolution neural network
- AFINet: Attentive Feature Integration Networks for Image Classification
- tFold-TR: Combining Deep Learning Enhanced Hybrid Potential Energy for Template-Based Modeling Structure Refinement
- Exploring open-ended gameplay features with Micro RollerCoaster Tycoon
- DefSent: Sentence Embeddings using Definition Sentences
- Bayesian Optimistic Optimisation with Exponentially Decaying Regret
- An Autonomous Drone for Search and Rescue in Forests using Airborne Optical Sectioning
- RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation
- Reinforcement learning of rare diffusive dynamics
- A Bregman Learning Framework for Sparse Neural Networks
- DocReader: Bounding-Box Free Training of a Document Information Extraction Model
- Multi-modal Conditional Bounding Box Regression for Music Score Following
All 177
- Video Anomaly Detection By The Duality Of Normality-Granted Optical Flow
- ADASYN-Random Forest Based Intrusion Detection Model
- How could Neural Networks understand Programs?
- Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
- Do Concept Bottleneck Models Learn as Intended?
- Primitive Representation Learning for Scene Text Recognition
- Visual Grounding with Transformers
- Loss-Aversively Fair Classification
- DocOIE: A Document-level Context-Aware Dataset for OpenIE
- Weakly supervised pan-cancer segmentation tool
- Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception
- An Analysis of Phenotypic Diversity in Multi-Solution Optimization
- Expressing and Exploiting the Common Subgoal Structure of Classical Planning Domains Using Sketches: Extended Version
- Accounting for Model Uncertainty in Algorithmic Discrimination
- Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
- In-Hindsight Quantization Range Estimation for Quantized Training
- Overcoming the Distance Estimation Bottleneck in Estimating Animal Abundance with Camera Traps
- T-EMDE: Sketching-based global similarity for cross-modal retrieval
- ReadTwice: Reading Very Large Documents with Memories
- A rigorous introduction to linear models
- SIRNN: A Math Library for Secure RNN Inference
- De-homogenization using Convolutional Neural Networks
- Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
- Similarities between Arabic Dialects: Investigating Geographical Proximity
- Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks
- Event-LSTM: An Unsupervised and Asynchronous Learning-based Representation for Event-based Data
- Temporal-Spatial Feature Pyramid for Video Saliency Detection
- SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data
- Robust Graph Learning Under Wasserstein Uncertainty
- Action Shuffling for Weakly Supervised Temporal Localization
- Age of Information Aware VNF Scheduling in Industrial IoT Using Deep Reinforcement Learning
- You Only Learn One Representation: Unified Network for Multiple Tasks
- REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training
- AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning
- The Modulo Radon Transform: Theory, Algorithms and Applications
- A Rigorous Information-Theoretic Definition of Redundancy and Relevancy in Feature Selection Based on (Partial) Information Decomposition
- Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation
- Rate-Distortion Analysis of Minimum Excess Risk in Bayesian Learning
- AutoDebias: Learning to Debias for Recommendation
- PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data
- Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning
- CREPO: An Open Repository to Benchmark Credal Network Algorithms
- ReLU Deep Neural Networks from the Hierarchical Basis Perspective
- Unsupervised Human Pose Estimation through Transforming Shape Templates
- Slashing Communication Traffic in Federated Learning by Transmitting Clustered Model Updates
- Transitioning from Real to Synthetic data: Quantifying the bias in model
- Matching Visual Features to Hierarchical Semantic Topics for Image Paragraph Captioning
- Coupling Intent and Action for Pedestrian Crossing Behavior Prediction
- An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
- Boltzmann machines as two-dimensional tensor networks
- Parameter-free Gradient Temporal Difference Learning
- Examining and Mitigating Kernel Saturation in Convolutional Neural Networks using Negative Images
- ExpMRC: Explainability Evaluation for Machine Reading Comprehension
- Fast constraint satisfaction problem and learning-based algorithm for solving Minesweeper
- FAID Diversity via Neural Networks
- Wiki-Reliability: A Large Scale Dataset for Content Reliability on Wikipedia
- Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learning
- AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
- BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning
- Deep feature selection-and-fusion for RGB-D semantic segmentation
- Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
- SRLF: A Stance-aware Reinforcement Learning Framework for Content-based Rumor Detection on Social Media
- Elastic Weight Consolidation (EWC): Nuts and Bolts
- MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE
- PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning
- Latency Analysis of Consortium Blockchained Federated Learning
- A Coupled Random Projection Approach to Large-Scale Canonical Polyadic Decomposition
- Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant Method
- Self-supervised spectral matching network for hyperspectral target detection
- Dynamic Multichannel Access via Multi-agent Reinforcement Learning: Throughput and Fairness Guarantees
- CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
- Meteorological and human mobility data on predicting COVID-19 cases by a novel hybrid decomposition method with anomaly detection analysis: a case study in the capitals of Brazil
- Robust Training Using Natural Transformation
- Neural Graph Matching based Collaborative Filtering
- Reconstructive Sequence-Graph Network for Video Summarization
- Approximate Fr'echet Mean for Data Sets of Sparse Graphs
- Societal Biases in Language Generation: Progress and Challenges