Papers
Tue 13 Apr 2021
172 papers
- Source and Target Bidirectional Knowledge Distillation for End-to-end Speech TranslationKnowledge distillation → Speech and audio distillation
- Online and Offline Reinforcement Learning by Planning with a Learned ModelOffline RL and imitation learning from data → Offline RL algorithms
- Understanding Transformers for Bot Detection in TwitterMechanistic interpretability → Knowledge and representations inside LLMs
- Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge DistillationKnowledge distillation → Multimodal distillation
- CXR Segmentation by AdaIN-based Domain Adaptation and Knowledge DistillationKnowledge distillation → Distillation for medical imaging
- Toward asynchronous EEG-based BCI: Detecting imagined words segments in continuous EEG signals
- Reinforcement learning for Admission Control in 5G Wireless Networks
- Safety-enhanced UAV Path Planning with Spherical Vector-based Particle Swarm Optimization
- Using Machine Learning at Scale in HPC Simulations with SmartSim: An Application to Ocean Climate Modeling
- EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
- Maximum Entropy Auto-Encoding
- Few-shot Image Generation via Cross-domain Correspondence
- Should Semantic Vector Composition be Explicit? Can it be Linear?
- Developing a Conversational Recommendation System for Navigating Limited Options
- Solving weakly supervised regression problem using low-rank manifold regularization
- Large-Scale Contextualised Language Modelling for Norwegian
- From Solving a Problem Boldly to Cutting the Gordian Knot: Idiomatic Text Generation
- Simultaneous Face Hallucination and Translation for Thermal to Visible Face Verification using Axial-GAN
- BERT Embeddings Can Track Context in Conversational Search
- Holistic Guidance for Occluded Person Re-Identification
- A Review of Anonymization for Healthcare Data
- TAAC: Temporally Abstract Actor-Critic for Continuous Control
- Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition
- "I'm Not Mad": Commonsense Implications of Negation and Contradiction
- A multiagent based framework secured with layered SVM-based IDS for remote healthcare systems
- DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
- Gaussian Process Model for Estimating Piecewise Continuous Regression Functions
- MS2: Multi-Document Summarization of Medical Studies
- Machine-learned 3D Building Vectorization from Satellite Imagery
- Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection Models
- Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer
- On the Interpretability and Significance of Bias Metrics in Texts: a PMI-based Approach
- ViT-V-Net: Vision Transformer for Unsupervised Volumetric Medical Image Registration
- Inference of cell dynamics on perturbation data using adjoint sensitivity
- Learning Log-Determinant Divergences for Positive Definite Matrices
- Learning to Jointly Deblur, Demosaick and Denoise Raw Images
- Single Image Depth Estimation: An Overview
- Modeling Framing in Immigration Discourse on Social Media
- Zhestyatsky at SemEval-2021 Task 2: ReLU over Cosine Similarity for BERT Fine-tuning
- Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
- Reward Shaping with Subgoals for Social Navigation
- BARF: Bundle-Adjusting Neural Radiance Fields
- Pointly-Supervised Instance Segmentation
- Lite-HRNet: A Lightweight High-Resolution Network
- DropLoss for Long-Tail Instance Segmentation
- Self-supervised object detection from audio-visual correspondence
- Mediators in Determining what Processing BERT Performs First
- Co-Scale Conv-Attentional Image Transformers
- Shape and Material Capture at Home
- All you need are a few pixels: semantic segmentation with PixelPick
- Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding
- ShapeMOD: Macro Operation Discovery for 3D Shape Programs
- Detoxifying Language Models Risks Marginalizing Minority Voices
- Thresholded Graphical Lasso Adjusts for Latent Variables: Application to Functional Neural Connectivity
- ExplainaBoard: An Explainable Leaderboard for NLP
- Optimal scaling of random-walk Metropolis algorithms using Bayesian large-sample asymptotics
- QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
- Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune
- Neuro-Symbolic VQA: A review from the perspective of AGI desiderata
- Data-Driven Reinforcement Learning for Virtual Character Animation Control
- GPU Semiring Primitives for Sparse Neighborhood Methods
- The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction
- Deep imagination is a close to optimal policy for planning in large decision trees under limited resources
- On the Impact of Random Seeds on the Fairness of Clinical Classifiers
- On the Use of Linguistic Features for the Evaluation of Generative Dialogue Systems
- Finding Concept-specific Biases in Form--Meaning Associations
- Modeling the dynamics of language change: logistic regression, Piotrowski's law, and a handful of examples in Polish
- δ-CLUE: Diverse Sets of Explanations for Uncertainty Estimates
- Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
- Learning and Planning in Complex Action Spaces
- Adversarial autoencoders and adversarial LSTM for improved forecasts of urban air pollution simulations
- Very Lightweight Photo Retouching Network with Conditional Sequential Modulation
- Podracer architectures for scalable Reinforcement Learning
- A Tale of Two Lexica Testing Computational Hypotheses with Deep Convolutional Neural Networks
- Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling
- Learning by example: fast reliability-aware seismic imaging with normalizing flows
- Understanding Hard Negatives in Noise Contrastive Estimation
- A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
- Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering
- Learning to recover orientations from projections in single-particle cryo-EM
- Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalities
- GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition
- Agents for Automated User Experience Testing
- UAV-ReID: A Benchmark on Unmanned Aerial Vehicle Re-identification in Video Imagery
- BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices
- Towards Unbiased Random Features with Lower Variance For Stationary Indefinite Kernels
- On the Impact of Knowledge-based Linguistic Annotations in the Quality of Scientific Embeddings
- COVID-19 case data for Italy stratified by age class
- Anomaly Detection in Image Datasets Using Convolutional Neural Networks, Center Loss, and Mahalanobis Distance
- Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts
- Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline
- On the Computational Intelligibility of Boolean Classifiers
- PHI-MVS: Plane Hypothesis Inference Multi-view Stereo for Large-Scale Scene Reconstruction
- Fast Hierarchical Games for Image Explanations
- Reward Shaping with Dynamic Trajectory Aggregation
- Visually Informed Binaural Audio Generation without Binaural Audios
- Muesli: Combining Improvements in Policy Optimization
- The Impact of Activation Sparsity on Overfitting in Convolutional Neural Networks
- Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection
- Optimizing the Long-Term Average Reward for Continuing MDPs: A Technical Report
All 172
- Multivariate Deep Evidential Regression
- What's in your Head? Emergent Behaviour in Multi-Task Transformer Models
- Automatic Correction of Internal Units in Generative Neural Networks
- Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds
- Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution
- Equivalence of Segmental and Neural Transducer Modeling: A Proof of Concept
- Adaptive Logit Adjustment Loss for Long-Tailed Visual Recognition
- Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentation
- Spatiotemporal Entropy Model is All You Need for Learned Video Compression
- NoiseVC: Towards High Quality Zero-Shot Voice Conversion
- Online Recognition of Actions Involving Objects
- 1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed
- Mixed supervision for surface-defect detection: from weakly to fully supervised learning
- UPB at SemEval-2021 Task 7: Adversarial Multi-Task Learning for Detecting and Rating Humor and Offense
- Model Learning with Personalized Interpretability Estimation (ML-PIE)
- First and Second Order Dynamics in a Hierarchical SOM system for Action Recognition
- LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
- Group Recommendation Techniques for Feature Modeling and Configuration
- Sequential Ski Rental Problem
- Transformer-based Methods for Recognizing Ultra Fine-grained Entities (RUFES)
- Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction
- Structural analysis of an all-purpose question answering model
- OCM3D: Object-Centric Monocular 3D Object Detection
- Conclusive Local Interpretation Rules for Random Forests
- MultiModalQA: Complex Question Answering over Text, Tables and Images
- Global Transport for Fluid Reconstruction with Learned Self-Supervision
- Lessons on Parameter Sharing across Layers in Transformers
- Detecting Operational Adversarial Examples for Reliable Deep Learning
- Deep Deterministic Path Following
- Sample-based and Feature-based Federated Learning for Unconstrained and Constrained Nonconvex Optimization via Mini-batch SSCA
- Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
- Disentangled Motif-aware Graph Learning for Phrase Grounding
- Gender Bias in Machine Translation
- Tracking translation invariance in CNNs
- Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack
- Temporal EigenPAC for dyslexia diagnosis
- VariTex: Variational Neural Face Textures
- CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images
- Experiments of ASR-based mispronunciation detection for children and adult English learners
- SPARK: SPAcecraft Recognition leveraging Knowledge of Space Environment
- Learning Multi-modal Information for Robust Light Field Depth Estimation
- Crossover Learning for Fast Online Video Instance Segmentation
- Dynamic Fusion Network For Light Field Depth Estimation
- Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation
- Hierarchical Adaptive Pooling by Capturing High-order Dependency for Graph Representation Learning
- AutoOED: Automated Optimal Experiment Design Platform
- "Subverting the Jewtocracy": Online Antisemitism Detection Using Multimodal Deep Learning
- Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustness
- Dynamic Texture Synthesis by Incorporating Long-range Spatial and Temporal Correlations
- QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization
- VR3Dense: Voxel Representation Learning for 3D Object Detection and Monocular Dense Depth Reconstruction
- Two-stage training algorithm for AI robot soccer
- Distilling Wikipedia mathematical knowledge into neural network models
- Multiple regression techniques for modeling dates of first performances of Shakespeare-era plays
- Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders
- Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack
- Document-Level Event Argument Extraction by Conditional Generation
- MESD: Exploring Optical Flow Assessment on Edge of Motion Objects with Motion Edge Structure Difference
- Revisiting Bayesian Autoencoders with MCMC
- GSA-Forecaster: Forecasting Graph-Based Time-Dependent Data with Graph Sequence Attention
- DirectProbe: Studying Representations without Classifiers
- Bi-level Off-policy Reinforcement Learning for Volt/VAR Control Involving Continuous and Discrete Devices
- SRR-Net: A Super-Resolution-Involved Reconstruction Method for High Resolution MR Imaging
- IMAGINE: Image Synthesis by Image-Guided Model Inversion
- NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media
- Fibro-CoSANet: Pulmonary Fibrosis Prognosis Prediction using a Convolutional Self Attention Network
- Simpler Certified Radius Maximization by Propagating Covariances
- The computational asymptotics of Gaussian variational inference and the Laplace approximation
- Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrieval
- Discourse Probing of Pretrained Language Models
- On the validity of kernel approximations for orthogonally-initialized neural networks
- Gradient Kernel Regression