Papers
Mon 29 Mar 2021
214 papers
- Complementary Relation Contrastive DistillationKnowledge distillation → General knowledge distillation methods
- Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP ModelsLLM safety and security → Backdoor and data poisoning attacks
- The Autodidactic Universe
- A Facial Feature Discovery Framework for Race Classification Using Deep Learning
- Deep Reinforcement Learning for Resource Allocation in Business Processes
- Reinforcement Learning Beyond Expectation
- Prediction of Wind Speed Using Artificial Neural Networks and ANFIS Methods (Observation Buoy Example)
- Deep Hedging of Derivatives Using Reinforcement Learning
- Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
- A Multiplexed Network for End-to-End, Multilingual OCR
- An Overview of Human Activity Recognition Using Wearable Sensors: Healthcare and Artificial Intelligence
- PLAN-B: Predicting Likely Alternative Next Best Sequences for Action Prediction
- TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations
- A tutorial on SE(3) transformation parameterizations and on-manifold optimization
- Flow-based Kernel Prior with Application to Blind Super-Resolution
- Platform for Situated Intelligence
- Domain-robust VQA with diverse datasets and methods but no target labels
- Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptation
- Deep Compression for PyTorch Model Deployment on Microcontrollers
- Does it work outside this benchmark? Introducing the Rigid Depth Constructor tool, depth validation dataset construction in rigid scenes for the masses
- Detecting and Mapping Trees in Unstructured Environments with a Stereo Camera and Pseudo-Lidar
- Modeling Graph Node Correlations with Neighbor Mixture Models
- Strong Optimal Classification Trees
- Contextual Text Embeddings for Twi
- Demonstrating Analog Inference on the BrainScaleS-2 Mobile System
- DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation
- TREC 2020 Podcasts Track Overview
- Dynamic Autonomous Surface Vehicle Control and Applications in Environmental Monitoring
- Entity Context Graph: Learning Entity Representations fromSemi-Structured Textual Sources on the Web
- Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
- Federated Learning with Taskonomy for Non-IID Data
- Shaping Advice in Deep Multi-Agent Reinforcement Learning
- Representation range needs for 16-bit neural network training
- A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings
- Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks
- Learning Under Adversarial and Interventional Shifts
- Explaining a Neural Attention Model for Aspect-Based Sentiment Classification Using Diagnostic Classification
- Modelling Heterogeneity Using Bayesian Structured Sparsity
- MISA: Online Defense of Trojaned Models using Misattributions
- Restricted Boltzmann Machines as Models of Interacting Variables
- Robust Audio-Visual Instance Discrimination
- Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data
- Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment Analysis
- Sign Language Production: A Review
- Cognitive networks identify the content of English and Italian popular posts about COVID-19 vaccines: Anticipation, logistics, conspiracy and loss of trust
- pH-RL: A personalization architecture to bring reinforcement learning to health practice
- Iterative Gradient Encoding Network with Feature Co-Occurrence Loss for Single Image Reflection Removal
- Comparison of different convolutional neural network activation functions and methods for building ensembles
- Automating Defense Against Adversarial Attacks: Discovery of Vulnerabilities and Application of Multi-INT Imagery to Protect Deployed Models
- Learning Domain Invariant Representations for Generalizable Person Re-Identification
- The Complexity of Nonconvex-Strongly-Concave Minimax Optimization
- Unsupervised Machine Translation On Dravidian Languages
- High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation
- In-Place Scene Labelling and Understanding with Implicit Scene Representation
- Industry Scale Semi-Supervised Learning for Natural Language Understanding
- Simultaneous Reconstruction and Uncertainty Quantification for Tomography
- CateNorm: Categorical Normalization for Robust Medical Image Segmentation
- Distilled Replay: Overcoming Forgetting through Synthetic Samples
- Text Normalization for Low-Resource Languages of Africa
- Augmenting Automated Game Testing with Deep Reinforcement Learning
- High-Fidelity and Arbitrary Face Editing
- PixelTransformer: Sample Conditioned Signal Generation
- LatentKeypointGAN: Controlling Images via Latent Keypoints
- CvT: Introducing Convolutions to Vision Transformers
- Rethinking Neural Operations for Diverse Tasks
- Adaptive Methods for Real-World Domain Generalization
- Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples
- LASER: Learning a Latent Action Space for Efficient Reinforcement Learning
- Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Framework
- Multiscale Clustering of Hyperspectral Images Through Spectral-Spatial Diffusion Geometry
- [Reproducibility Report] Rigging the Lottery: Making All Tickets Winners
- eDarkTrends: Harnessing Social Media Trends in Substance use disorders for Opioid Listings on Cryptomarket
- Shrinking Bigfoot: Reducing wav2vec 2.0 footprint
- Compositional Abstraction Error and a Category of Causal Models
- Privacy and Trust Redefined in Federated Machine Learning
- Towards An Ethics-Audit Bot
- Automation: An Essential Component Of Ethical AI?
- Retraining DistilBERT for a Voice Shopping Assistant by Using Universal Dependencies
- Enhanced Boundary Learning for Glass-like Object Segmentation
- Evaluation of Correctness in Unsupervised Many-to-Many Image Translation
- Slimmable Compressive Autoencoders for Practical Neural Image Compression
- Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention
- CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems
- von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learning
- StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
- Self-Constructing Neural Networks Through Random Mutation
- ViViT: A Video Vision Transformer
- The Sample Complexity of Distribution-Free Parity Learning in the Robust Shuffle Model
- Memory Enhanced Embedding Learning for Cross-Modal Video-Text Retrieval
- Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation
- A Model-Based Approach to Synthetic Data Set Generation for Patient-Ventilator Waveforms for Machine Learning and Educational Use
- Omniscient Video Super-Resolution
- Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation
- Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers
- On the Adversarial Robustness of Vision Transformers
- Competing Adaptive Networks
- Unified Graph Structured Models for Video Understanding
- The EM Algorithm is Adaptively-Optimal for Unbalanced Symmetric Gaussian Mixtures
- Machine learning based digital twin for stochastic nonlinear multi-degree of freedom dynamical system
- Regular Polytope Networks
All 214
- Learning Generative Models of Textured 3D Meshes from Real-World Images
- English-Twi Parallel Corpus for Machine Translation
- Shape-constrained Symbolic Regression -- Improving Extrapolation with Prior Knowledge
- Graph Classification by Mixture of Diverse Experts
- SetVAE: Learning Hierarchical Composition for Generative Modeling of Set-Structured Data
- GNeRF: GAN-based Neural Radiance Field without Posed Camera
- Product semantics translation from brain activity via adversarial learning
- Graph-based Facial Affect Analysis: A Review
- RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
- A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos
- MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
- IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction
- Busy-Quiet Video Disentangling for Video Classification
- Supporting verification of news articles with automated search for semantically similar articles
- Performance Analysis of Out-of-Distribution Detection on Various Trained Neural Networks
- Classification of Seeds using Domain Randomization on Self-Supervised Learning Frameworks
- Contrastive Explanations of Plans Through Model Restrictions
- HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences
- Enhancing the Transferability of Adversarial Attacks through Variance Tuning
- Risk Bounds for Learning via Hilbert Coresets
- Tracking 6-DoF Object Motion from Events and Frames
- RAN-GNNs: breaking the capacity limits of graph neural networks
- Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
- Structure Learning of Contextual Markov Networks using Marginal Pseudo-likelihood
- SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events
- Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularization
- Cloud2Curve: Generation and Vectorization of Parametric Sketches
- An Adversarial Human Pose Estimation Network Injected with Graph Structure
- Learning on heterogeneous graphs using high-order relations
- Score-oriented loss (SOL) functions
- Tuning of extended state observer with neural network-based control performance assessment
- Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition
- Context-aware short-term interest first model for session-based recommendation
- Photoacoustic image synthesis with generative adversarial networks
- Context Modeling in 3D Human Pose Estimation: A Unified Perspective
- Remote Sensing Image Translation via Style-Based Recalibration Module and Improved Style Discriminator
- Structure of Multiple Mirror System from Kaleidoscopic Projections of Single 3D Point
- Retrieving Event-related Human Brain Dynamics from Natural Sentence Reading
- Tracking Based Semi-Automatic Annotation for Scene Text Videos
- ClaRe: Practical Class Incremental Learning By Remembering Previous Class Representations
- Adaptive Surface Normal Constraint for Depth Estimation
- ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training
- NLP for Ghanaian Languages
- Dual-Parameterized Quantum Circuit GAN Model in High Energy Physics
- PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
- Category-Adaptive Domain Adaptation for Semantic Segmentation
- A Hierarchical Approach to Remote Sensing Scene Classification
- Capsule Network is Not More Robust than Convolutional Network
- Monitoring Object Detection Abnormalities via Data-Label and Post-Algorithm Abstractions
- Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
- Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining
- Pairing Character Classes in a Deathmatch Shooter Game via a Deep-Learning Surrogate Model
- Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks
- Dynamic Network Embedding Survey
- Deep Image Compositing
- CNN-based search model underestimates attention guidance by simple visual features
- Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model
- Transformer Tracking
- Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing
- Efficient Explanations from Empirical Explainers
- PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
- FocusedDropout for Convolutional Neural Network
- Translating Numerical Concepts for PDEs into Neural Architectures
- A Dataset and Benchmark Towards Multi-Modal Face Anti-Spoofing Under Surveillance Scenarios
- Self-Supervised Visibility Learning for Novel View Synthesis
- Mining Latent Classes for Few-shot Segmentation
- SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud
- No frame left behind: Full Video Action Recognition
- Lagrangian Objective Function Leads to Improved Unforeseen Attack Generalization in Adversarial Training
- Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
- AlignMixup: Improving Representations By Interpolating Aligned Features
- Joint Resource Management for MC-NOMA: A Deep Reinforcement Learning Approach
- Robust Reinforcement Learning under model misspecification
- Contextual Scene Augmentation and Synthesis via GSACNet
- Attention-guided Image Compression by Deep Reconstruction of Compressive Sensed Saliency Skeleton
- Joint User Association and Power Allocation in Heterogeneous Ultra Dense Network via Semi-Supervised Representation Learning
- Visual Distant Supervision for Scene Graph Generation
- Embedding API Dependency Graph for Neural Code Generation
- Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding
- Private Non-smooth Empirical Risk Minimization and Stochastic Convex Optimization in Subquadratic Steps
- Refractive Light-Field Features for Curved Transparent Objects in Structure from Motion
- LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis
- Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
- FixNorm: Dissecting Weight Decay for Training Deep Neural Networks
- Variational Rejection Particle Filtering
- A bandit-learning approach to multifidelity approximation
- Stiff Neural Ordinary Differential Equations
- Multi-facet Universal Schema
- Changing the Mind of Transformers for Topically-Controllable Language Generation
- Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
- POSEFusion: Pose-guided Selective Fusion for Single-view Human Volumetric Capture
- Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications
- Centrality Meets Centroid: A Graph-based Approach for Unsupervised Document Summarization
- Fooling LiDAR Perception via Adversarial Trajectory Perturbation
- Classifying Video based on Automatic Content Detection Overview
- TFPose: Direct Human Pose Estimation with Transformers
- Bayesian Attention Networks for Data Compression
- Whitening Sentence Representations for Better Semantics and Faster Retrieval
- Onfocus Detection: Identifying Individual-Camera Eye Contact from Unconstrained Images
- Checkerboard Context Model for Efficient Learned Image Compression
- Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays
- A Comparative Evaluation of Predominant Deep Learning Quantified Stock Trading Strategies
- LiDAR R-CNN: An Efficient and Universal 3D Object Detector
- Elsa: Energy-based learning for semi-supervised anomaly detection
- Best-Buddy GANs for Highly Detailed Image Super-Resolution
- "Weak AI" is Likely to Never Become "Strong AI", So What is its Greatest Value for us?
- Monocular 3D Vehicle Detection Using Uncalibrated Traffic Cameras through Homography
- Transitional Learning: Exploring the Transition States of Degradation for Blind Super-resolution
- Generalizing to the Open World: Deep Visual Odometry with Online Adaptation
- Zero-shot Adversarial Quantization
- One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
- Deep reinforcement learning of event-triggered communication and control for multi-agent cooperative transport
- A More Fine-Grained Aspect-Sentiment-Opinion Triplet Extraction Task
- Bayesian Deep Basis Fitting for Depth Completion with Uncertainty