Papers
Wed 24 Mar 2021
158 papers
- FastMoE: A Fast Mixture-of-Expert Training SystemMixture-of-experts → Efficient MoE training and inference systems
- On Imitation Learning of Linear Control Policies: Enforcing Stability and Robustness Constraints via LMI ConditionsOffline RL and imitation learning from data → Imitation learning methods
- US Fatal Police Shooting Analysis and Prediction
- Voice Privacy with Smart Digital Assistants in Educational Settings
- Drug Recommendation System based on Sentiment Analysis of Drug Reviews using Machine Learning
- NaturalProofs: Mathematical Theorem Proving in Natural Language
- Pyfectious: An individual-level simulator to discover optimal containment polices for epidemic diseases
- Toward Building Science Discovery Machines
- Quantum Mechanics and Machine Learning Synergies: Graph Attention Neural Networks to Predict Chemical Reactivity
- An Empirical Analysis of Image-Based Learning Techniques for Malware Classification
- A Novel Adaptive Minority Oversampling Technique for Improved Classification in Data Imbalanced Scenarios
- FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning
- CNN vs ELM for Image-Based Malware Classification
- Improving Editorial Workflow and Metadata Quality at Springer Nature
- Ontology-Based Recommendation of Editorial Products
- Analysis of Truncated Orthogonal Iteration for Sparse Eigenvector Problems
- Conditions and Assumptions for Constraint-based Causal Structure Learning
- The Duality of Data and Knowledge Across the Three Waves of AI
- A Broad Study on the Transferability of Visual Representations with Contrastive Learning
- Tracking Pedestrian Heads in Dense Crowd
- Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence
- Addressing catastrophic forgetting for medical domain expansion
- A Variational Inequality Approach to Bayesian Regression Games
- 3D Reasoning for Unsupervised Anomaly Detection in Pediatric WbMRI
- Similarity-Based Equational Inference in Physics
- Machine Learning-based Automatic Graphene Detection with Color Correction for Optical Microscope Images
- Feature Weighted Non-negative Matrix Factorization
- Entropy Minimizing Matrix Factorization
- Semi-Supervised Learning for Bone Mineral Density Estimation in Hip X-ray Images
- A Survey of Multimedia Technologies and Robust Algorithms
- Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case
- Why Do Local Methods Solve Nonconvex Problems?
- Under Pressure: Learning to Detect Slip with Barometric Tactile Sensors
- Matched sample selection with GANs for mitigating attribute confounding
- A Portable, Self-Contained Neuroprosthetic Hand with Deep Learning-Based Finger Control
- DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
- ModGNN: Expert Policy Approximation in Multi-Agent Systems with a Modular Graph Neural Network Architecture
- A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision
- Blind Speech Separation and Dereverberation using Neural Beamforming
- StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands
- A Framework for 3D Tracking of Frontal Dynamic Objects in Autonomous Cars
- TagMe: GPS-Assisted Automatic Object Annotation in Videos
- Multi-Label Classification Neural Networks with Hard Logical Constraints
- Learning to Generate Code Comments from Class Hierarchies
- Diverse Branch Block: Building a Convolution as an Inception-like Unit
- Foreground color prediction through inverse compositing
- Active Multitask Learning with Committees
- Mixture Density Network Estimation of Continuous Variable Maximum Likelihood Using Discrete Training Samples
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
- Vision Transformers for Dense Prediction
- Scalable Pareto Front Approximation for Deep Multi-Objective Learning
- Generating Novel Scene Compositions from Single Images and Videos
- Automated Mapping of Vulnerability Advisories onto their Fix Commits in Open Source Repositories
- Affective Processes: stochastic modelling of temporal context for emotion and facial expression recognition
- Structured Co-reference Graph Attention for Video-grounded Dialogue
- A Two-Stage Variable Selection Approach for Correlated High Dimensional Predictors
- Bag of Tricks for Node Classification with Graph Neural Networks
- The Shapley Value of coalition of variables provides better explanations
- Object Localization Through a Single Multiple-Model Convolutional Neural Network with a Specific Training Approach
- Truth and Subjunctive Theories of Knowledge: No Luck?
- DNN Quantization with Attention
- Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types
- Are Multilingual Models Effective in Code-Switching?
- Information-based Disentangled Representation Learning for Unsupervised MR Harmonization
- AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild
- FakeMix Augmentation Improves Transparent Object Detection
- Safe Linear-Quadratic Dual Control with Almost Sure Performance Guarantee
- When Word Embeddings Become Endangered
- Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages
- Address Behaviour Vulnerabilities in the Next Generation of Autonomous Robots
- CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL
- Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications
- Dynamic Slimmable Network
- Learning Versatile Neural Architectures by Propagating Network Codes
- Generic Merging of Structure from Motion Maps with a Low Memory Footprint
- Structure-Aware Face Clustering on a Large-Scale Graph with bf107 Nodes
- DRO: Deep Recurrent Optimizer for Video to Depth
- On Preference Learning Based on Sequential Bayesian Optimization with Pairwise Comparison
- The Blessings of Unlabeled Background in Untrimmed Videos
- PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation
- Language learnability in the limit for general metrics: a Gold-Angluin result
- M3DSSD: Monocular 3D Single Stage Object Detector
- Learning Polar Encodings for Arbitrary-Oriented Ship Detection in SAR Images
- Multi-Agent Off-Policy TD Learning: Finite-Time Analysis with Near-Optimal Sample Complexity and Communication Complexity
- Unsupervised collaborative learning using privileged information
- Temporal Context Aggregation Network for Temporal Action Proposal Refinement
- Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
- Representing Numbers in NLP: a Survey and a Vision
- Vulnerability of Appearance-based Gaze Estimation
- Behavior coordination for self-adaptive robots using constraint-based configuration
- Black-box Detection of Backdoor Attacks with Limited Information and Data
- Learning Graph Representation by Aggregating Subgraphs via Mutual Information Maximization
- Towards Both Accurate and Robust Neural Networks without Extra Data
- MIcro-Surgical Anastomose Workflow recognition challenge report
- A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios
- W2WNet: a two-module probabilistic Convolutional Neural Network with embedded data cleansing functionality
- Finnish Paraphrase Corpus
- Repetitive Activity Counting by Sight and Sound
- Greedy-Based Feature Selection for Efficient LiDAR SLAM
- Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases
All 158
- Shift-and-Balance Attention
- Finetuning Pretrained Transformers into RNNs
- Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
- Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information
- Towards a General Framework to Embed Advanced Machine Learning in Process Control Systems
- Minimax Regret for Stochastic Shortest Path
- Knowledge-aware Contrastive Molecular Graph Learning
- MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
- Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications
- Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
- Thinking Aloud: Dynamic Context Generation Improves Zero-Shot Reasoning Performance of GPT-2
- Czert -- Czech BERT-like Model for Language Representation
- Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
- Jo-SRC: A Contrastive Approach for Combating Noisy Labels
- Lightweight Image Super-Resolution with Multi-scale Feature Interaction Network
- AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
- The Gradient Convergence Bound of Federated Multi-Agent Reinforcement Learning with Efficient Communication
- Can Vision Transformers Learn without Natural Images?
- Convex Online Video Frame Subset Selection using Multiple Criteria for Data Efficient Autonomous Driving
- deGraphCS: Embedding Variable-based Flow Graph for Neural Code Search
- Topic Modeling Genre: An Exploration of French Classical and Enlightenment Drama
- A Multi-parameter Persistence Framework for Mathematical Morphology
- UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
- Industrial Machine Tool Component Surface Defect Dataset
- X-view: Non-egocentric Multi-View 3D Object Detector
- Discriminator Augmented Model-Based Reinforcement Learning
- Including Sparse Production Knowledge into Variational Autoencoders to Increase Anomaly Detection Reliability
- From Shadow Generation to Shadow Removal
- Resonant Scanning Design and Control for Fast Spatial Sampling
- MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising
- Non-Compression Auto-Encoder for Detecting Road Surface Abnormality via Vehicle Driving Noise
- MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
- Relation-aware Instance Refinement for Weakly Supervised Visual Grounding
- One to Many: Adaptive Instrument Segmentation via Meta Learning and Dynamic Online Adaptation in Robotic Surgical Video
- Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction
- From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search
- SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing
- On a realization of motion and similarity group equivalence classes of labeled points in mathbb Rk with applications to computer vision
- RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation
- VLGrammar: Grounded Grammar Induction of Vision and Language
- Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data
- A VAE-Bayesian Deep Learning Scheme for Solar Generation Forecasting based on Dimensionality Reduction
- Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation
- Solving and Learning Nonlinear PDEs with Gaussian Processes
- Multi-view 3D Reconstruction with Transformer
- Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution
- Convergence Analysis of Nonconvex Distributed Stochastic Zeroth-order Coordinate Method
- Supporting Clustering with Contrastive Learning
- Goal Seeking Quadratic Unconstrained Binary Optimization
- Meta-Learned Invariant Risk Minimization
- Scene-Intuitive Agent for Remote Embodied Visual Grounding
- Efficient Regional Memory Network for Video Object Segmentation
- Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
- Benchmarking Deep Trackers on Aerial Videos
- Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
- Improved Estimation of Concentration Under ℓp-Norm Distance Metrics Using Half Spaces
- CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example
- Region Similarity Representation Learning