Papers
Mon 11 Oct 2021
209 papers
- Development and testing of an image transformer for explainable autonomous driving systemsEnd-to-end autonomous driving → End-to-end system architecture
- Generalization Techniques Empirically Outperform Differential Privacy against Membership InferenceLLM safety and security → Membership inference attacks
- Instance-based Label Smoothing For Better Calibrated Classification NetworksKnowledge distillation → General knowledge distillation methods
- Compact CNN Models for On-device Ocular-based User Recognition in Mobile DevicesKnowledge distillation → General knowledge distillation methods
- Topic Modeling, Clade-assisted Sentiment Analysis, and Vaccine Brand Reputation Analysis of COVID-19 Vaccine-related Facebook Comments in the Philippines
- Calling to CNN-LSTM for Rumor Detection: A Deep Multi-channel Model for Message Veracity Classification in Microblogs
- Real-time, low-cost multi-person 3D pose estimation
- Novel Features for Time Series Analysis: A Complex Networks Approach
- Time Series Analysis via Network Science: Concepts and Algorithms
- Vit-GAN: Image-to-image Translation with Vision Transformes and Conditional GANS
- Prediction of Occurrence of Extreme Events using Machine Learning
- EMDS-7: Environmental Microorganism Image Dataset Seventh Version for Multiple Object Detection Evaluation
- Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules
- Certified Patch Robustness via Smoothed Vision Transformers
- Reason induced visual attention for explainable autonomous driving
- Towards Safer Transportation: a self-supervised learning approach for traffic video deraining
- A Survey of Online Auction Mechanism Design Using Deep Learning Approaches
- A comprehensive review of Binary Neural Network
- Using UAVs for vehicle tracking and collision risk assessment at intersections
- Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations
- Mining the Weights Knowledge for Optimizing Neural Network Structures
- C3PU: Cross-Coupling Capacitor Processing Unit Using Analog-Mixed Signal In-Memory Computing for AI Inference
- Rank-based loss for learning hierarchical representations
- Learning with Algorithmic Supervision via Continuous Relaxations
- Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection
- A global convergence theory for deep ReLU implicit networks via over-parameterization
- CAPITAL: Optimal Subgroup Identification via Constrained Policy Tree Search
- Real-time EEG-based Emotion Recognition using Discrete Wavelet Transforms on Full and Reduced Channel Signals
- TCube: Domain-Agnostic Neural Time-series Narration
- Parameterizing Activation Functions for Adversarial Robustness
- Review of Kernel Learning for Intra-Hour Solar Forecasting with Infrared Sky Images and Cloud Dynamic Feature Extraction
- Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo
- Signal Processing on Cell Complexes
- Partial Variable Training for Efficient On-Device Federated Learning
- Generalizing to New Domains by Mapping Natural Language to Lifted LTL
- GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs
- Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees
- Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
- Next Period Recommendation Reality Check
- DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering
- Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
- Bayesian Regularization for Functional Graphical Models with Applications to Neuroimaging
- Spatial Data Mining of Public Transport Incidents reported in Social Media
- EchoVPR: Echo State Networks for Visual Place Recognition
- SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition
- Scalable Traffic Signal Controls using Fog-Cloud Based Multiagent Reinforcement Learning
- UrbanNet: Leveraging Urban Maps for Long Range 3D Object Detection
- Urban traffic dynamic rerouting framework: A DRL-based model with fog-cloud architecture
- HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing
- Smoothed Separable Nonnegative Matrix Factorization
- UnfairGAN: An Enhanced Generative Adversarial Network for Raindrop Removal from A Single Image
- Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs
- Learnability of the output distributions of local quantum circuits
- Satellite galaxy abundance dependency on cosmology in Magneticum simulations
- Which Samples Should be Learned First: Easy or Hard?
- Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning
- Differentiable Stereopsis: Meshes from multiple views using differentiable rendering
- We Need to Talk About Data: The Importance of Data Readiness in Natural Language Processing
- Learning Realistic Human Reposing using Cyclic Self-Supervision with 3D Shape, Pose, and Appearance Consistency
- Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
- Momentum Centering and Asynchronous Update for Adaptive Gradient Methods
- Unsupervised Neural Machine Translation with Generative Language Models Only
- Data-driven approaches for predicting spread of infectious diseases through DINNs: Disease Informed Neural Networks
- Spatial-temporal V-Net for automatic segmentation and quantification of right ventricles in gated myocardial perfusion SPECT images
- Neural Algorithmic Reasoners are Implicit Planners
- Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture
- Mesh Draping: Parametrization-Free Neural Mesh Transfer
- Density-based interpretable hypercube region partitioning for mixed numeric and categorical data
- Differentially Private Approximate Quantiles
- Learning Temporally Causal Latent Processes from General Temporal Data
- Using Document Similarity Methods to create Parallel Datasets for Code Translation
- Calibrate your listeners! Robust communication-based training for pragmatic speakers
- Bottom-Up Constituency Parsing and Nested Named Entity Recognition with Pointer Networks
- Safe Reinforcement Learning Using Robust Control Barrier Functions
- Estimating IRI based on pavement distress type, density, and severity: Insights from machine learning techniques
- Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling
- Machine Learning for the Control and Monitoring of Electric Machine Drives: Advances and Trends
- Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching
- CASPR: A Commonsense Reasoning-based Conversational Socialbot
- Towards Streaming Egocentric Action Anticipation
- SignBERT: Pre-Training of Hand-Model-Aware Representation for Sign Language Recognition
- Point Cloud Augmentation with Weighted Local Transformations
- Multiway sparse distance weighted discrimination
- Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric
- Graph-Based Machine Learning Improves Just-in-Time Defect Prediction
- Explainable Fact-checking through Question Answering
- Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting
- Intriguing Properties of Input-dependent Randomized Smoothing
- Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference
- Graph-Guided Network for Irregularly Sampled Multivariate Time Series
- Leveraging Transformers for StarCraft Macromanagement Prediction
- Semi-Autoregressive Image Captioning
- Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
- Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks
- AMRA*: Anytime Multi-Resolution Multi-Heuristic A*
- Compositionality as we see it, everywhere around us
- Learnable Adaptive Cosine Estimator (LACE) for Image Classification
- ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
- MD Loss: Efficient Training of 3D Seismic Fault Segmentation Network under Sparse Labels by Weakening Anomaly Annotation
- Reversible Genetically Modified Mode Jumping MCMC
All 209
- Unsupervised Source Separation via Bayesian Inference in the Latent Domain
- Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Features
- You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
- On a Benefit of Mask Language Modeling: Robustness to Simplicity Bias
- Understanding Pooling in Graph Neural Networks
- Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
- Homogeneous Learning: Self-Attention Decentralized Deep Learning
- TEET! Tunisian Dataset for Toxic Speech Detection
- Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning
- Phase Collapse in Neural Networks
- Multi-institutional Validation of Two-Streamed Deep Learning Method for Automated Delineation of Esophageal Gross Tumor Volume using planning-CT and FDG-PETCT
- Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block
- Interactive Feature Fusion for End-to-End Noise-Robust Speech Recognition
- Chaos as an interpretable benchmark for forecasting and data-driven modelling
- A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generation
- Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types
- Fast Attributed Graph Embedding via Density of States
- β-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
- Continual Learning with Differential Privacy
- Multi-Task Learning for Situated Multi-Domain End-to-End Dialogue Systems
- High-order Tensor Pooling with Attention for Action Recognition
- It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data
- Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
- Navigation In Urban Environments Amongst Pedestrians Using Multi-Objective Deep Reinforcement Learning
- CLIP4Caption ++: Multi-CLIP for Video Caption
- Performance Analysis of Fractional Learning Algorithms
- TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency
- Gradual Federated Learning with Simulated Annealing
- Learning Division with Neural Arithmetic Logic Modules
- K-Wav2vec 2.0: Automatic Speech Recognition based on Joint Decoding of Graphemes and Syllables
- Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization
- Learning a subspace of policies for online adaptation in Reinforcement Learning
- Robust and Scalable SDE Learning: A Functional Perspective
- Exchangeability-Aware Sum-Product Networks
- Beyond Accuracy: A Consolidated Tool for Visual Question Answering Benchmarking
- Beyond Desktop Computation: Challenges in Scaling a GPU Infrastructure
- WeTS: A Benchmark for Translation Suggestion
- ViSeRet: A simple yet effective approach to moment retrieval via fine-grained video segmentation
- Sim2Air - Synthetic aerial dataset for UAV monitoring
- AWEU-Net: An Attention-Aware Weight Excitation U-Net for Lung Nodule Segmentation
- Offensive Language Detection with BERT-based models, By Customizing Attention Probabilities
- The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation
- REIN-2: Giving Birth to Prepared Reinforcement Learning Agents Using Reinforcement Learning Agents
- Non-Parametric Neuro-Adaptive Coordination of Multi-Agent Systems
- Pano-AVQA: Grounded Audio-Visual Question Answering on 360^circ Videos
- An automated threshold Edge Drawing algorithm
- A Comprehensive Comparison of Word Embeddings in Event & Entity Coreference Resolution
- Learning High-Speed Flight in the Wild
- Dynamic Forecasting of Conversation Derailment
- Multiple Object Trackers in OpenCV: A Benchmark
- SurroundNet: Towards Effective Low-Light Image Enhancement
- Density-Based Clustering with Kernel Diffusion
- Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation
- Feature Selection for Recommender Systems with Quantum Computing
- Deep Video Anomaly Detection: Opportunities and Challenges
- A Closer Look at Prototype Classifier for Few-shot Image Classification
- DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios
- Rethinking Person Re-Identification via Semantic-Based Pretraining
- Document-Level Text Simplification: Dataset, Criteria and Baseline
- Efficient Training of Audio Transformers with Patchout
- Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions
- Two-level Group Convolution
- Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?
- Bridging the Gap between Label- and Reference-based Synthesis in Multi-attribute Image-to-Image Translation
- LSC-GAN: Latent Style Code Modeling for Continuous Image-to-image Translation
- Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques
- Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
- Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
- Multi-View Self-Attention Based Transformer for Speaker Recognition
- Using Personality Detection Tools for Software Engineering Research: How Far Can We Go?
- When is gray-box modeling advantageous for virtual flow metering?
- Pitch Preservation In Singing Voice Synthesis
- Bid Optimization using Maximum Entropy Reinforcement Learning
- EDFace-Celeb-1M: Benchmarking Face Hallucination with a Million-scale Dataset
- The CaLiGraph Ontology as a Challenge for OWL Reasoners
- Self-supervised Learning is More Robust to Dataset Imbalance
- Online Graph Learning in Dynamic Environments
- Cross Domain Emotion Recognition using Few Shot Knowledge Transfer
- Time-varying Graph Learning Under Structured Temporal Priors
- A Survey on Proactive Customer Care: Enabling Science and Steps to Realize it
- An Information-Theoretic Analysis of The Cost of Decentralization for Learning and Inference Under Privacy Constraints
- Boosting Fast Adversarial Training with Learnable Adversarial Initialization
- Pre-trained Language Models in Biomedical Domain: A Systematic Survey
- Disturbing Target Values for Neural Network Regularization
- Exact Matching of Random Graphs with Constant Correlation
- Nonparametric Functional Analysis of Generalized Linear Models Under Nonlinear Constraints
- A Survey of Learning Criteria Going Beyond the Usual Risk
- The Skellam Mechanism for Differentially Private Federated Learning
- Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
- Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception
- COVID-Datathon: Biomarker identification for COVID-19 severity based on BALF scRNA-seq data
- Advances in Multi-turn Dialogue Comprehension: A Survey
- An Efficient Deep Learning Model for Automatic Modulation Recognition Based on Parameter Estimation and Transformation
- A Review on Part-of-Speech Technologies
- Value-Function-based Sequential Minimization for Bi-level Optimization
- A Deep Generative Model for Reordering Adjacency Matrices
- Revisit Dictionary Learning for Video Compressive Sensing under the Plug-and-Play Framework
- Label-Occurrence-Balanced Mixup for Long-tailed Recognition
- Equivalence Analysis between Counterfactual Regret Minimization and Online Mirror Descent
- Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems
- Heterogeneous Stream-reservoir Graph Networks with Data Assimilation
- BuildingNet: Learning to Label 3D Buildings
- Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition
- Towards Demystifying Representation Learning with Non-contrastive Self-supervision
- LaughNet: synthesizing laughter utterances from waveform silhouettes and a single laughter example
- NFT-K: Non-Fungible Tangent Kernels
- SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records
- Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
- Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition