Papers
Mon 19 Apr 2021
189 papers
- Manipulating SGD with Data Ordering AttacksLLM safety and security → Backdoor and data poisoning attacks
- Approximated Multi-Agent Fitted Q IterationOffline RL and imitation learning from data → Offline RL algorithms
- Multi-Modal Fusion Transformer for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
- Protecting the Intellectual Properties of Deep Neural Networks with an Additional Class and Steganographic ImagesLLM safety and security → Watermarking generated content and models
- Compact CNN Structure Learning by Knowledge DistillationKnowledge distillation → General knowledge distillation methods
- Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement LearningMixture-of-experts → MoE in reinforcement learning and robotics
- Distilling Knowledge via Knowledge ReviewKnowledge distillation → General knowledge distillation methods
- Anchor Nodes Positioning for Self-localization in Wireless Sensor Networks using Belief Propagation and Evolutionary Algorithms
- PyPlutchik: visualising and comparing emotion-annotated corpora
- NeRD: Neural 3D Reflection Symmetry Detector
- Federated Word2Vec: Leveraging Federated Learning to Encourage Collaborative Representation Learning
- Natural Language Generation Using Link Grammar for General Conversational Intelligence
- End-to-End Jet Classification of Boosted Top Quarks with the CMS Open Data
- Applying Convolutional Neural Networks for Stock Market Trends Identification
- Image Modeling with Deep Convolutional Gaussian Mixture Models
- A Novel Interaction-based Methodology Towards Explainable AI with Better Understanding of Pneumonia Chest X-ray Images
- Generalized-TODIM Method for Multi-criteria Decision Making with Basic Uncertain Information and its Application
- Randomized Algorithms for Scientific Computing (RASC)
- Modeling Classroom Occupancy using Data of WiFi Infrastructure in a University Campus
- Adaptive learning for financial markets mixing model-based and model-free RL for volatility targeting
- SALAD: Self-Adaptive Lightweight Anomaly Detection for Real-time Recurrent Time Series
- Multi-target prediction for dummies using two-branch neural networks
- When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
- Estimating Traffic Speeds using Probe Data: A Deep Neural Network Approach
- Suppressing simulation bias using multi-modal data
- skweak: Weak Supervision Made Easy for NLP
- Learning GMMs with Nearly Optimal Robustness Guarantees
- Calibration and Consistency of Adversarial Surrogate Losses
- "Don't quote me on that": Finding Mixtures of Sources in News Articles
- Modeling "Newsworthiness" for Lead-Generation Across Corpora
- Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
- Memory Efficient 3D U-Net with Reversible Mobile Inverted Bottlenecks for Brain Tumor Segmentation
- NewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)
- Neural Language Models with Distant Supervision to Identify Major Depressive Disorder from Clinical Notes
- A New Class of Efficient Adaptive Filters for Online Nonlinear Modeling
- Refining Targeted Syntactic Evaluation of Language Models
- Quaternion Generative Adversarial Networks
- Inference of Upcoming Human Grasp Using EMG During Reach-to-Grasp Movement
- Engineering Sketch Generation for Computer-Aided Design
- Operationalizing a National Digital Library: The Case for a Norwegian Transformer Model
- ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
- Semantic Knowledge Discovery and Discussion Mining of Incel Online Community: Topic modeling
- ELECTRAMed: a new pre-trained language representation model for biomedical NLP
- Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approach
- Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information
- LaTeX-Numeric: Language-agnostic Text attribute eXtraction for E-commerce Numeric Attributes
- Probing Commonsense Explanation in Dialogue Response Generation
- Extracting Temporal Event Relation with Syntax-guided Graph Transformer
- A Framework using Contrastive Learning for Classification with Noisy Labels
- Learning to Communicate with Strangers via Channel Randomisation Methods
- Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
- Can Latent Alignments Improve Autoregressive Machine Translation?
- Comparing Correspondences: Video Prediction with Correspondence-wise Losses
- Attention in Attention Network for Image Super-Resolution
- Temporal Query Networks for Fine-grained Video Understanding
- NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets
- Bayesian Uncertainty and Expected Gradient Length -- Regression: Two Sides Of The Same Coin?
- Automatic glissade determination through a mathematical model in electrooculographic records
- Interpreting intermediate convolutional layers of generative CNNs trained on waveforms
- Interpretability in deep learning for finance: a case study for the Heston model
- Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior
- Few-shot learning via tensor hallucination
- Entropy-based Optimization via A* Algorithm for Parking Space Recommendation
- Bayesian Algorithm Execution: Estimating Computable Properties of Black-box Functions Using Mutual Information
- A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
- Few-Shot Model Adaptation for Customized Facial Landmark Detection, Segmentation, Stylization and Shadow Removal
- Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs
- Inharmonious Region Localization
- Epsilon Consistent Mixup: Structural Regularization with an Adaptive Consistency-Interpolation Tradeoff
- What can human minimal videos tell us about dynamic recognition models?
- One More Check: Making "Fake Background" Be Tracked Again
- Provable Robustness of Adversarial Training for Learning Halfspaces with Noise
- Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy
- Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers
- Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
- Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
- Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation
- Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training
- OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
- Agent-Centric Representations for Multi-Agent Reinforcement Learning
- Probing for Bridging Inference in Transformer Language Models
- TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime
- Beyond Joint Demosaicking and Denoising: An Image Processing Pipeline for a Pixel-bin Image Sensor
- Continual Learning in Sensor-based Human Activity Recognition: an Empirical Benchmark Analysis
- Algoritmos de miner'ia de datos en la industria sanitaria
- Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence
- A Two-stage Deep Network for High Dynamic Range Image Reconstruction
- A Joint Energy and Latency Framework for Transfer Learning over 5G Industrial Edge Networks
- BM-NAS: Bilevel Multimodal Neural Architecture Search
- A Hierarchical Coding Scheme for Glasses-free 3D Displays Based on Scalable Hybrid Layered Representation of Real-World Light Fields
- Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
- A Multi-Task Deep Learning Framework for Building Footprint Segmentation
- Non-linear Functional Modeling using Neural Networks
- DANICE: Domain adaptation without forgetting in neural image compression
- Adversarial Diffusion Attacks on Graph-based Traffic Prediction Models
- Deep Reinforcement Learning in a Monetary Model
- Contrastive Learning for Compact Single Image Dehazing
- Single-view robot pose and joint angle estimation via render & compare
- A speckle filter for Sentinel-1 SAR Ground Range Detected data based on Residual Convolutional Neural Networks
- Learning to Sparsify Travelling Salesman Problem Instances
All 189
- Random Reshuffling with Variance Reduction: New Analysis and Better Rates
- Code Structure Guided Transformer for Source Code Summarization
- Investigating Outdoor Recognition Performance of Infrared Beacons for Infrastructure-based Localization
- Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting
- A Mathematical Analysis of Learning Loss for Active Learning in Regression
- Reinforcement learning for linear-convex models with jumps via stability analysis of feedback controls
- Transcriptome-wide prediction of prostate cancer gene expression from histopathology images using co-expression based convolutional neural networks
- Vision-Based Guidance for Tracking Dynamic Objects
- LAFEAT: Piercing Through Adversarial Defenses with Latent Features
- Multi-person Implicit Reconstruction from a Single Image
- Fitbeat: COVID-19 Estimation based on Wristband Heart Rate
- Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
- Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video
- Non-Linear Fusion for Self-Paced Multi-View Clustering
- Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation
- Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors
- LSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network
- BERTi'c -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian
- Continual Learning with Fully Probabilistic Models
- Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study
- Multi-context Attention Fusion Neural Network for Software Vulnerability Identification
- Coarse-to-Fine Searching for Efficient Generative Adversarial Networks
- Overcoming Catastrophic Forgetting with Gaussian Mixture Replay
- SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes
- Removing Adversarial Noise in Class Activation Feature Space
- Mixtures of Gaussian Processes for regression under multiple prior distributions
- Cyclist Intention Detection: A Probabilistic Approach
- Direction-Aggregated Attack for Transferable Adversarial Examples
- LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
- Bidirectional Interaction between Visual and Motor Generative Models using Predictive Coding and Active Inference
- Conditional Variational Capsule Network for Open Set Recognition
- Self-Paced Uncertainty Estimation for One-shot Person Re-Identification
- Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition
- ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
- Restoration of Video Frames from a Single Blurred Image with Motion Understanding
- RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration using Invariant Compatibility
- Bribery as a Measure of Candidate Success: Complexity Results for Approval-Based Multiwinner Rules
- SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization
- DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
- TetraPackNet: Four-Corner-Based Object Detection in Logistics Use-Cases
- SAS: A Simple, Accurate and Scalable Node Classification Algorithm
- Locate Who You Are: Matching Geo-location to Text for User Identity Linkage
- TransCrowd: weakly-supervised crowd counting with transformers
- No comments: Addressing commentary sections in websites' analyses
- Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
- Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
- Multi-fold Correlation Attention Network for Predicting Traffic Speeds with Heterogeneous Frequency
- Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics
- UVCE-IIITT@DravidianLangTech-EACL2021: Tamil Troll Meme Classification: You need to Pay more Attention
- A novel time-frequency Transformer based on self-attention mechanism and its application in fault diagnosis of rolling bearings
- An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks
- Improving Attribution Methods by Learning Submodular Functions
- Self-Supervised WiFi-Based Activity Recognition
- Learning Interpretable Models for Coupled Networks Under Domain Constraints
- Image Inpainting with External-internal Learning and Monochromic Bottleneck
- IIITT@LT-EDI-EACL2021-Hope Speech Detection: There is always Hope in Transformers
- Surrogate Gradient Field for Latent Space Manipulation
- Scattered Factor Universality -- The Power of the Remainder
- DA-DGCEx: Ensuring Validity of Deep Guided Counterfactual Explanations With Distribution-Aware Autoencoder Loss
- Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and Selection
- A Competitive Method to VIPriors Object Detection Challenge
- A Negation Quantum Decision Model to Predict the Interference Effect in Categorization
- RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging
- Metadata Normalization
- Autoencoders for unsupervised anomaly detection in high energy physics
- Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
- Neural Unsupervised Semantic Role Labeling
- Do We Really Need Gold Samples for Sample Weighting Under Label Noise?
- Option Tracing: Beyond Correctness Analysis in Knowledge Tracing
- BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
- Mining Latent Structures for Multimedia Recommendation
- Lidar Point Cloud Guided Monocular 3D Object Detection
- Few-shot Continual Learning: a Brain-inspired Approach
- Production vs Perception: The Role of Individuality in Usage-Based Grammar Induction
- Benchmarking the Benchmark -- Analysis of Synthetic NIDS Datasets
- Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
- TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers
- Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective
- Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
- Labels, Information, and Computation: Efficient Learning Using Sufficient Labels
- Multidimensional Scaling for Gene Sequence Data with Autoencoders
- Few-shot Learning for Topic Modeling
- Kernel Adversarial Learning for Real-world Image Super-resolution
- Sentiment Classification in Swahili Language Using Multilingual BERT
- Scalable Bayesian Deep Learning with Kernel Seed Networks
- Masked Face Recognition using ResNet-50
- Constraints Satisfiability Driven Reinforcement Learning for Autonomous Cyber Defense
- Quantum algorithms for SVD-based data representation and analysis
- Contrastive Learning Improves Model Robustness Under Label Noise