Papers
Mon 8 Aug 2022
142 papers
- Fast Offline Policy Optimization for Large Scale RecommendationOffline RL and imitation learning from data → Decision transformers and sequence modeling
- A Theoretical View on Sparsely Activated NetworksMixture-of-experts → Expert routing strategies
- SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANsKnowledge distillation → General knowledge distillation methods
- Analog Bits: Generating Discrete Data using Diffusion Models with Self-ConditioningDiffusion models → Diffusion foundations and sampling
- Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World ModelWorld models → Embodied and robot world models
- A Model Drift Detection and Adaptation Framework for 5G Core Networks
- Deep Billboards towards Lossless Real2Sim in Virtual Reality
- Automatic Detection of Noisy Electrocardiogram Signals without Explicit Noise Labels
- Predicting Pedestrian Crosswalk Behavior Using Convolutional Neural Networks
- Hard-Constrained Deep Learning for Climate Downscaling
- FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators
- A Frequency-aware Software Cache for Large Recommendation System Embeddings
- PerD: Perturbation Sensitivity-based Neural Trojan Detection Framework on NLP Applications
- Learning from imperfect training data using a robust loss function: application to brain image segmentation
- Multi-Depth Boundary-Aware Left Atrial Scar Segmentation Network
- Deep Patch Visual Odometry
- Clustering Optimisation Method for Highly Connected Biological Data
- Deep Maxout Network Gaussian Process
- Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning
- In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimation
- Denoising Induction Motor Sounds Using an Autoencoder
- NeuralVDB: High-resolution Sparse Volume Representation using Hierarchical Neural Networks
- Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
- Occlusion-Aware Instance Segmentation via BiLayer Network Architectures
- Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi-Supervised Segmentation
- Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
- Truth Set Algebra: A New Way to Prove Undefinability
- Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts
- Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Survey
- Recovering the Graph Underlying Networked Dynamical Systems under Partial Observability: A Deep Learning Approach
- Liquid State Machine-Empowered Reflection Tracking in RIS-Aided THz Communications
- A Systematic Evaluation of Response Selection for Open Domain Dialogue
- Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast
- On Taking Advantage of Opportunistic Meta-knowledge to Reduce Configuration Spaces for Automated Machine Learning
- Soft Sensors and Process Control using AI and Dynamic Simulation
- Generalization and Overfitting in Matrix Product State Machine Learning Architectures
- Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing
- Gradient Flows for L2 Support Vector Machine Training
- Learning to Identify Drilling Defects in Turbine Blades with Single Stage Detectors
- Semi-Supervised Cross-Modal Salient Object Detection with U-Structure Networks
- SDWPF: A Dataset for Spatial Dynamic Wind Power Forecasting Challenge at KDD Cup 2022
- Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
- Learning to Learn to Predict Performance Regressions in Production at Meta
- A Visual Analytics System for Improving Attention-based Traffic Forecasting Models
- Investigating Efficiently Extending Transformers for Long Input Summarization
- QSAM-Net: Rain streak removal by quaternion neural network with self-attention module
- EFI: A Toolbox for Feature Importance Fusion and Interpretation in Python
- Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets
- Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment
- 3D Vision with Transformers: A Survey
- PlaneFormers: From Sparse View Planes to 3D Reconstruction
- Boosting neural video codecs by exploiting hierarchical redundancy
- Gaze Estimation Approach Using Deep Differential Residual Network
- Continual Reinforcement Learning with TELLA
- Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
- On Rademacher Complexity-based Generalization Bounds for Deep Learning
- LWGNet: Learned Wirtinger Gradients for Fourier Ptychographic Phase Retrieval
- Self-Supervised Contrastive Representation Learning for 3D Mesh Segmentation
- Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation
- Improving performance in multi-objective decision-making in Bottles environments with soft maximin approaches
- Label-Free Synthetic Pretraining of Object Detectors
- Distinctive Image Captioning via CLIP Guided Group Optimization
- Snowpack Estimation in Key Mountainous Water Basins from Openly-Available, Multimodal Data Sources
- Differentially Private Fr'echet Mean on the Manifold of Symmetric Positive Definite (SPD) Matrices with log-Euclidean Metric
- A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation
- Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval
- A Multi-label Continual Learning Framework to Scale Deep Learning Approaches for Packaging Equipment Monitoring
- Uncertain Bayesian Networks: Learning from Incomplete Data
- A Linear Programming Approach for Resource-Aware Information-Theoretic Tree Abstractions
- Boosting Video-Text Retrieval with Explicit High-Level Semantics
- Vision-Based Activity Recognition in Children with Autism-Related Behaviors
- SIAD: Self-supervised Image Anomaly Detection System
- Object Detection Using Sim2Real Domain Randomization for Robotic Applications
- fMRI-S4: learning short- and long-range dynamic fMRI dependencies using 1D Convolutions and State Space Models
- Neural Message Passing for Visual Relationship Detection
- Understanding Masked Image Modeling via Learning Occlusion Invariant Feature
- Abstractive Meeting Summarization: A Survey
- Efficient Neural Net Approaches in Metal Casting Defect Detection
- Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctness
- Deep Machine Learning Reconstructing Lattice Topology with Strong Thermal Fluctuations
- Automatic lesion analysis for increased efficiency in outcome prediction of traumatic brain injury
- A review on longitudinal data analysis with random forest in precision medicine
- INSPIRED2: An Improved Dataset for Sociable Conversational Recommendation
- Towards Semantic Communications: Deep Learning-Based Image Semantic Coding
- Template-based Abstractive Microblog Opinion Summarisation
- Image Quality Assessment with Gradient Siamese Network
- SwISS: A Scalable Markov chain Monte Carlo Divide-and-Conquer Strategy
- Multi-Frames Temporal Abnormal Clues Learning Method for Face Anti-Spoofing
- Pairwise Learning via Stagewise Training in Proximal Setting
- Optimistic Optimisation of Composite Objective with Exponentiated Update
- GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training
- Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions
- Dataset of Industrial Metal Objects
- Rapid Flow Behavior Modeling of Thermal Interface Materials Using Deep Neural Networks
- SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty
- A Map of Diverse Synthetic Stable Roommates Instances
- Eight Years of Face Recognition Research: Reproducibility, Achievements and Open Issues
- TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training
- Channel Estimation under Hardware Impairments: Bayesian Methods versus Deep Learning
- Deep Computational Model for the Inference of Ventricular Activation Properties
All 142
- Two-Stream Networks for Object Segmentation in Videos
- Sparse Attentive Memory Network for Click-through Rate Prediction with Long Sequences
- Stain-Adaptive Self-Supervised Learning for Histopathology Image Analysis
- Solving the Online Assignment Problem with Machine Learned Advice
- Information Extraction from Scanned Invoice Images using Text Analysis and Layout Features
- Advances of Artificial Intelligence in Classical and Novel Spectroscopy-Based Approaches for Cancer Diagnostics. A Review
- Ensembled Autoencoder Regularization for Multi-Structure Segmentation for Kidney Cancer Treatment
- Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model
- Generating Coherent Narratives by Learning Dynamic and Discrete Entity States with a Contrastive Framework
- Towards lifelong learning of Recurrent Neural Networks for control design
- Aerial Monocular 3D Object Detection
- All-optical image classification through unknown random diffusers using a single-pixel diffractive network
- NPB-REC: Non-parametric Assessment of Uncertainty in Deep-learning-based MRI Reconstruction from Undersampled Data
- MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis
- Sampling Based On Natural Image Statistics Improves Local Surrogate Explainers
- Abutting Grating Illusion: Cognitive Challenge to Neural Network Models
- Extrinsic Camera Calibration with Semantic Segmentation
- AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning
- Provable Acceleration of Nesterov's Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks
- Detecting User Exits from Online Behavior: A Duration-Dependent Latent State Model
- Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images
- Adversarial robustness of VAEs through the lens of local geometry
- CSSAM:Code Search via Attention Matching of Code Semantics and Structures
- Depth Quality-Inspired Feature Manipulation for Efficient RGB-D and Video Salient Object Detection
- Dynamic Maintenance of Kernel Density Estimation Data Structure: From Practice to Theory
- SelfCoLearn: Self-supervised collaborative learning for accelerating dynamic MR imaging
- Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph
- Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration
- DialogSum Challenge: Results of the Dialogue Summarization Shared Task
- Neural Optimization Machine: A Neural Network Approach for Optimization
- Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach
- What can we know about that which we cannot even imagine?
- Clear Memory-Augmented Auto-Encoder for Surface Defect Detection
- Learning Entity Linking Features for Emerging Entities
- Creating Lexical Resources for Endangered Languages
- CheXRelNet: An Anatomy-Aware Model for Tracking Longitudinal Relationships between Chest X-Rays
- Automatically constructing Wordnet synsets
- Data-centric AI approach to improve optic nerve head segmentation and localization in OCT en face images
- Creating Reverse Bilingual Dictionaries
- Rankability and Linear Ordering Problem: New Probabilistic Insight and Algorithms
- RadSegNet: A Reliable Approach to Radar Camera Fusion
- Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality