Papers
Thu 21 Jul 2022
174 papers
- A Theoretical Framework for Inference and Learning in Predictive Coding NetworksWorld models → World models for navigation
- Deep Diffusion Models for Seismic ProcessingDiffusion models → Flow matching, time series and science
- Differentiable Integrated Motion Prediction and Planning with Learnable Cost Function for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Addressing Optimism Bias in Sequence Modeling for Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
- Rethinking Textual Adversarial Defense for Pre-trained Language Models
- Multi-Task Learning for Depression Detection in Dialogs
- Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning
- Solving the optimal stopping problem with reinforcement learning: an application in financial option exercise
- PirouNet: Creating Dance through Artist-Centric Deep Learning
- Inference of Regulatory Networks Through Temporally Sparse Data
- Efficient Graph-Friendly COCO Metric Computation for Train-Time Model Evaluation
- Learning Unsupervised Hierarchies of Audio Concepts
- Classifying Crop Types using Gaussian Bayesian Models and Neural Networks on GHISACONUS USGS data from NASA Hyperspectral Satellite Imagery
- Domain Generalization for Activity Recognition via Adaptive Feature Fusion
- Target Identification and Bayesian Model Averaging with Probabilistic Hierarchical Factor Probabilities
- Toward a Generic Mapping Language for Transformations between RDF and Data Interchange Formats
- Low cost prediction of probability distributions of molecular properties for early virtual screening
- Delayed Feedback in Generalised Linear Bandits Revisited
- Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
- Strategising template-guided needle placement for MR-targeted prostate biopsy
- Mean-based incomplete pairwise comparisons method with the reference values
- Data-Driven Stochastic AC-OPF using Gaussian Processes
- An advanced combination of semi-supervised Normalizing Flow & Yolo (YoloNF) to detect and recognize vehicle license plates
- Auto-regressive Image Synthesis with Integrated Quantization
- Focused Decoding Enables 3D Anatomical Detection by Transformers
- Deep Sufficient Representation Learning via Mutual Information
- Modeling User Behavior With Interaction Networks for Spam Detection
- Towards Interpretable Video Super-Resolution via Alternating Optimization
- MeshLoc: Mesh-Based Visual Localization
- TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors
- A Proposal for Foley Sound Synthesis Challenge
- DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection
- Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization
- A Transferable Recommender Approach for Selecting the Best Density Functional Approximations in Chemical Discovery
- Irrelevant Pixels are Everywhere: Find and Exclude Them for More Efficient Computer Vision
- BigIssue: A Realistic Bug Localization Benchmark
- GreenDB -- A Dataset and Benchmark for Extraction of Sustainability Information of Consumer Goods
- Explainable AI Algorithms for Vibration Data-based Fault Detection: Use Case-adadpted Methods and Critical Evaluation
- The trade-offs of model size in large recommendation models : A 10000 × compressed criteo-tb DLRM model (100 GB parameters to mere 10MB)
- Federated Semi-Supervised Domain Adaptation via Knowledge Transfer
- Heterogeneous Ensemble Learning for Enhanced Crash Forecasts -- A Frequentest and Machine Learning based Stacking Framework
- Fusing Frame and Event Vision for High-speed Optical Flow for Edge Application
- Synthetic Dataset Generation for Adversarial Machine Learning Research
- JAWS: Auditing Predictive Uncertainty Under Covariate Shift
- Interpretable Boosted Decision Tree Analysis for the Majorana Demonstrator
- Efficient model compression with Random Operation Access Specific Tile (ROAST) hashing
- A machine learning based approach to gravitational lens identification with the International LOFAR Telescope
- R2P: A Deep Learning Model from mmWave Radar to Point Cloud
- Correcting Model Bias with Sparse Implicit Processes
- ME-GAN: Learning Panoptic Electrocardio Representations for Multi-view ECG Synthesis Conditioned on Heart Diseases
- Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions
- TinyViT: Fast Pretraining Distillation for Small Vision Transformers
- Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset
- Neural Pixel Composition: 3D-4D View Synthesis from Multi-Views
- Generalizable Patch-Based Neural Rendering
- In Defense of Online Models for Video Instance Segmentation
- Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
- Novel Class Discovery without Forgetting
- Deep Learning of Radiative Atmospheric Transfer with an Autoencoder
- Generative Multiplane Images: Making a 2D GAN 3D-Aware
- A Dynamical Systems Algorithm for Clustering in Hyperspectral Imagery
- MetaComp: Learning to Adapt for Online Depth Completion
- Leveraging Natural Supervision for Language Representation Learning and Generation
- A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing
- Deep Statistic Shape Model for Myocardium Segmentation
- Approximate Differentiable Rendering with Algebraic Surfaces
- Unsupervised pre-training of graph transformers on patient population graphs
- Boosting 3D Object Detection via Object-Focused Image Fusion
- Designing An Illumination-Aware Network for Deep Image Relighting
- Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression
- CheckINN: Wide Range Neural Network Verification in Imandra (Extended)
- Careful What You Wish For: on the Extraction of Adversarially Trained Models
- MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
- A Primer on Topological Data Analysis to Support Image Analysis Tasks in Environmental Science
- Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
- Unveiling the Latent Space Geometry of Push-Forward Generative Models
- Estimating value at risk: LSTM vs. GARCH
- Neural Network Learning of Chemical Bond Representations in Spectral Indices and Features
- NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages
- Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition
- MQRetNN: Multi-Horizon Time Series Forecasting with Retrieval Augmentation
- A cost effective eye movement tracker based wheel chair control algorithm for people with paraplegia
- Multi-modal Retinal Image Registration Using a Keypoint-Based Vessel Structure Aligning Network
- Towards Efficient Adversarial Training on Vision Transformers
- Generating and Detecting True Ambiguity: A Forgotten Danger in DNN Supervision Testing
- Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion
- Online Localisation and Colored Mesh Reconstruction Architecture for 3D Visual Feedback in Robotic Exploration Missions
- Metropolis Monte Carlo sampling: convergence, localization transition and optimality
- Bayesian Recurrent Units and the Forward-Backward Algorithm
- Towards Confident Detection of Prostate Cancer using High Resolution Micro-ultrasound
- LPYOLO: Low Precision YOLO for Face Detection on FPGA
- Wer ist schuld, wenn Algorithmen irren? Entscheidungsautomatisierung, Organisationen und Verantwortung
- Fast Data Driven Estimation of Cluster Number in Multiplex Images using Embedded Density Outliers
- Semantic-Aware Fine-Grained Correspondence
- Magic ELF: Image Deraining Meets Association Learning and Transformer
- An Efficient Spatio-Temporal Pyramid Transformer for Action Detection
- Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration
- COBRA: Cpu-Only aBdominal oRgan segmentAtion
- Estimation of Non-Crossing Quantile Regression Process with Deep ReQU Neural Networks
- Deep Audio Waveform Prior
All 174
- Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation
- Human Trajectory Prediction via Neural Social Physics
- DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network
- StreamYOLO: Real-time Object Detection for Streaming Perception
- The Neural Race Reduction: Dynamics of Abstraction in Gated Networks
- KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo
- Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning
- Sequence Models for Drone vs Bird Classification
- Semantic-aware Modular Capsule Routing for Visual Question Answering
- Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
- Correspondence Matters for Video Referring Expression Comprehension
- D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights
- CodeT: Code Generation with Generated Tests
- Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives
- FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling
- Error Compensation Framework for Flow-Guided Video Inpainting
- On the Implementation of a Reinforcement Learning-based Capacity Sharing Algorithm in O-RAN
- NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition
- Pose for Everything: Towards Category-Agnostic Pose Estimation
- Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing
- Temporal Saliency Query Network for Efficient Video Recognition
- Multi-Asset Closed-Loop Reservoir Management Using Deep Reinforcement Learning
- Land Classification in Satellite Images by Injecting Traditional Features to CNN Models
- EC-KitY: Evolutionary Computation Tool Kit in Python with Seamless Machine Learning Integration
- LocVTP: Video-Text Pre-training for Temporal Localization
- Unimodal vs. Multimodal Siamese Networks for Outfit Completion
- Learning from Data with Noisy Labels Using Temporal Self-Ensemble
- Auto Machine Learning for Medical Image Analysis by Unifying the Search on Data Augmentation and Neural Architecture
- CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
- Language Model Cascades
- UFO: Unified Feature Optimization
- Efficient Search of Multiple Neural Architectures with Different Complexities via Importance Sampling
- Reinforcement learning for Energies of the future and carbon neutrality: a Challenge Design
- Enhancing Generative Networks for Chest Anomaly Localization through Automatic Registration-Based Unpaired-to-Pseudo-Paired Training Data Translation
- OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search
- Efficient CNN Architecture Design Guided by Visualization
- AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection
- SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer
- Semi-Supervised Learning of Optical Flow by Flow Supervisor
- AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields
- A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration
- UniFed: All-In-One Federated Learning Platform to Unify Open-Source Frameworks
- Knowledge-enhanced Black-box Attacks for Recommendations
- Detecting Small Query Graphs in A Large Graph via Neural Subgraph Search
- On an Edge-Preserving Variational Model for Optical Flow Estimation
- Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
- Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
- Action2Score: An Embedding Approach To Score Player Action
- Affective Behavior Analysis using Action Unit Relation Graph and Multi-task Cross Attention
- Image Generation Network for Covert Transmission in Online Social Network
- AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance
- A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks
- Towards Accurate Open-Set Recognition via Background-Class Regularization
- Comparative Study on Supervised versus Semi-supervised Machine Learning for Anomaly Detection of In-vehicle CAN Network
- Grounding Visual Representations with Texts for Domain Generalization
- Multi Resolution Analysis (MRA) for Approximate Self-Attention
- One-vs-the-Rest Loss to Focus on Important Samples in Adversarial Training
- An Evolutionary Game based Secure Clustering Protocol with Fuzzy Trust Evaluation and Outlier Detection for Wireless Sensor Networks
- Gradient-based Point Cloud Denoising with Uniformity
- Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification
- ProMix: Combating Label Noise via Maximizing Clean Sample Utility
- Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context
- DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta
- Human-centric Image Cropping with Partition-aware and Content-preserving Features
- FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
- Region Aware Video Object Segmentation with Deep Motion Modeling
- Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis
- SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition
- SplitMixer: Fat Trimmed From MLP-like Models
- GBDF: Gender Balanced DeepFake Dataset Towards Fair DeepFake Detection
- The Birth of Bias: A case study on the evolution of gender bias in an English language model
- Unsupervised Legendre-Galerkin Neural Network for Singularly Perturbed Partial Differential Equations
- Differentially Private Partial Set Cover with Applications to Facility Location
- SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks