Papers
Tue 17 Jan 2023
137 papers
- Learning Customized Visual Models with Retrieval-Augmented KnowledgeRetrieval-augmented generation → Multimodal RAG
- GLIGEN: Open-Set Grounded Text-to-Image GenerationDiffusion models → Image generation, text-to-image and editing
- Denoising Diffusion Probabilistic Models as a Defense against Adversarial AttacksDiffusion models → Robustness, privacy and adversarial aspects
- Show me what you want: Inverse reinforcement learning to automatically design robot swarms by demonstrationOffline RL and imitation learning from data → Inverse reinforcement learning
- Hierarchical Memory Pool Based Edge Semi-Supervised Continual Learning Method
- eBPF-based Working Set Size Estimation in Memory Management
- Outlier-Based Domain of Applicability Identification for Materials Property Prediction Models
- Robust Scheduling with GFlowNets
- Command Line Interface Risk Modeling
- Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search
- Leveraging Vision-Language Models for Granular Market Change Prediction
- Lowering Detection in Sport Climbing Based on Orientation of the Sensor Enhanced Quickdraw
- Sleep Activity Recognition and Characterization from Multi-Source Passively Sensed Data
- Enactive Artificial Intelligence: Subverting Gender Norms in Robot-Human Interaction
- A Semi-supervised Sensing Rate Learning based CMAB Scheme to Combat COVID-19 by Trustful Data Collection in the Crowd
- Towards the design of user-centric strategy recommendation systems for collaborative Human-AI tasks
- EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets
- Safety Verification of Neural Network Control Systems Using Guaranteed Neural Network Model Reduction
- Adversarial AI in Insurance: Pervasiveness and Resilience
- The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description
- Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness
- Curriculum Script Distillation for Multilingual Visual Question Answering
- SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping
- Causal Falsification of Digital Twins
- Learning a Formality-Aware Japanese Sentence Representation
- Dual-sPLS: a family of Dual Sparse Partial Least Squares regressions for feature selection and prediction with tunable sparsity; evaluation on simulated and near-infrared (NIR) data
- Robotic Navigation Autonomy for Subretinal Injection via Intelligent Real-Time Virtual iOCT Volume Slicing
- Artificial Neuronal Ensembles with Learned Context Dependent Gating
- Using Large Text-to-Image Models with Structured Prompts for Skin Disease Identification: A Case Study
- A Combinatorial Semi-Bandit Approach to Charging Station Selection for Electric Vehicles
- Embodied Agents for Efficient Exploration and Smart Scene Description
- COVINS-G: A Generic Back-end for Collaborative Visual-Inertial SLAM
- Revisiting mass-radius relationships for exoplanet populations: a machine learning insight
- Heterogeneous Multi-Robot Reinforcement Learning
- Mortality Prediction with Adaptive Feature Importance Recalibration for Peritoneal Dialysis Patients: a deep-learning-based study on a real-world longitudinal follow-up dataset
- On the State of German (Abstractive) Text Summarization
- Vision Learners Meet Web Image-Text Pairs
- MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module
- Are Language Models Worse than Humans at Following Prompts? It's Complicated
- A Fast Algorithm for Adaptive Private Mean Estimation
- SegViz: A federated-learning based framework for multi-organ segmentation on heterogeneous data sets with partial annotations
- Prompting Large Language Model for Machine Translation: A Case Study
- The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks
- Transformers as Algorithms: Generalization and Stability in In-context Learning
- Monotonicity for AI ethics and society: An empirical study of the monotonic neural additive model in criminology, education, health care, and finance
- Transformer Based Implementation for Automatic Book Summarization
- Preserving Privacy in Surgical Video Analysis Using Artificial Intelligence: A Deep Learning Classifier to Identify Out-of-Body Scenes in Endoscopic Videos
- ActSafe: Predicting Violations of Medical Temporal Constraints for Medication Adherence
- An Energy-Efficient Reconfigurable Autoencoder Implementation on FPGA
- Optimal Algorithms for Latent Bandits with Cluster Structure
- Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects
- Consciousness is entailed by compositional learning of new causal structures in deep predictive processing systems
- Simplistic Collection and Labeling Practices Limit the Utility of Benchmark Datasets for Twitter Bot Detection
- Dataset Distillation: A Comprehensive Review
- Which Model Shall I Choose? Cost/Quality Trade-offs for Text Classification Tasks
- Opti-CAM: Optimizing saliency maps for interpretability
- From Risk Prediction to Risk Factors Interpretation. Comparison of Neural Networks and Classical Statistics for Dementia Prediction
- Your Day in Your Pocket: Complex Activity Recognition from Smartphone Accelerometers
- Metamobility: Connecting Future Mobility with Metaverse
- Negative Flux Aggregation to Estimate Feature Attributions
- Sim-Anchored Learning for On-the-Fly Adaptation
- Statistical analysis of word flow among five Indo-European languages
- Vision Based Machine Learning Algorithms for Out-of-Distribution Generalisation
- Long Range Pooling for 3D Large-Scale Scene Understanding
- Composite Deep Network with Feature Weighting for Improved Delineation of COVID Infection in Lung CT
- RILS: Masked Visual Reconstruction in Language Semantic Space
- FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks
- Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
- DR-WLC: Dimensionality Reduction cognition for object detection and pose estimation by Watching, Learning and Checking
- Self-supervised Domain Adaptation for Breaking the Limits of Low-quality Fundus Image Quality Enhancement
- Towards Estimating Transferability using Hard Subsets
- Memory-Augmented Theory of Mind Network
- Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG Signals
- BSNet: Lane Detection via Draw B-spline Curves Nearby
- MAFUS: a Framework to predict mortality risk in MAFLD subjects
- Deep Conditional Measure Quantization
- Online Filtering over Expanding Graphs
- Cooperation Learning Enhanced Colonic Polyp Segmentation Based on Transformer-CNN Fusion
- The quantum cost function concentration dependency on the parametrization expressivity
- Multi-Biometric Fuzzy Vault based on Face and Fingerprints
- CS-lol: a Dataset of Viewer Comment with Scene in E-sports Live-streaming
- Training Methods of Multi-label Prediction Classifiers for Hyperspectral Remote Sensing Images
- Learning to solve arithmetic problems with a virtual abacus
- SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation
- Building Scalable Video Understanding Benchmarks through Sports
- A reinforcement learning path planning approach for range-only underwater target localization with autonomous vehicles
- Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs
- Event-based Shape from Polarization
- Causal Models with Constraints
- USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval
- Syntactically Robust Training on Partially-Observed Data for Open Information Extraction
- Knowledge Acquisition and Completion for Long-Term Human-Robot Interactions using Knowledge Graph Embedding
- HanoiT: Enhancing Context-aware Translation via Selective Context
- Pathfinding Neural Cellular Automata
- Follow Us and Become Famous! Insights and Guidelines From Instagram Engagement Mechanisms
- Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes
- Subgraph Centralization: A Necessary Step for Graph Anomaly Detection
- Acute ischemic stroke lesion segmentation in non-contrast CT images using 3D convolutional neural networks
- 2nd Swiss German Speech to Standard German Text Shared Task at SwissText 2022
- Multicenter automatic detection of invasive carcinoma on breast whole slide images
All 137
- Ensemble Reservoir Computing for Dynamical Systems: Prediction of Phase-Space Stable Region for Hadron Storage Rings
- A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction
- Reusable Self-Attention Recommender Systems in Fashion Industry Applications
- Temporal Dynamics of Coordinated Online Behavior: Stability, Archetypes, and Influence
- Geometric ergodicity of SGLD via reflection coupling
- FedCliP: Federated Learning with Client Pruning
- The Recent Advances in Automatic Term Extraction: A survey
- Tracing and Manipulating Intermediate Values in Neural Math Problem Solvers
- BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversation
- Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam
- Two Stage Contextual Word Filtering for Context bias in Unified Streaming and Non-streaming Transducer
- Face Inverse Rendering via Hierarchical Decoupling
- Predictive Modeling of Coronal Hole Areas Using Long Short-Term Memory Networks
- Bag of States: A Non-sequential Approach to Video-based Engagement Measurement
- FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs
- SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network
- Improved generalization with deep neural operators for engineering systems: Path towards digital twin
- Quantifying and Managing Impacts of Concept Drifts on IoT Traffic Inference in Residential ISP Networks
- Audio2Gestures: Generating Diverse Gestures from Audio
- DQNAS: Neural Architecture Search using Reinforcement Learning
- Distribution Aligned Feature Clustering for Zero-Shot Sketch-Based Image Retrieval
- From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification
- Cross-domain Self-supervised Framework for Photoacoustic Computed Tomography Image Reconstruction
- DIGITOUR: Automatic Digital Tours for Real-Estate Properties
- Rethinking Lightweight Salient Object Detection via Network Depth-Width Tradeoff
- Feature-based Image Matching for Identifying Individual K=ak=a
- Explainable, Interpretable & Trustworthy AI for Intelligent Digital Twin: Case Study on Remaining Useful Life
- Artificial intelligence as a gateway to scientific discovery: Uncovering features in retinal fundus images
- Multi-fidelity surrogate modeling for temperature field prediction using deep convolution neural network
- Multi Kernel Positional Embedding ConvNeXt for Polyp Segmentation
- Graph Learning Across Data Silos
- VaxxHesitancy: A Dataset for Studying Hesitancy towards COVID-19 Vaccination on Twitter
- Free Lunch for Generating Effective Outlier Supervision
- Probabilistic Traffic Forecasting with Dynamic Regression
- Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment
- Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks
- Scaling Deep Networks with the Mesh Adaptive Direct Search algorithm