Papers
Sat 27 Aug 2022
56 papers
- TrojViT: Trojan Insertion in Vision TransformersLLM safety and security → Backdoor and data poisoning attacks
- Conversion of Legal Agreements into Smart Legal Contracts using NLP
- MangoLeafBD: A Comprehensive Image Dataset to Classify Diseased and Healthy Mango Leaves
- ContrastVAE: Contrastive Variational AutoEncoder for Sequential Recommendation
- A Generic Algorithm for Top-K On-Shelf Utility Mining
- CLUDA : Contrastive Learning in Unsupervised Domain Adaptation for Semantic Segmentation
- Unsupervised Representation Learning in Deep Reinforcement Learning: A Review
- Minimal Feature Analysis for Isolated Digit Recognition for varying encoding rates in noisy environments
- Lottery Aware Sparsity Hunting: Enabling Federated Learning on Resource-Limited Edge
- Label-Efficient Self-Training for Attribute Extraction from Semi-Structured Web Documents
- Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-End Neural Diarization
- Textwash -- automated open-source text anonymisation
- Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models
- Geometrical Homogeneous Clustering for Image Data Reduction
- MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages
- SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning
- Self-Supervised Face Presentation Attack Detection with Dynamic Grayscale Snippets
- Towards Improving Unit Commitment Economics: An Add-On Tailor for Renewable Energy and Reserve Predictions
- A Diversity-Aware Domain Development Methodology
- On Biased Behavior of GANs for Face Verification
- Adversarial Robustness for Tabular Data through Cost and Utility Awareness
- Lossy Image Compression with Quantized Hierarchical VAEs
- CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks
- YOLOX-PAI: An Improved YOLOX, Stronger and Faster than YOLOv6
- LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal
- RL-DistPrivacy: Privacy-Aware Distributed Deep Inference for low latency IoT systems
- Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation
- Multi-Outputs Is All You Need For Deblur
- Improving debris flow evacuation alerts in Taiwan using machine learning
- On Unsupervised Training of Link Grammar Based Language Models
- A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck
- AesUST: Towards Aesthetic-Enhanced Universal Style Transfer
- Object Goal Navigation using Data Regularized Q-Learning
- Neural Observer with Lyapunov Stability Guarantee for Uncertain Nonlinear Systems
- Weakly and Semi-Supervised Detection, Segmentation and Tracking of Table Grapes with Limited and Noisy Data
- A Federated Learning-enabled Smart Street Light Monitoring Application: Benefits and Future Challenges
- Domain-Specific NER via Retrieving Correlated Samples
- Sub-mW Neuromorphic SNN audio processing applications with Rockpool and Xylo
- 6D Robotic Assembly Based on RGB-only Object Pose Estimation
- Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data
- Anti-Retroactive Interference for Lifelong Learning
- Tensor Decomposition based Personalized Federated Learning
- Likelihood-Free Parameter Estimation with Neural Bayes Estimators
- Virtual Control Group: Measuring Hidden Performance Metrics
- Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos
- xCloth: Extracting Template-free Textured 3D Clothes from a Monocular Image
- Consistency between ordering and clustering methods for graphs
- BOBA: Byzantine-Robust Federated Learning with Label Skewness
- A scalable pipeline for COVID-19: the case study of Germany, Czechia and Poland
- Overparameterization from Computational Constraints
- Quantifying French Document Complexity
- Network-Level Adversaries in Federated Learning
- Pipeline-Invariant Representation Learning for Neuroimaging
- RepParser: End-to-End Multiple Human Parsing with Representative Parts
- A Comprehensive Review of Digital Twin -- Part 2: Roles of Uncertainty Quantification and Optimization, a Battery Digital Twin, and Perspectives
- Neural Camera Models