Papers
Fri 20 Aug 2021
128 papers
- An Independent Study of Reinforcement Learning and Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving
- Early-exit deep neural networks for distorted images: providing an efficient edge offloadingEfficient LLM inference and serving → Early exit and edge inference
- Boosting of Head Pose Estimation by Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Regulating Ownership Verification for Deep Neural Networks: Scenarios, Protocols, and ProspectsLLM safety and security → Watermarking generated content and models
- Geo-Context Aware Study of Vision-Based Autonomous Driving Models and Spatial Video Data
- Knowledge Perceived Multi-modal Pretraining in E-commerce
- Addressing the IEEE AV Test Challenge with Scenic and VerifAI
- Extracting Qualitative Causal Structure with Transformer-Based NLP
- A Conditional Cascade Model for Relational Triple Extraction
- Web image search engine based on LSH index and CNN Resnet50
- A survey on Bayesian inference for Gaussian mixture model
- Improvement of a Prediction Model for Heart Failure Survival through Explainable Artificial Intelligence
- Does Adversarial Oversampling Help us?
- Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control
- Spatio-Temporal Split Learning for Privacy-Preserving Medical Platforms: Case Studies with COVID-19 CT, X-Ray, and Cholesterol Data
- Safe Transformative AI via a Windfall Clause
- A Multi-Task Learning Framework for COVID-19 Monitoring and Prediction of PPE Demand in Community Health Centres
- Beyond Tracking: Using Deep Learning to Discover Novel Interactions in Biological Swarms
- Detecting and Segmenting Adversarial Graphics Patterns from Images
- A Multiple-View Geometric Model for Specularity Prediction on General Curved Surfaces
- BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policies
- Cascade Watchdog: A Multi-tiered Adversarial Guard for Outlier Detection
- Fourier Neural Operator Networks: A Fast and General Solver for the Photoacoustic Wave Equation
- Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training
- InBiodiv-O: An Ontology for Indian Biodiversity Knowledge Management
- OSRM-CCTV: Open-source CCTV-aware routing and navigation system for privacy, anonymity and safety (Preprint)
- Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image
- Crown Jewels Analysis using Reinforcement Learning with Attack Graphs
- One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
- Temporally Nonstationary Component Analysis; Application to Noninvasive Fetal Electrocardiogram Extraction
- LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning
- Influence Selection for Active Learning
- MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition
- D-DARTS: Distributed Differentiable Architecture Search
- Data-driven Smart Ponzi Scheme Detection
- Discriminative Region-based Multi-Label Zero-Shot Learning
- Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions
- Zoom, Enhance! Measuring Surveillance GAN Up-sampling
- A Recommender System for Scientific Datasets and Analysis Pipelines
- MG-GAN: A Multi-Generator Model Preventing Out-of-Distribution Samples in Pedestrian Trajectory Prediction
- Approximate Bayesian Neural Doppler Imaging
- Efficient Online Estimation of Causal Effects by Deciding What to Observe
- Practical and Fast Momentum-Based Power Methods
- Optimal Order Simple Regret for Gaussian Process Bandits
- PowerLinear Activation Functions with application to the first layer of CNNs
- Open Relation Modeling: Learning to Define Relations between Entities
- Dual-Neighborhood Deep Fusion Network for Point Cloud Analysis
- Video Ads Content Structuring by Combining Scene Confidence Prediction and Tagging
- Extracting Radiological Findings With Normalized Anatomical Information Using a Span-Based BERT Relation Extraction Model
- Exploring Data Aggregation and Transformations to Generalize across Visual Domains
- Parsing Birdsong with Deep Audio Embeddings
- An Adaptable Deep Learning-Based Intrusion Detection System to Zero-Day Attacks
- Towards Photorealistic Colorization by Imagination
- Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer
- Quantization Backdoors to Deep Learning Commercial Frameworks
- Region-level Active Detector Learning
- Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection
- Trans4Trans: Efficient Transformer for Transparent Object and Semantic Scene Segmentation in Real-World Navigation Assistance
- Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds
- A Neural Conversation Generation Model via Equivalent Shared Memory Investigation
- State-Of-The-Art Algorithms For Low-Rank Dynamic Mode Decomposition
- VAE-CE: Visual Contrastive Explanation using Disentangled VAEs
- User Localization Based on Call Detail Records
- Contrastive Representations for Label Noise Require Fine-Tuning
- Group-based Distinctive Image Captioning with Memory Attention
- Convolutional Neural Network (CNN) vs Vision Transformer (ViT) for Digital Holography
- Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation
- Unsupervised Domain-adaptive Hash for Networks
- PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier
- Accelerating Federated Learning with a Global Biased Optimiser
- Estimation of Convex Polytopes for Automatic Discovery of Charge State Transitions in Quantum Dot Arrays
- Transfer-Recursive-Ensemble Learning for Multi-Day COVID-19 Prediction in India using Recurrent Neural Networks
- ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generation
- Semi-supervised Network Embedding with Differentiable Deep Quantisation
- TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction
- Lessons from the Clustering Analysis of a Search Space: A Centroid-based Approach to Initializing NAS
- Semantic Communication with Adaptive Universal Transformer
- Continual Learning for Image-Based Camera Localization
- Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions
- Airbert: In-domain Pretraining for Vision-and-Language Navigation
- GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps
- Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks
- A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasets
- Towards Understanding the Generative Capability of Adversarially Robust Classifiers
- DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction
- Fastformer: Additive Attention Can Be All You Need
- FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
- Structure-Preserving Deraining with Residue Channel Prior Guidance
- PASTO: Strategic Parameter Optimization in Recommendation Systems -- Probabilistic is Better than Deterministic
- Semi-supervised learning for joint SAR and multispectral land cover classification
- Kompetenzerwerbsf"orderung durch E-Assessment: Individuelle Kompetenzerfassung am Beispiel des Fachs Mathematik
- SoMeSci- A 5 Star Open Data Gold Standard Knowledge Graph of Software Mentions in Scientific Articles
- SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning
- A Contactless Fingerprint Recognition System
- AutoLay: Benchmarking amodal layout estimation for autonomous driving
- Out-of-boundary View Synthesis Towards Full-Frame Video Stabilization
- Video-based Person Re-identification with Spatial and Temporal Memory Networks
- Is it Time to Replace CNNs with Transformers for Medical Images?
- AdvDrop: Adversarial Attack to DNNs by Dropping Information
- UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning
All 128
- Federated Distributionally Robust Optimization for Phase Configuration of RISs
- Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentation
- Single Underwater Image Enhancement Using an Analysis-Synthesis Network
- Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images
- Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data
- DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
- Dual Projection Generative Adversarial Networks for Conditional Image Generation
- Spatiotemporal Texture Reconstruction for Dynamic Objects Using a Single RGB-D Camera
- Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey
- Deep Virtual Markers for Articulated 3D Shapes
- Deep Sequence Modeling: Development and Applications in Asset Pricing
- GAN Inversion for Out-of-Range Images with Geometric Transformations
- Weakly-supervised Joint Anomaly Detection and Classification
- Discriminative Domain-Invariant Adversarial Network for Deep Domain Generalization
- Distributionally Robust Learning
- Few Shot Activity Recognition Using Variational Inference
- Twitter User Representation Using Weakly Supervised Graph Embedding
- Uniformity Testing in the Shuffle Model: Simpler, Better, Faster
- SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining
- CloudShield: Real-time Anomaly Detection in the Cloud
- ASAT: Adaptively Scaled Adversarial Training in Time Series
- Application of Adversarial Examples to Physical ECG Signals
- Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling
- Plug and Play, Model-Based Reinforcement Learning
- Unified Representation of Geometric Primitives for Graph-SLAM Optimization Using Decomposed Quadrics
- Semi-supervised learning for medical image classification using imbalanced training data
- CIGLI: Conditional Image Generation from Language & Image
- Mitigating Greenhouse Gas Emissions Through Generative Adversarial Networks Based Wildfire Prediction