Papers
Wed 3 Aug 2022
148 papers
- Reinforcement Learning for Joint V2I Network Selection and Autonomous Driving PoliciesEnd-to-end autonomous driving → Cooperative and V2X driving
- Sequence Model Imitation Learning with Unobserved ContextsOffline RL and imitation learning from data → Imitation learning methods
- Robot Learning from Demonstration Using Elastic MapsOffline RL and imitation learning from data → Robot learning from demonstration
- KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled AnalysisOffline RL and imitation learning from data → Imitation learning methods
- Pyramidal Denoising Diffusion Probabilistic ModelsDiffusion models → Diffusion foundations and sampling
- Compressive Self-localization Using Relative Attribute Embedding
- Psychophysiological Arousal in Young Children Who Stutter: An Interpretable AI Approach
- Hybrid Approach to Identify Druglikeness Leading Compounds against COVID-19 3CL Protease
- Court Judgement Labeling Using Topic Modeling and Syntactic Parsing
- Content-Based Landmark Retrieval Combining Global and Local Features using Siamese Neural Networks
- Style Transfer of Black and White Silhouette Images using CycleGAN and a Randomly Generated Dataset
- DALLE-URBAN: Capturing the urban design expertise of large text to image transformers
- Human Saliency-Driven Patch-based Matching for Interpretable Post-mortem Iris Recognition
- Unifying physical systems' inductive biases in neural ODE using dynamics constraints
- Improving Meta-Learning Generalization with Activation-Based Early-Stopping
- AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning
- Deep VULMAN: A Deep Reinforcement Learning-Enabled Cyber Vulnerability Management Framework
- Bayesian regularization of empirical MDPs
- A Multibranch Convolutional Neural Network for Hyperspectral Unmixing
- Graph Neural Networks Extract High-Resolution Cultivated Land Maps from Sentinel-2 Image Series
- An Optimal Likelihood Free Method for Biological Model Selection
- Word-Level Fine-Grained Story Visualization
- Estimating Visual Information From Audio Through Manifold Learning
- Towards Generating Large Synthetic Phytoplankton Datasets for Efficient Monitoring of Harmful Algal Blooms
- Visual Analysis and Detection of Contrails in Aircraft Engine Simulations
- Differentiable Predictive Control with Safety Guarantees: A Control Barrier Function Approach
- Image-based Detection of Surface Defects in Concrete during Construction
- Counterfactual Image Synthesis for Discovery of Personalized Predictive Image Markers
- Design of secure and robust cognitive system for malware detection
- Unsupervised Flow Refinement near Motion Boundaries
- How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?
- HiCu: Leveraging Hierarchy for Curriculum Learning in Automated ICD Coding
- LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor
- GROWN+UP: A Graph Representation Of a Webpage Network Utilizing Pre-training
- Adversarial Attacks on ASR Systems: An Overview
- AdaCat: Adaptive Categorical Discretization for Autoregressive Models
- MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Training
- Quantum-Inspired Tensor Neural Networks for Partial Differential Equations
- Free-HeadGAN: Neural Talking Head Synthesis with Explicit Gaze Control
- SGEM: stochastic gradient with energy and momentum
- Large-scale Building Damage Assessment using a Novel Hierarchical Transformer Architecture on Satellite Images
- Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
- Interpretable bilinear attention network with domain adaptation improves drug-target prediction
- RealPatch: A Statistical Matching Framework for Model Patching with Real Samples
- A Study of Modeling Rising Intonation in Cantonese Neural Speech Synthesis
- On the independence between phenomenal consciousness and computational intelligence
- Multimodal sensor fusion in the latent representation space
- Machine learning optimization of Majorana hybrid nanowires
- Conv-NILM-Net, a causal and multi-appliance model for energy source separation
- SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences
- One Node at a Time: Node-Level Network Classification
- Empirical Study of Overfitting in Deep FNN Prediction Models for Breast Cancer Metastasis
- GPPF: A General Perception Pre-training Framework via Sparsely Activated Multi-Task Learning
- KPI-BERT: A Joint Named Entity Recognition and Relation Extraction Model for Financial Reports
- Subject-Specific Lesion Generation and Pseudo-Healthy Synthesis for Multiple Sclerosis Brain Images
- Masked Vision and Language Modeling for Multi-modal Representation Learning
- SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation
- Noise tolerance of learning to rank under class-conditional label noise
- LSSANet: A Long Short Slice-Aware Network for Pulmonary Nodule Detection
- Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics
- Detecting Multivariate Time Series Anomalies with Zero Known Label
- Convolutional Persistence Transforms
- Edge-Based Self-Supervision for Semi-Supervised Few-Shot Microscopy Image Cell Segmentation
- Active Learning on a Programmable Photonic Quantum Processor
- A Novel Approach To Network Intrusion Detection System Using Deep Learning For Sdn: Futuristic Approach
- Unsupervised Discovery of Semantic Concepts in Satellite Imagery with Style-based Wavelet-driven Generative Models
- Gradient descent provably escapes saddle points in the training of shallow ReLU networks
- A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval
- Efficient Fine-Tuning of Compressed Language Models with Learners
- HybridGNN: Learning Hybrid Representation in Multiplex Heterogeneous Networks
- Evaluation and comparison of eight popular Lidar and Visual SLAM algorithms
- Robots with Different Embodiments Can Express and Influence Carefulness in Object Manipulation
- AstroVision: Towards Autonomous Feature Detection and Description for Missions to Small Bodies Using Deep Learning
- Large scale analysis of gender bias and sexism in song lyrics
- AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy
- Centroids Matching: an efficient Continual Learning approach operating in the embedding space
- Template matching with white balance adjustment under multiple illuminants
- SSformer: A Lightweight Transformer for Semantic Segmentation
- Cross-lingual Approaches for the Detection of Adverse Drug Reactions in German from a Patient's Perspective
- Supervised and Reinforcement Learning from Observations in Reconnaissance Blind Chess
- YOLO-FaceV2: A Scale and Occlusion Aware Face Detector
- Neural Nets with a Newton Conjugate Gradient Method on Multiple GPUs
- Character Generation through Self-Supervised Vectorization
- Equivariant Disentangled Transformation for Domain Generalization under Combination Shift
- Vision-Based Safety System for Barrierless Human-Robot Collaboration
- Maintaining Performance with Less Data
- Gradient-based Uncertainty for Monocular Depth Estimation
- Robust PCA for Anomaly Detection and Data Imputation in Seasonal Time Series
- Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
- Adaptive Domain Generalization via Online Disagreement Minimization
- Localization and Classification of Parasitic Eggs in Microscopic Images Using an EfficientDet Detector
- Learning Object Manipulation Skills from Video via Approximate Differentiable Physics
- PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
- Augmentation Learning for Semi-Supervised Classification
- Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
- Exploration with Model Uncertainty at Extreme Scale in Real-Time Bidding
- Negative Frames Matter in Egocentric Visual Query 2D Localization
- Decay2Distill: Leveraging spatial perturbation and regularization for self-supervised image denoising
- PalQuant: Accelerating High-precision Networks on Low-precision Accelerators
All 148
- SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud
- Per-Clip Video Object Segmentation
- Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks
- DeepProphet2 -- A Deep Learning Gene Recommendation Engine
- Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding
- N-RPN: Hard Example Learning for Region Proposal Networks
- EgPDE-Net: Building Continuous Neural Networks for Time Series Prediction with Exogenous Variables
- Cross-Lingual Knowledge Transfer for Clinical Phenotyping
- Multimodal Generation of Novel Action Appearances for Synthetic-to-Real Recognition of Activities of Daily Living
- Rethinking the Evaluation of Unbiased Scene Graph Generation
- Graph Signal Processing for Heterogeneous Change Detection Part II: Spectral Domain Analysis
- Neural Dynamic Movement Primitives -- a survey
- Asynchronous Federated Learning for Edge-assisted Vehicular Networks
- XCon: Learning with Experts for Fine-grained Category Discovery
- Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition
- Flow Annealed Importance Sampling Bootstrap
- Evaluating and improving social awareness of energy communities through semantic network analysis of online news
- Graph Signal Processing for Heterogeneous Change Detection Part I: Vertex Domain Filtering
- Leveraging Smartphone Sensors for Detecting Abnormal Gait for Smart Wearable Mobile Technologies
- Introducing BEREL: BERT Embeddings for Rabbinic-Encoded Language
- Exploring Generative Neural Temporal Point Process
- A Deep Learning Approach to Detect Lean Blowout in Combustion Systems
- The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift
- Robust Graph Neural Networks using Weighted Graph Laplacian
- Coarse-to-Fine Knowledge-Enhanced Multi-Interest Learning Framework for Multi-Behavior Recommendation
- Multiclass ASMA vs Targeted PGD Attack in Image Segmentation
- Multi-Feature Vision Transformer via Self-Supervised Representation Learning for Improvement of COVID-19 Diagnosis
- Robust Learning of Deep Time Series Anomaly Detection Models with Contaminated Training Data
- 'Labelling the Gaps': A Weakly Supervised Automatic Eye Gaze Estimation
- Re-Attention Transformer for Weakly Supervised Object Localization
- Learning Prior Feature and Attention Enhanced Image Inpainting
- EMC2A-Net: An Efficient Multibranch Cross-channel Attention Network for SAR Target Classification
- Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation
- Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing
- A New Implementation of Federated Learning for Privacy and Security Enhancement
- Medical image registration using unsupervised deep neural network: A scoping literature review
- A Lightweight Transmission Parameter Selection Scheme Using Reinforcement Learning for LoRaWAN
- Statistical Attention Localization (SAL): Methodology and Application to Object Classification
- Link Prediction on Heterophilic Graphs via Disentangled Representation Learning
- Adversarial Camouflage for Node Injection Attack on Graphs
- VQ-T: RNN Transducers using Vector-Quantized Prediction Network States
- Neural Contourlet Network for Monocular 360 Depth Estimation
- Effidit: Your AI Writing Assistant
- Benchmarking zero-shot and few-shot approaches for tokenization, tagging, and dependency parsing of Tagalog text
- TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
- A comprehensive survey on computer-aided diagnostic systems in diabetic retinopathy screening
- Post-hoc Interpretability based Parameter Selection for Data Oriented Nuclear Reactor Accident Diagnosis System
- The Importance of the Instantaneous Phase in Detecting Faces with Convolutional Neural Networks