Papers
Wed 27 Jul 2022
149 papers
- Membership Inference Attacks via Adversarial ExamplesLLM safety and security → Membership inference attacks
- Look Closer to Your Enemy: Learning to Attack via Teacher-Student MimickingKnowledge distillation → Federated, robust and private distillation
- DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic WatermarkingLLM safety and security → Watermarking generated content and models
- Prediction of User Request and Complaint in Spoken Customer-Agent Conversations
- IoT based Smart Water Quality Prediction for Biofloc Aquaculture
- Investigating the Impact of Backward Strategy Learning in a Logic Tutor: Aiding Subgoal Learning towards Improved Problem Solving
- POSET-RL: Phase ordering for Optimizing Size and Execution Time using Reinforcement Learning
- Development of fully intuitionistic fuzzy data envelopment analysis model with missing data: an application to Indian police sector
- Internet of Things (IoT) based ECG System for Rural Health Care
- Blockchain associated machine learning and IoT based hypoglycemia detection system with auto-injection feature
- On the robustness of self-supervised representations for multi-view object classification
- Deep 360^circ Optical Flow Estimation Based on Multi-Projection Fusion
- Brain Tumor Diagnosis and Classification via Pre-Trained Convolutional Neural Networks
- Detecting Spam Reviews on Vietnamese E-commerce Websites
- Image sensing with multilayer, nonlinear optical neural networks
- 3D-Morphomics, Morphological Features on CT scans for lung nodule malignancy diagnosis
- Will AI Make Cyber Swords or Shields: A few mathematical models of technological progress
- Multi-Objective Provisioning of Network Slices using Deep Reinforcement Learning
- Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers
- Structural Similarity for Improved Transfer in Reinforcement Learning
- Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields
- Towards Sleep Scoring Generalization Through Self-Supervised Meta-Learning
- Look at Adjacent Frames: Video Anomaly Detection without Offline Training
- Learning to Assess Danger from Movies for Cooperative Escape Planning in Hazardous Environments
- AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
- Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction
- CompText: Visualizing, Comparing & Understanding Text Corpus
- Calibrate: Interactive Analysis of Probabilistic Model Output
- Label-Only Membership Inference Attack against Node-Level Graph Neural Networks
- Deep Learning for Classification of Thyroid Nodules on Ultrasound: Validation on an Independent Dataset
- The Leaf Clinical Trials Corpus: a new resource for query generation from clinical trial eligibility criteria
- GAUDI: A Neural Architect for Immersive 3D Scene Generation
- Lighting (In)consistency of Paint by Text
- Differentially Private Learning of Hawkes Processes
- Break and Make: Interactive Structural Understanding Using LEGO Bricks
- Distributional Actor-Critic Ensemble for Uncertainty-Aware Continuous Control
- SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation
- ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization
- Shift-tolerant Perceptual Similarity Metric
- Multi-layer Representation Learning for Robust OOD Image Classification
- Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization
- Fast expansion into harmonics on the disk: a steerable basis with fast radial convolutions
- Meta-Interpolation: Time-Arbitrary Frame Interpolation via Dual Meta-Learning
- Unsupervised Training for Neural TSP Solver
- Causal foundations of bias, disparity and fairness
- Conformal Prediction Bands for Two-Dimensional Functional Time Series
- Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes
- Do Quantum Circuit Born Machines Generalize?
- Using Deep Learning to Detecting Deepfakes
- Robust Output Analysis with Monte-Carlo Methodology
- A Semi-automatic Cell Tracking Process Towards Completing the 4D Atlas of C. elegans Development
- Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination
- Lightweight and Progressively-Scalable Networks for Semantic Segmentation
- Fairness and Randomness in Machine Learning: Statistical Independence and Relativization
- Encoding Concepts in Graph Neural Networks
- Towards the Neuroevolution of Low-level Artificial General Intelligence
- Correlations Between COVID-19 and Dengue
- D3C2-Net: Dual-Domain Deep Convolutional Coding Network for Compressive Sensing
- Data-Driven Sample Average Approximation with Covariate Information
- A Proper Orthogonal Decomposition approach for parameters reduction of Single Shot Detector networks
- Learning Hyper Label Model for Programmatic Weak Supervision
- Abstracting Sketches through Simple Primitives
- Contrastive Masked Autoencoders are Stronger Vision Learners
- A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck
- Future Unruptured Intracranial Aneurysm Growth Prediction using Mesh Convolutional Neural Networks
- UNIMIB at TREC 2021 Clinical Trials Track
- Learning with Combinatorial Optimization Layers: a Probabilistic Approach
- Satellite Image Based Cross-view Localization for Autonomous Vehicle
- Multi-Forgery Detection Challenge 2022: Push the Frontier of Unconstrained and Diverse Forgery Detection
- Generalizable multi-task, multi-domain deep segmentation of sparse pediatric imaging datasets via multi-scale contrastive regularization and multi-joint anatomical priors
- Modelling Social Context for Fake News Detection: A Graph Neural Network Based Approach
- The Cellwise Minimum Covariance Determinant Estimator
- Time to augment self-supervised visual representation learning
- AutoTransition: Learning to Recommend Video Transition Effects
- PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on
- Towards the Probabilistic Fusion of Learned Priors into Standard Pipelines for 3D Reconstruction
- Adaptive sampling for scanning pixel cameras
- VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training
- Reducing the Vision and Language Bias for Temporal Sentence Grounding
- Safe and Robust Experience Sharing for Deterministic Policy Gradient Algorithms
- Skimming, Locating, then Perusing: A Human-Like Framework for Natural Language Video Localization
- Dynamic Shielding for Reinforcement Learning in Black-Box Environments
- Time Series Forecasting Models Copy the Past: How to Mitigate
- Iterative Scene Graph Generation
- A Contact-Safe Reinforcement Learning Framework for Contact-Rich Robot Manipulation
- End-To-End Audiovisual Feature Fusion for Active Speaker Detection
- Concept Drift Challenge in Multimedia Anomaly Detection: A Case Study with Facial Datasets
- Leveraging GAN Priors for Few-Shot Part Segmentation
- Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo views
- Rethinking Efficacy of Softmax for Lightweight Non-Local Neural Networks
- Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips
- TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model
- Post-Train Adaptive MobileNet for Fast Anti-Spoofing
- Emergent social NPC interactions in the Social NPCs Skyrim mod and beyond
- BeCAPTCHA-Type: Biometric Keystroke Data Generation for Improved Bot Detection
- Evolutionary Multiparty Distance Minimization
- Identifying Hard Noise in Long-Tailed Sample Distribution
- Efficient Video Deblurring Guided by Motion Magnitude
- Optimizing transformations for contrastive learning in a differentiable framework
- Deep Clustering with Features from Self-Supervised Pretraining
All 149
- Camouflaged Object Detection via Context-aware Cross-level Fusion
- Learning Appearance-motion Normality for Video Anomaly Detection
- Are Neighbors Enough? Multi-Head Neural n-gram can be Alternative to Self-attention
- One-Trimap Video Matting
- Traffic Sign Detection With Event Cameras and DCNN
- Inverse Airborne Optical Sectioning
- Towards Soft Fairness in Restless Multi-Armed Bandits
- Towards Clear Expectations for Uncertainty Estimation
- PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation
- ALBench: A Framework for Evaluating Active Learning in Object Detection
- Two-Stream UNET Networks for Semantic Segmentation in Medical Images
- RealTime QA: What's the Answer Right Now?
- Gaia: Graph Neural Network with Temporal Shift aware Attention for Gross Merchandise Value Forecast in E-commerce
- Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processing
- SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding
- Generator Knows What Discriminator Should Learn in Unconditional GANs
- Should Bank Stress Tests Be Fair?
- Convolutional Embedding Makes Hierarchical Vision Transformer Stronger
- NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
- Portrait Interpretation and a Benchmark
- JDRec: Practical Actor-Critic Framework for Online Combinatorial Recommender System
- Learning the Evolution of Correlated Stochastic Power System Dynamics
- Federated Selective Aggregation for Knowledge Amalgamation
- Marker and source-marker reprogramming of Most Permissive Boolean networks and ensembles with BoNesis
- Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
- Is Attention All That NeRF Needs?
- GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data
- Applied Computer Vision on 2-Dimensional Lung X-Ray Images for Assisted Medical Diagnosis of Pneumonia
- Detecting Concept Drift in the Presence of Sparsity -- A Case Study of Automated Change Risk Assessment System
- Vector Quantized Image-to-Image Translation
- INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks
- Learning from Positive and Unlabeled Data with Augmented Classes
- End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement
- Fault Detection and Classification of Aerospace Sensors using a VGG16-based Deep Neural Network
- Sparse Deep Neural Network for Nonlinear Partial Differential Equations
- Instance-specific 6-DoF Object Pose Estimation from Minimal Annotations
- Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition
- Contextual Information and Commonsense Based Prompt for Emotion Recognition in Conversation
- AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation
- Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
- Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks
- Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base
- Contrastive Image Synthesis and Self-supervised Feature Adaptation for Cross-Modality Biomedical Image Segmentation
- Mid-level Representation Enhancement and Graph Embedded Uncertainty Suppressing for Facial Expression Recognition
- Atomic structure generation from reconstructing structural fingerprints
- Boosting Point-BERT by Multi-choice Tokens
- PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations
- XADLiME: eXplainable Alzheimer's Disease Likelihood Map Estimation via Clinically-guided Prototype Learning
- Information We Can Extract About a User From 'One Minute Mobile Application Usage'