Papers
Wed 20 Jul 2022
216 papers
- An Introduction to Modern Statistical LearningDiffusion models → Diffusion foundations and sampling
- Learning Deformable Object Manipulation from Expert DemonstrationsOffline RL and imitation learning from data → Robot manipulation imitation learning
- Discriminator-Weighted Offline Imitation Learning from Suboptimal DemonstrationsOffline RL and imitation learning from data → Imitation learning methods
- Diffsound: Discrete Diffusion Model for Text-to-sound GenerationDiffusion models → Audio, speech and music
- DeepIPC: Deeply Integrated Perception and Control for an Autonomous Vehicle in Real EnvironmentsEnd-to-end autonomous driving → End-to-end system architecture
- Adaptive Mixture of Experts Learning for Generalizable Face Anti-SpoofingMixture-of-experts → Vision mixture-of-experts
- Non-Uniform Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Resolving Copycat Problems in Visual Imitation Learning via Residual Action PredictionOffline RL and imitation learning from data → Imitation learning methods
- Can a Hebbian-like learning rule be avoiding the curse of dimensionality in sparse distributed data?
- An Exploratory Study of Tweets about the SARS-CoV-2 Omicron Variant: Insights from Sentiment Analysis, Language Interpretation, Source Tracking, Type Classification, and Embedded URL Detection
- A Large-Scale Dataset of Twitter Chatter about Online Learning during the Current COVID-19 Omicron Wave
- Learning to estimate a surrogate respiratory signal from cardiac motion by signal-to-signal translation
- Many-to-One Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Internet of Things Systems
- Action Quality Assessment using Transformers
- Cross-Modal Contrastive Representation Learning for Audio-to-Image Generation
- AutoDiCE: Fully Automated Distributed CNN Inference at the Edge
- A System-driven Automatic Ground Truth Generation Method for DL Inner-City Driving Corridor Detectors
- Learning to identify cracks on wind turbine blade surfaces using drone-based inspection images
- Solving the Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach
- End-to-End and Self-Supervised Learning for ComParE 2022 Stuttering Sub-Challenge
- Improved Generalization Guarantees in Restricted Data Models
- Co-Located Human-Human Interaction Analysis using Nonverbal Cues: A Survey
- On minimax density estimation via measure transport
- MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis
- Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM
- On Label Granularity and Object Localization
- Direct Localization in Underwater Acoustics via Convolutional Neural Networks: A Data-Driven Approach
- Slimmable Quantum Federated Learning
- The Game of Hidden Rules: A New Kind of Benchmark Challenge for Machine Learning
- Hydra: Hybrid Server Power Model
- Spotting Temporally Precise, Fine-Grained Events in Video
- On the Robustness of 3D Object Detectors
- Hybrid CNN-Transformer Model For Facial Affect Recognition In the ABAW4 Challenge
- Revisiting Hotels-50K and Hotel-ID
- Provably tuning the ElasticNet across instances
- Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach
- 2D GANs Meet Unsupervised Single-view 3D Reconstruction
- Flow-based Visual Quality Enhancer for Super-resolution Magnetic Resonance Spectroscopic Imaging
- Controllable and Guided Face Synthesis for Unconstrained Face Recognition
- Scene Recognition with Objectness, Attribute and Category Learning
- Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles
- Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
- Pediatric Bone Age Assessment using Deep Learning Models
- Liver Segmentation using Turbolift Learning for CT and Cone-beam C-arm Perfusion Imaging
- Constrained Prescriptive Trees via Column Generation
- GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
- Visual Knowledge Tracing
- Structural Causal 3D Reconstruction
- Analysis of the Effect of Low-Overhead Lossy Image Compression on the Performance of Visual Crowd Counting for Smart City Applications
- Automated Kantian Ethics: A Faithful Implementation
- Tackling Long-Tailed Category Distribution Under Domain Shifts
- Digraphwave: Scalable Extraction of Structural Node Embeddings via Diffusion on Directed Graphs
- AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation
- Learning Underspecified Models
- A Generalized & Robust Framework For Timestamp Supervision in Temporal Action Segmentation
- Continual Variational Autoencoder Learning via Online Cooperative Memorization
- Latent Discriminant deterministic Uncertainty
- Towards Better Evaluation for Dynamic Link Prediction
- Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance
- BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis
- World Robot Challenge 2020 -- Partner Robot: A Data-Driven Approach for Room Tidying with Mobile Manipulator
- Mixed-Precision Inference Quantization: Radically Towards Faster inference speed, Lower Storage requirement, and Lower Loss
- Model Compression for Resource-Constrained Mobile Robots
- What Do We Maximize in Self-Supervised Learning?
- Discover and Mitigate Unknown Biases with Debiasing Alternate Networks
- Is an Object-Centric Video Representation Beneficial for Transfer?
- Semantic uncertainty intervals for disentangled latent spaces
- DataPerf: Benchmarks for Data-Centric AI Development
- Monocular 3D Object Reconstruction with GAN Inversion
- 3D Clothed Human Reconstruction in the Wild
- Pretraining a Neural Network before Knowing Its Architecture
- Densely Constrained Depth Estimator for Monocular 3D Object Detection
- Adaptive Step-Size Methods for Compressed SGD
- Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model
- Fully Sparse 3D Object Detection
- MOTCOM: The Multi-Object Tracking Dataset Complexity Metric
- Locality Guidance for Improving Vision Transformers on Tiny Datasets
- Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks
- Difficulty-Aware Simulator for Open Set Recognition
- Tailoring Self-Supervision for Supervised Learning
- Secrets of Event-Based Optical Flow
- MANI-Rank: Multiple Attribute and Intersectional Group Fairness for Consensus Ranking
- Mitigating Algorithmic Bias with Limited Annotations
- Predictive Object-Centric Process Monitoring
- Generative Domain Adaptation for Face Anti-Spoofing
- E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs
- BYEL : Bootstrap Your Emotion Latent
- Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain
- Digital Twin-based Intrusion Detection for Industrial Control Systems
- DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
- ReFactor GNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective
- NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds
- NeuralNEB -- Neural Networks can find Reaction Paths Fast
- Temporal and cross-modal attention for audio-visual zero-shot learning
- M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes
- On a Generalized Framework for Time-Aware Knowledge Graphs
- Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry
- Measuring and signing fairness as performance under multiple stakeholder distributions
- Exploration of Parameter Spaces Assisted by Machine Learning
- Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores
All 216
- Telepresence Video Quality Assessment
- Operation-Level Performance Benchmarking of Graph Neural Networks for Scientific Applications
- Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction
- Deep Reinforcement Learning for Market Making Under a Hawkes Process-Based Limit Order Book Model
- VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
- Fixed Points of Cone Mapping with the Application to Neural Networks
- Probable Domain Generalization via Quantile Risk Minimization
- Deep Preconditioners and their application to seismic wavefield processing
- A Secure Clustering Protocol with Fuzzy Trust Evaluation and Outlier Detection for Industrial Wireless Sensor Networks
- Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
- Robust Landmark-based Stent Tracking in X-ray Fluoroscopy
- ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network
- An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentation
- Large Scale Radio Frequency Signal Classification
- A note on the variation of geometric functionals
- Labeling instructions matter in biomedical image analysis
- Successor Representation Active Inference
- When Is TTS Augmentation Through a Pivot Language Useful?
- Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification
- Stream-based active learning with linear models
- A Novel Neural Network Training Method for Autonomous Driving Using Semi-Pseudo-Labels and 3D Data Augmentations
- Discrete-Constrained Regression for Local Counting Models
- Learning to Solve Soft-Constrained Vehicle Routing Problems with Lagrangian Relaxation
- GenHPF: General Healthcare Predictive Framework with Multi-task Multi-source Learning
- Evaluating the Stability of Deep Image Quality Assessment With Respect to Image Scaling
- Everything is There in Latent Space: Attribute Editing and Attribute Style Manipulation by StyleGAN Latent Space Exploration
- An Embedded Monocular Vision Approach for Ground-Aware Objects Detection and Position Estimation
- Automated machine learning for borehole resistivity measurements
- Quantifying the Effect of Feedback Frequency in Interactive Reinforcement Learning for Robotic Tasks
- EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer
- UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
- AI Fairness: from Principles to Practice
- Journal Impact Factor and Peer Review Thoroughness and Helpfulness: A Supervised Machine Learning Study
- Operating Envelopes under Probabilistic Electricity Demand and Solar Generation Forecasts
- NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis
- The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing
- Multimodal Transformer for Automatic 3D Annotation and Object Detection
- EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching
- Unsupervised Industrial Anomaly Detection via Pattern Generative and Contrastive Networks
- FaceFormer: Scale-aware Blind Face Restoration with Transformers
- Unsupervised energy disaggregation via convolutional sparse coding
- Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder
- CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
- AU-Supervised Convolutional Vision Transformers for Synthetic Facial Expression Recognition
- Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy
- Drivable Volumetric Avatars using Texel-Aligned Features
- Localization supervision of chest x-ray classifiers using label-specific eye-tracking annotation
- A Hybrid Convolutional Neural Network with Meta Feature Learning for Abnormality Detection in Wireless Capsule Endoscopy Images
- Learning Counterfactually Invariant Predictors
- Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
- ApHMM: Accelerating Profile Hidden Markov Models for Fast and Energy-Efficient Genome Analysis
- GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
- Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition
- A temporally and spatially local spike-based backpropagation algorithm to enable training in hardware
- Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges
- Interpreting Latent Spaces of Generative Models for Medical Images using Unsupervised Methods
- CrossHuman: Learning Cross-Guidance from Multi-Frame Images for Human Reconstruction
- Introducing Auxiliary Text Query-modifier to Content-based Audio Retrieval
- Revisiting data augmentation for subspace clustering
- OTPose: Occlusion-Aware Transformer for Pose Estimation in Sparsely-Labeled Videos
- Feature Representation Learning for Unsupervised Cross-domain Image Retrieval
- Multi-Task Learning for Emotion Descriptors Estimation at the fourth ABAW Challenge
- Differentiable Agent-based Epidemiology
- Towards Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Generative Models
- The Need for a Meta-Architecture for Robot Autonomy
- Learning Sequence Representations by Non-local Recurrent Neural Memory
- Temporal Planning with Incomplete Knowledge and Perceptual Information
- RV4JaCa -- Runtime Verification for Multi-Agent Systems
- Robust Object Detection With Inaccurate Bounding Boxes
- Correntropy-Based Logistic Regression with Automatic Relevance Determination for Robust Sparse Brain Activity Decoding
- Lesion detection in contrast enhanced spectral mammography
- Efficient Meta-Tuning for Content-aware Neural Video Delivery
- Uncertainty Inspired Underwater Image Enhancement
- Intrinsic dimension estimation for discrete metrics
- Object-Compositional Neural Implicit Surfaces
- BigColor: Colorization using a Generative Color Prior for Natural Images
- On the Versatile Uses of Partial Distance Correlation in Deep Learning
- Quantized Training of Gradient Boosting Decision Trees
- Explaining Deepfake Detection by Analysing Image Matching
- ERA: Expert Retrieval and Assembly for Early Action Prediction
- Improving Data Driven Inverse Text Normalization using Data Augmentation
- Duplicate Detection as a Service
- Efficient Dependency Analysis for Rule-Based Ontologies
- Generalizable and Robust Deep Learning Algorithm for Atrial Fibrillation Diagnosis Across Ethnicities, Ages and Sexes
- GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features
- ExoSGAN and ExoACGAN: Exoplanet Detection using Adversarial Training Algorithms
- Pseudo-label Guided Cross-video Pixel Contrast for Robotic Surgical Scene Segmentation with Limited Annotations
- Streamable Neural Fields
- HTNet: Anchor-free Temporal Action Localization with Hierarchical Transformers
- Hand-Assisted Expression Recognition Method from Synthetic Images at the Fourth ABAW Challenge
- Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
- Learning Depth from Focus in the Wild
- Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology
- Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box
- Learning Topological Interactions for Multi-Class Medical Image Segmentation
- FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
- Task Allocation using a Team of Robots
- GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation
- Aware of the History: Trajectory Forecasting with the Local Behavior Data
- Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
- Integrating Linguistic Theory and Neural Language Models
- Test-Time Adaptation via Conjugate Pseudo-labels
- DC-BENCH: Dataset Condensation Benchmark
- Doge Tickets: Uncovering Domain-general Language Models by Playing Lottery Tickets
- HyperNet: Self-Supervised Hyperspectral Spatial-Spectral Feature Understanding Network for Hyperspectral Change Detection
- Perspective Phase Angle Model for Polarimetric 3D Reconstruction
- EVHA: Explainable Vision System for Hardware Testing and Assurance -- An Overview
- Explicit Image Caption Editing
- Learning from few examples: Classifying sex from retinal images via deep learning
- Learning Latent Traits for Simulated Cooperative Driving Tasks
- Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability
- Exploiting Domain Transferability for Collaborative Inter-level Domain Adaptive Object Detection
- Combined Federated and Split Learning in Edge Computing for Ubiquitous Intelligence in Internet of Things: State of the Art and Future Directions
- Unsupervised Deep Multi-Shape Matching
- Towards Accurate and Robust Classification in Continuously Transitioning Industrial Sprays with Mixup
- AiATrack: Attention in Attention for Transformer Visual Tracking