Papers
Fri 9 Dec 2022
155 papers
- Sparse Upcycling: Training Mixture-of-Experts from Dense CheckpointsMixture-of-experts → MoE large language models
- SmartBrush: Text and Shape Guided Object Inpainting with Diffusion ModelDiffusion models → 3D, point cloud and scene generation
- Training-Free Structured Diffusion Guidance for Compositional Text-to-Image SynthesisDiffusion models → Image generation, text-to-image and editing
- Co-training 2L Submodels for Visual RecognitionKnowledge distillation → Detection and dense prediction distillation
- ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow RemovalDiffusion models → 3D, point cloud and scene generation
- EEG Opto-processor: epileptic seizure detection using diffractive photonic computing units
- A Data-driven Loss Weighting Scheme across Heterogeneous Tasks for Image Denoising
- Easing Automatic Neurorehabilitation via Classification and Smoothness Analysis
- An AI-Powered VVPAT Counter for Elections in India
- Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification
- The Turing Deception
- Matrix Profile XXVII: A Novel Distance Measure for Comparing Long Time Series
- AP: Selective Activation for De-sparsifying Pruned Neural Networks
- Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks
- Improving Mutual Information based Feature Selection by Boosting Unique Relevance
- Towards Better Long-range Time Series Forecasting using Generative Forecasting
- Dual adaptive training of photonic neural networks
- Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement
- Sharing Linkable Learning Objects with the use of Metadata and a Taxonomy Assistant for Categorization
- Self-Supervised Object Goal Navigation with In-Situ Finetuning
- Audiovisual Masked Autoencoders
- Finger-NestNet: Interpretable Fingerphoto Verification on Smartphone using Deep Nested Residual Network
- Multi-task Learning for Personal Health Mention Detection on Social Media
- Online Convex Optimization of Programmable Quantum Computers to Simulate Time-Varying Quantum Channels
- Networked Restless Bandits with Positive Externalities
- Local Neighborhood Features for 3D Classification
- CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection
- Measuring Data
- Multi-view Graph Convolutional Networks with Differentiable Node Selection
- All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management
- Leveraging Contextual Data Augmentation for Generalizable Melanoma Detection
- Visuotactile Affordances for Cloth Manipulation with Local Control
- A soft nearest-neighbor framework for continual semi-supervised learning
- Plug-and-Play Recipe Generation with Content Planning
- Cyclic Block Coordinate Descent With Variance Reduction for Composite Nonconvex Optimization
- FAIR AI Models in High Energy Physics
- The RPM3D project: 3D Kinematics for Remote Patient Monitoring
- Towards Stroke Patients' Upper-limb Automatic Motor Assessment Using Smartwatches
- Estimating Chicago's tree cover and canopy height using multi-spectral satellite imagery
- VindLU: A Recipe for Effective Video-and-Language Pretraining
- The unstable formula theorem revisited via algorithms
- Cross-Domain Synthetic-to-Real In-the-Wild Depth and Normal Estimation for 3D Scene Understanding
- Incorporating Emotions into Health Mention Classification Task on Social Media
- Towards a learning-based performance modeling for accelerating Deep Neural Networks
- Decomposable Sparse Tensor on Tensor Regression
- Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall
- Robustness Implies Privacy in Statistical Estimation
- LADIS: Language Disentanglement for 3D Shape Editing
- Scalable Graph Convolutional Network Training on Distributed-Memory Systems
- Memories are One-to-Many Mapping Alleviators in Talking Face Generation
- Regulating Gatekeeper AI and Data: Transparency, Access, and Fairness under the DMA, the GDPR, and beyond
- Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning
- Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and Regularization
- Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks
- LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
- VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
- Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentation
- MOPRD: A multidisciplinary open peer review dataset
- PDE-LEARN: Using Deep Learning to Discover Partial Differential Equations from Noisy, Limited Data
- Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers
- SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering
- Towards High-Order Complementary Recommendation via Logical Reasoning Network
- Seeing a Rose in Five Thousand Ways
- PACMAN: a framework for pulse oximeter digit detection and reading in a low-resource setting
- Simulating first-order phase transition with hierarchical autoregressive networks
- TargetCall: Eliminating the Wasted Computation in Basecalling via Pre-Basecalling Filtering
- A Learned Born Series for Highly-Scattering Media
- Emergent Computations in Trained Artificial Neural Networks and Real Brains
- Learning Graph Algorithms With Recurrent Graph Neural Networks
- Doubly Robust Kernel Statistics for Testing Distributional Treatment Effects
- TRBLLmaker -- Transformer Reads Between Lyrics Lines maker
- Information-Theoretic Safe Exploration with Gaussian Processes
- CKG: Dynamic Representation Based on Context and Knowledge Graph
- Robust detection and attribution of climate change under interventions
- HieNet: Bidirectional Hierarchy Framework for Automated ICD Coding
- ProductGraphSleepNet: Sleep Staging using Product Spatio-Temporal Graph Learning with Attentive Temporal Aggregation
- Expeditious Saliency-guided Mix-up through Random Gradient Thresholding
- Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition
- Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet
- RCDT: Relational Remote Sensing Change Detection with Transformer
- Frugal Reinforcement-based Active Learning
- Deep Learning of Causal Structures in High Dimensions
- Implicit variance regularization in non-contrastive SSL
- A perspective on physical reservoir computing with nanomagnetic devices
- Closed pattern mining of interval data and distributional data
- Album cover art image generation with Generative Adversarial Networks
- PIVOT: Prompting for Video Continual Learning
- Noise2Contrast: Multi-Contrast Fusion Enables Self-Supervised Tomographic Image Denoising
- Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture Models
- A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
- Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization
- Machine Learning Framework: Competitive Intelligence and Key Drivers Identification of Market Share Trends Among Healthcare Facilities
- CEPHA29: Automatic Cephalometric Landmark Detection Challenge 2023
- Understanding electricity prices beyond the merit order principle using explainable AI
- AUC Maximization for Low-Resource Named Entity Recognition
- Visual Detection of Personal Protective Equipment and Safety Gear on Industry Workers
- Synthetic Data for Object Classification in Industrial Applications
- Image-Based Fire Detection in Industrial Environments with YOLOv4
- Music Recommendation System based on Emotion, Age and Ethnicity
- Genie: Show Me the Data for Quantization
All 155
- Understanding Online Migration Decisions Following the Banning of Radical Communities
- AuE-IPA: An AU Engagement Based Infant Pain Assessment Method
- Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
- From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader
- SLAM for Visually Impaired People: a Survey
- Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
- Physically Plausible Animation of Human Upper Body from a Single Image
- Predicting Shape Development: a Riemannian Method
- MED-SE: Medical Entity Definition-based Sentence Embedding
- Augmenting Knowledge Transfer across Graphs
- A Grid-based Sensor Floor Platform for Robot Localization using Machine Learning
- Multi-Task Off-Policy Learning from Bandit Feedback
- On the Sensitivity of Reward Inference to Misspecified Human Models
- Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning
- PATO: Policy Assisted TeleOperation for Scalable Robot Data Collection
- The Platform for non-metallic pipes defects recognition. Design and Implementation
- Physics-based Indirect Illumination for Inverse Rendering
- Implementing Neural Network-Based Equalizers in a Coherent Optical Transmission System Using Field-Programmable Gate Arrays
- 4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions
- Tencent AVS: A Holistic Ads Video Dataset for Multi-modal Scene Segmentation
- Attention in a family of Boltzmann machines emerging from modern Hopfield networks
- Benchmarking Self-Supervised Learning on Diverse Pathology Datasets
- Non-equispaced Fourier Neural Solvers for PDEs
- Comparative Study of Sentiment Analysis for Multi-Sourced Social Media Platforms
- Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models
- Machine Learning-based Classification of Birds through Birdsong
- Dynamic Test-Time Augmentation via Differentiable Functions
- Near-Optimal Differentially Private Reinforcement Learning
- Motion and Context-Aware Audio-Visual Conditioned Video Prediction
- Reinforcement Learning for Predicting Traffic Accidents
- SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection
- MSI: Maximize Support-Set Information for Few-Shot Segmentation
- Iterative Minimax Games with Coupled Linear Constraints
- Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds
- Neural Volume Super-Resolution
- A Computer Vision Method for Estimating Velocity from Jumps
- Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations
- An Attention-based Multi-Scale Feature Learning Network for Multimodal Medical Image Fusion
- Robust Graph Representation Learning via Predictive Coding
- MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction
- DRIP: Domain Refinement Iteration with Polytopes for Backward Reachability Analysis of Neural Feedback Loops
- FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
- Ego-Body Pose Estimation via Ego-Head Pose Estimation
- Open-world Story Generation with Structured Knowledge Enhancement: A Comprehensive Survey
- Mitigation of Spatial Nonstationarity with Vision Transformers
- Category-Level 6D Object Pose Estimation with Flexible Vector-Based Rotation Representation
- The Normalized Cross Density Functional: A Framework to Quantify Statistical Dependence for Random Processes
- A PINN Approach to Symbolic Differential Operator Discovery with Sparse Data
- Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation
- Digital Twin for Real-time Li-ion Battery State of Health Estimation with Partially Discharged Cycling Data
- UNet Based Pipeline for Lung Segmentation from Chest X-Ray Images
- Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop
- Contrastive View Design Strategies to Enhance Robustness to Domain Shifts in Downstream Object Detection
- Training Data Influence Analysis and Estimation: A Survey
- Multidimensional Service Quality Scoring System