Papers
Fri 25 Nov 2022
190 papers
- SpaText: Spatio-Textual Representation for Controllable Image GenerationDiffusion models → Image generation, text-to-image and editing
- BeLFusion: Latent Diffusion for Behavior-Driven Human Motion PredictionDiffusion models → Video generation
- Solving math word problems with process- and outcome-based feedbackLLM reasoning → Reinforcement learning for reasoning +1
- Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual GroundingKnowledge distillation → Detection and dense prediction distillation
- Latent Space Diffusion Models of Cryo-EM StructuresDiffusion models → Flow matching, time series and science
- 3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
- CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text LabelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- TRAC: A Textual Benchmark for Reasoning about Actions and ChangeLLM reasoning → Reasoning benchmarks and evaluation
- XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation LearningKnowledge distillation → Multimodal distillation
- Generative Modeling in Sinogram Domain for Sparse-view CT ReconstructionDiffusion models → Medical imaging and segmentation
- Generative Modeling in Structural-Hankel Domain for Color Image InpaintingDiffusion models → 3D, point cloud and scene generation
- Approaching Globally Optimal Energy Efficiency in Interference Networks via Machine Learning
- OOG- Optuna Optimized GAN Sampling Technique for Tabular Imbalanced Malware Data
- Deep-Learning-based Vulnerability Detection in Binary Executables
- SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition
- Dense Hebbian neural networks: a replica symmetric picture of supervised learning
- Cellular Automata Model for Non-Structural Proteins Comparing Transmissibility and Pathogenesis of SARS Covid (CoV-2, CoV) and MERS Covid
- PaCMO: Partner Dependent Human Motion Generation in Dyadic Human Activity using Neural Operators
- The Vanishing Decision Boundary Complexity and the Strong First Component
- Artificial Intelligence-based Eosinophil Counting in Gastrointestinal Biopsies
- Learning Visual Planning Models from Partially Observed Images
- Composite Score for Anomaly Detection in Imbalanced Real-World Industrial Dataset
- Semantic Table Detection with LayoutLMv3
- ToothInpaintor: Tooth Inpainting from Partial 3D Dental Model and 2D Panoramic Image
- Underground Diagnosis Based on GPR and Learning in the Model Space
- CodeExp: Explanatory Code Document Generation
- Aesthetically Relevant Image Captioning
- Improving Proactive Dialog Agents Using Socially-Aware Reinforcement Learning
- Copula Density Neural Estimation
- Interactive Image Manipulation with Complex Text Instructions
- Testing the effectiveness of saliency-based explainability in NLP using randomized survey-based experiments
- Learning Feynman Diagrams using Graph Neural Networks
- An Analysis of Social Biases Present in BERT Variants Across Multiple Languages
- Elements of effective machine learning datasets in astronomy
- Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces
- Non-invasive Liver Fibrosis Screening on CT Images using Radiomics
- Deep Learning Training Procedure Augmentations
- Link Prediction with Non-Contrastive Learning
- FedSysID: A Federated Approach to Sample-Efficient System Identification
- MDA: Availability-Aware Federated Learning Client Selection
- Machine Learning Algorithms for Time Series Analysis and Forecasting
- Pac-Man Pete: An extensible framework for building AI in VEX Robotics
- Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
- Interpretability Analysis of Deep Models for COVID-19 Detection
- The Naughtyformer: A Transformer Understands Offensive Humor
- Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling
- Homology-constrained vector quantization entropy regularizer
- Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images
- Finetuning BERT on Partially Annotated NER Corpora
- A Moral- and Event- Centric Inspection of Gender Bias in Fairy Tales at A Large Scale
- The smooth output assumption, and why deep networks are better than wide ones
- Less Data, More Knowledge: Building Next Generation Semantic Communication Networks
- A Machine Learning, Natural Language Processing Analysis of Youth Perspectives: Key Trends and Focus Areas for Sustainable Youth Development Policies
- Efficient 3D Reconstruction, Streaming and Visualization of Static and Dynamic Scene Parts for Multi-client Live-telepresence in Large-scale Environments
- FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations
- WALDO: Future Video Synthesis using Object Layer Decomposition and Parametric Flow Prediction
- MAEDAY: MAE for few and zero shot AnomalY-Detection
- RUST: Latent Neural Scene Representations from Unposed Imagery
- Neural DAEs: Constrained neural networks
- On the Effect of Anticipation on Reading Times
- PIP: Positional-encoding Image Prior
- Doubly robust nearest neighbors in factor models
- A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
- RbA: Segmenting Unknown Regions Rejected by All
- Analysis of Error Feedback in Federated Non-Convex Optimization with Biased Compression
- CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis
- Domain generalization in fetal brain MRI segmentation with multi-reconstruction augmentation
- Multiverse: Multilingual Evidence for Fake News Detection
- Degenerate Swin to Win: Plain Window-based Transformer without Sophisticated Operations
- Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
- Neural Poisson: Indicator Functions for Neural Fields
- Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
- Strategyproof Decision-Making in Panel Data Settings and Beyond
- DoubleU-NetPlus: A Novel Attention and Context Guided Dual U-Net with Multi-Scale Residual Feature Fusion Network for Semantic Segmentation of Medical Images
- GPT-3-driven pedagogical agents for training children's curious question-asking skills
- Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing
- The Effect of Epigenetic Blocking on Dynamic Multi-Objective Optimisation Problems
- Learning Large Causal Structures from Inverse Covariance Matrix via Sparse Matrix Decomposition
- Data-driven identification and analysis of the glass transition in polymer melts
- GREAD: Graph Neural Reaction-Diffusion Networks
- Invariance-Aware Randomized Smoothing Certificates
- Overcoming Catastrophic Forgetting by XAI
- MCFFA-Net: Multi-Contextual Feature Fusion and Attention Guided Network for Apple Foliar Disease Classification
- NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologies
- Exposure and Emergence in Usage-Based Grammar: Computational Experiments in 35 Languages
- An Isolation-Aware Online Virtual Network Embedding via Deep Reinforcement Learning
- Learning 3D Scene Priors with 2D Supervision
- Interaction Region Visual Transformer for Egocentric Action Anticipation
- Graph Convolutional Network-based Feature Selection for High-dimensional and Low-sample Size Data
- Evaluation of the impact of the indiscernibility relation on the fuzzy-rough nearest neighbours algorithm
- PipeFisher: Efficient Training of Large Language Models Using Pipelining and Fisher Information Matrices
- A Strong Baseline for Generalized Few-Shot Semantic Segmentation
- PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation
- Automating Cobb Angle Measurement for Adolescent Idiopathic Scoliosis using Instance Segmentation
- MS-PS: A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Dataset
- Inverse Feasibility in Over-the-Air Federated Learning
- Unifying conditional and unconditional semantic image synthesis with OCO-GAN
- Fuzzy clustering for the within-season estimation of cotton phenology
- An Ensemble-Based Deep Framework for Estimating Thermo-Chemical State Variables from Flamelet Generated Manifolds
- Deep grading for MRI-based differential diagnosis of Alzheimer's disease and Frontotemporal dementia
All 190
- A Hierarchical Variable Autonomy Mixed-Initiative Framework for Human-Robot Teaming in Mobile Robotics
- Language-Assisted 3D Feature Learning for Semantic Scene Understanding
- Spatial-Spectral Transformer for Hyperspectral Image Denoising
- Boundary Adversarial Examples Against Adversarial Overfitting
- ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision
- Positive unlabeled learning with tensor networks
- Training Data Improvement for Image Forgery Detection using Comprint
- Detecting broken Absorber Tubes in CSP plants using intelligent sampling and dual loss
- Copy-Pasting Coherent Depth Regions Improves Contrastive Learning for Urban-Scene Segmentation
- EDGAR: Embedded Detection of Gunshots by AI in Real-time
- Fine-Grained Face Swapping via Regional GAN Inversion
- Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning
- Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating
- M2M: A general method to perform various data analysis tasks from a differentially private sketch
- A Survey of Learning Curves with Bad Behavior: or How More Data Need Not Lead to Better Performance
- Cross-Domain Ensemble Distillation for Domain Generalization
- CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry
- Re^2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization
- Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence Learning
- Open-Source Skull Reconstruction with MONAI
- Task-Oriented Communication for Edge Video Analytics
- On the Universal Approximation Property of Deep Fully Convolutional Neural Networks
- Molecular Joint Representation Learning via Multi-modal Information
- Real-Time Under-Display Cameras Image Restoration and HDR on Mobile Devices
- MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs
- Privileged Prior Information Distillation for Image Matting
- Automata Cascades: Expressivity and Sample Complexity
- Cross-network transferable neural models for WLAN interference estimation
- Toward Unlimited Self-Learning MCMC with Parallel Adaptive Annealing
- SCOOP: Self-Supervised Correspondence and Optimization-Based Scene Flow
- Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
- Strategic Facility Location with Clients that Minimize Total Waiting Time
- Collection and Evaluation of a Long-Term 4D Agri-Robotic Dataset
- Efficient Feature Extraction for High-resolution Video Frame Interpolation
- Assistive Teaching of Motor Control Tasks to Humans
- CoMFormer: Continual Learning in Semantic and Panoptic Segmentation
- Dynamic Neural Portraits
- Combating noisy labels in object detection datasets
- TrustGAN: Training safe and trustworthy deep learning models through generative adversarial networks
- Aggregated Text Transformer for Scene Text Detection
- BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
- Expanding Small-Scale Datasets with Guided Imagination
- FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
- ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation
- Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
- Unsupervised Continual Semantic Adaptation through Neural Rendering
- MIAD: A Maintenance Inspection Dataset for Unsupervised Anomaly Detection
- Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution
- The European AI Liability Directives -- Critique of a Half-Hearted Approach and Lessons for the Future
- Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers
- MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention
- Particle-based Variational Inference with Preconditioned Functional Gradient Flow
- Contextual Decision-Making with Knapsacks Beyond the Worst Case
- Affine Transformation Edited and Refined Deep Neural Network for Quantitative Susceptibility Mapping
- Combinatorial Civic Crowdfunding with Budgeted Agents: Welfare Optimality at Equilibrium and Optimal Deviation
- Spatial-Temporal Attention Network for Open-Set Fine-Grained Image Recognition
- Efficient Incremental Text-to-Speech on GPUs
- Operator Splitting Value Iteration
- LU decomposition and Toeplitz decomposition of a neural network
- MUSTER: A Multi-scale Transformer-based Decoder for Semantic Segmentation
- Combining Constructive and Perturbative Deep Learning Algorithms for the Capacitated Vehicle Routing Problem
- Mutual Guidance and Residual Integration for Image Enhancement
- Towards Good Practices for Missing Modality Robust Action Recognition
- Confidence Interval Construction for Multivariate time series using Long Short Term Memory Network
- Fault-Tolerant Offline Multi-Agent Path Planning
- Policy-Adaptive Estimator Selection for Off-Policy Evaluation
- TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks
- Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis from Monocular Image
- A Deep Learning Anomaly Detection Method in Textual Data
- Comparison Study Between Token Classification and Sequence Classification In Text Classification
- AFR-Net: Attention-Driven Fingerprint Recognition Network
- MUSIED: A Benchmark for Event Detection from Multi-Source Heterogeneous Informal Texts
- Identifying Incorrect Annotations in Multi-Label Classification Data
- Complementary Explanations for Effective In-Context Learning
- TPA-Net: Generate A Dataset for Text to Physics-based Animation
- Learning with Silver Standard Data for Zero-shot Relation Extraction
- Galvatron: Efficient Transformer Training over Multiple GPUs Using Automatic Parallelism
- FFHQ-UV: Normalized Facial UV-Texture Dataset for 3D Face Reconstruction
- Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition
- Minimal Width for Universal Property of Deep RNN
- Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality?
- DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection
- Far3Det: Towards Far-Field 3D Detection
- WSSL: Weighted Self-supervised Learning Framework For Image-inpainting
- ComCLIP: Training-Free Compositional Image and Text Matching
- Extreme Acceleration of Graph Neural Network-based Prediction Models for Quantum Chemistry
- Adaptive Attention Link-based Regularization for Vision Transformers
- Ladder Siamese Network: a Method and Insights for Multi-level Self-Supervised Learning
- Signed Binary Weight Networks
- End-to-End Stochastic Optimization with Energy-Based Model