Papers
Wed 12 Apr 2023
184 papers
- An Edit Friendly DDPM Noise Space: Inversion and ManipulationsDiffusion models → Image generation, text-to-image and editing
- PATMAT: Person Aware Tuning of Mask-Aware Transformer for Face InpaintingDiffusion models → Image generation, text-to-image and editing
- CLIP-Guided Vision-Language Pre-training for Question Answering in 3D ScenesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRADiffusion models → Image generation, text-to-image and editing
- DreamPose: Fashion Image-to-Video Synthesis via Stable DiffusionDiffusion models → 3D, point cloud and scene generation
- MABL: Bi-Level Latent-Variable World Model for Sample-Efficient Multi-Agent Reinforcement LearningWorld models → Latent dynamics models and model-based RL
- APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIPMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
- Boosted Prompt Ensembles for Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion ModelsDiffusion models → Inverse problems and image restoration
- Diffusion models with location-scale noiseDiffusion models → Diffusion foundations and sampling
- Exploring Diffusion Models for Unsupervised Video Anomaly DetectionDiffusion models → Flow matching, time series and science
- Boosting long-term forecasting performance for continuous-time dynamic graph networks via data augmentationWorld models → World models for language agents
- InterGen: Diffusion-based Multi-human Motion Generation under Complex InteractionsDiffusion models → Video generation
- A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge DistillationKnowledge distillation → Distillation for spiking neural networks
- Improving Diffusion Models for Scene Text Editing with Dual EncodersDiffusion models → Image generation, text-to-image and editing
- Can Large Language Models Transform Computational Social Science?
- Neural Field Conditioning Strategies for 2D Semantic Segmentation
- Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
- SmartChoices: Augmenting Software with Learned Implementations
- An Equivariant Generative Framework for Molecular Graph-Structure Co-Design
- Positive AI: Key Challenges in Designing Artificial Intelligence for Wellbeing
- Neural Architecture Search Using Genetic Algorithm for Facial Expression Recognition
- Color-based classification of EEG Signals for people with the severe locomotive disorder
- Identifying Trades Using Technical Analysis and ML/DL Models
- NRTS: A Client-Server architecture for supporting data recording, transmission and evaluation of multidisciplinary teams during the neonatal resuscitation simulation scenario
- Towards Spatio-temporal Sea Surface Temperature Forecasting via Static and Dynamic Learnable Personalized Graph Convolution Network
- A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
- Textual Explanations for Automated Commentary Driving
- Evaluation of ChatGPT Model for Vulnerability Detection
- Measuring Re-identification Risk
- Meta-Learned Models of Cognition
- ML-Enabled Outdoor User Positioning in 5G NR Systems via Uplink SRS Channel Estimates
- SiLK -- Simple Learned Keypoints
- Learning Over Contracting and Lipschitz Closed-Loops for Partially-Observed Nonlinear Systems (Extended Version)
- Using Large Language Models for (De-)Formalization and Natural Argumentation Exercises for Beginner's Students
- LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity
- Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
- Visual based Tomato Size Measurement System for an Indoor Farming Environment
- Accurate transition state generation with an object-aware equivariant elementary reaction diffusion model
- Neural Network Algorithm for Intercepting Targets Moving Along Known Trajectories by a Dubins' Car
- NP-Free: A Real-Time Normalization-free and Parameter-tuning-free Representation Approach for Open-ended Time Series
- Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNet
- Post-selection Inference for Conformal Prediction: Trading off Coverage for Precision
- Detection of Fake Generated Scientific Abstracts
- R-Shiny Applications for Local Clustering to be Included in the growclusters for R Package
- AGI for Agriculture
- Towards Evaluating Explanations of Vision Transformers for Medical Imaging
- UniverSeg: Universal Medical Image Segmentation
- Label-Free Concept Bottleneck Models
- Assessment Framework for Deepfake Detection in Real-world Situations
- FollowMe: Vehicle Behaviour Prediction in Autonomous Vehicle Settings
- Explanation of Face Recognition via Saliency Maps
- AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection
- TopTrack: Tracking Objects By Their Top
- Generation of artificial facial drug abuse images using Deep De-identified anonymous Dataset augmentation through Genetics Algorithm (3DG-GA)
- Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints
- E(3) × SO(3)-Equivariant Networks for Spherical Deconvolution in Diffusion MRI
- Fast emulation of cosmological density fields based on dimensionality reduction and supervised machine-learning
- Energy-guided Entropic Neural Optimal Transport
- Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays
- Maximal Fairness
- Facilitating Sim-to-real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation
- Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
- Landslide Susceptibility Prediction Modeling Based on Self-Screening Deep Learning Model
- TextANIMAR: Text-based 3D Animal Fine-Grained Retrieval
- Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
- Open-TransMind: A New Baseline and Benchmark for 1st Foundation Model Challenge of Intelligent Transportation
- Fluctuation based interpretable analysis scheme for quantum many-body snapshots
- RECLIP: Resource-efficient CLIP by Training with Small Images
- Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
- SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything
- Crowd Counting with Sparse Annotation
- VidStyleODE: Disentangled Video Editing via StyleGAN and NeuralODEs
- Generating Aligned Pseudo-Supervision from Non-Aligned Data for Image Restoration in Under-Display Camera
- Adaptive Human Matting for Dynamic Videos
- Exploiting Logic Locking for a Neural Trojan Attack on Machine Learning Accelerators
- An Improved Heart Disease Prediction Using Stacked Ensemble Method
- Literature Review: Computer Vision Applications in Transportation Logistics and Warehousing
- GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning
- Fast vehicle detection algorithm based on lightweight YOLO7-tiny
- Maximum-likelihood Estimators in Physics-Informed Neural Networks for High-dimensional Inverse Problems
- Auditing ICU Readmission Rates in an Clinical Database: An Analysis of Risk Factors and Clinical Outcomes
- Neural Attention Forests: Transformer-Based Forest Improvement
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
- Bayesian Causal Inference in Doubly Gaussian DAG-probit Models
- HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting
- Localizing Model Behavior with Path Patching
- Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
- OO-dMVMT: A Deep Multi-view Multi-task Classification Framework for Real-time 3D Hand Gesture Classification and Segmentation
- CMOS + stochastic nanomagnets: heterogeneous computers for probabilistic inference and learning
- Visual Localization using Imperfect 3D Models from the Internet
- Explicitly Minimizing the Blur Error of Variational Autoencoders
- ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition
- MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer
- ReDWINE: A Clinical Datamart with Text Analytical Capabilities to Facilitate Rehabilitation Research
- Hard Patches Mining for Masked Image Modeling
- A Phoneme-Informed Neural Network Model for Note-Level Singing Transcription
- Automated computed tomography and magnetic resonance imaging segmentation using deep learning: a beginner's guide
- Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep Radiomic Features from Synthetic Correlated Diffusion Imaging
All 184
- Evaluating Classifier Confidence for Surface EMG Pattern Recognition
- Towards Understanding How Data Augmentation Works with Imbalanced Data
- Dynamic Mixed Membership Stochastic Block Model for Weighted Labeled Networks
- Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL
- Are Local Features All You Need for Cross-Domain Visual Place Recognition?
- Unicom: Universal and Compact Representation Learning for Image Retrieval
- FetMRQC: Automated Quality Control for fetal brain MRI
- Adaptive Gated Graph Convolutional Network for Explainable Diagnosis of Alzheimer's Disease using EEG Data
- Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics
- Edge-cloud Collaborative Learning with Federated and Centralized Features
- LMR: Lane Distance-Based Metric for Trajectory Prediction
- Mesh2Tex: Generating Mesh Textures from Image Queries
- NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs
- Scale-Equivariant Deep Learning for 3D Data
- Learning Homographic Disambiguation Representation for Neural Machine Translation
- RESET: Revisiting Trajectory Sets for Conditional Behavior Prediction
- Rethinking Dense Retrieval's Few-Shot Ability
- Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challenges
- HaDR: Applying Domain Randomization for Generating Synthetic Multimodal Dataset for Hand Instance Segmentation in Cluttered Industrial Environments
- DiscoGen: Learning to Discover Gene Regulatory Networks
- DUFormer: Solving Power Line Detection Task in Aerial Images using Semantic Segmentation
- Gradient-Free Textual Inversion
- GDP nowcasting with artificial neural networks: How much does long-term memory matter?
- Proximity Forest 2.0: A new effective and scalable similarity-based classifier for time series
- Deep neural network approximation of composite functions without the curse of dimensionality
- Measuring Gender Bias in West Slavic Language Models
- Using Multiple RDF Knowledge Graphs for Enriching ChatGPT Responses
- An Image Quality Assessment Dataset for Portraits
- Measuring Normative and Descriptive Biases in Language Models Using Census Data
- Best Practices for 2-Body Pose Forecasting
- ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer
- Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results
- Function Space and Critical Points of Linear Convolutional Networks
- Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications
- Learning to search for and detect objects in foveal images using deep learning
- Communicating Uncertainty in Machine Learning Explanations: A Visualization Analytics Approach for Predictive Process Monitoring
- Few-shot Class-incremental Learning for Cross-domain Disease Classification
- SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval
- Dynamic Graph Representation Learning with Neural Networks: A Survey
- Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
- Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer
- Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance
- Human-Robot Skill Transfer with Enhanced Compliance via Dynamic Movement Primitives
- Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification
- HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery
- Real-time Trajectory-based Social Group Detection
- Semantic-Aware Mixup for Domain Generalization
- Precise localization of corneal reflections in eye images using deep learning trained on synthetic data
- Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation
- Rail Detection: An Efficient Row-based Network and A New Benchmark
- SuperpixelGraph: Semi-automatic generation of building footprint through semantic-sensitive superpixel and neural graph networks
- RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
- Localisation of Regularised and Multiview Support Vector Machine Learning
- Breaking Modality Disparity: Harmonized Representation for Infrared and Visible Image Registration
- WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
- Global Prompt Cell: A Portable Control Module for Effective Prompt Tuning
- Instance-Aware Domain Generalization for Face Anti-Spoofing
- Self Optimisation and Automatic Code Generation by Evolutionary Algorithms in PLC based Controlling Processes
- Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation
- How you feelin'? Learning Emotions and Mental States in Movie Scenes
- Multi-agent Policy Reciprocity with Theoretical Guarantee
- A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data
- SAMM (Segment Any Medical Model): A 3D Slicer Integration to SAM
- NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models
- NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation
- Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation
- ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning
- Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning
- Learned multiphysics inversion with differentiable programming and machine learning
- Semantic Feature Verification in FLAN-T5
- Discovering Structure From Corruption for Unsupervised Image Reconstruction
- Does Informativeness Matter? Active Learning for Educational Dialogue Act Classification
- SGL: Structure Guidance Learning for Camera Localization
- A Predictive Model using Machine Learning Algorithm in Identifying Students Probability on Passing Semestral Course
- Neural Invertible Variable-degree Optical Aberrations Correction
- On the Adversarial Inversion of Deep Biometric Representations
- An End-to-End Network for Upright Adjustment of Panoramic Images
- Learning Transferable Pedestrian Representation from Multimodal Information Supervision
- DynamicDet: A Unified Dynamic Architecture for Object Detection
- Distilling Token-Pruned Pose Transformer for 2D Human Pose Estimation
- Taxonomic Class Incremental Learning
- MEMA Runtime Framework: Minimizing External Memory Accesses for TinyML on Microcontrollers
- CLCLSA: Cross-omics Linked embedding with Contrastive Learning and Self Attention for multi-omics integration with incomplete multi-omics data
- Galactic ChitChat: Using Large Language Models to Converse with Astronomy Literature