{"total":113,"rows":[{"id":"2102.01558","title":"Occluded Video Instance Segmentation: A Benchmark","created":"2021-02-02","cited_by_count":154,"area":null},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147,"area":null},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135,"area":null},{"id":"2302.04062","title":"Machine Learning for Synthetic Data Generation: A Review","created":"2023-02-08","cited_by_count":120,"area":null},{"id":"2205.03257","title":"Synthetic Data -- what, why and how?","created":"2022-05-06","cited_by_count":67,"area":null},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59,"area":null},{"id":"2205.01551","title":"Cross-View Cross-Scene Multi-View Crowd Counting","created":"2022-05-03","cited_by_count":28,"area":null},{"id":"2110.03091","title":"Improving Fractal Pre-training","created":"2021-10-06","cited_by_count":26,"area":null},{"id":"2211.11602","title":"Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback","created":"2022-11-21","cited_by_count":26,"area":"alignment"},{"id":"2112.12252","title":"Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehicles","created":"2021-12-22","cited_by_count":22,"area":null},{"id":"2308.14100","title":"Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay","created":"2023-08-27","cited_by_count":20,"area":null},{"id":"2501.08983","title":"Compositional Generative Model of Unbounded 4D Cities","created":"2025-01-15","cited_by_count":17,"area":null},{"id":"2110.05145","title":"Sim2Air - Synthetic aerial dataset for UAV monitoring","created":"2021-10-11","cited_by_count":16,"area":null},{"id":"2303.10280","title":"Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances","created":"2023-03-17","cited_by_count":16,"area":null},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2211.05764","title":"DC-Check: A Data-Centric AI checklist to guide the development of reliable machine learning systems","created":"2022-11-09","cited_by_count":14,"area":null},{"id":"2405.17258","title":"$\\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning","created":"2024-05-27","cited_by_count":13,"area":null},{"id":"2406.12397","title":"Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models","created":"2024-06-18","cited_by_count":13,"area":"synth"},{"id":"2109.15068","title":"iShape: A First Step Towards Irregular Shape Instance Segmentation","created":"2021-09-30","cited_by_count":12,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2311.08199","title":"Diffusion-based generation of Histopathological Whole Slide Images at a Gigapixel scale","created":"2023-11-14","cited_by_count":10,"area":"diffusion"},{"id":"2110.15267","title":"UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model","created":"2021-10-28","cited_by_count":9,"area":null},{"id":"2209.00128","title":"Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata","created":"2022-08-31","cited_by_count":9,"area":null},{"id":"2107.09546","title":"Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutions","created":"2021-07-20","cited_by_count":7,"area":null},{"id":"2203.00734","title":"Knock, knock. Who's there? -- Identifying football player jersey numbers with synthetic data","created":"2022-03-01","cited_by_count":7,"area":null},{"id":"2403.18351","title":"Generating Diverse Agricultural Data for Vision-Based Farming Applications","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2410.09168","title":"Hybrid Training Approaches for LLMs: Leveraging Real and Synthetic Data to Enhance Model Performance in Domain-Specific Applications","created":"2024-10-11","cited_by_count":7,"area":"synth"},{"id":"2107.00360","title":"Towards Measuring Bias in Image Classification","created":"2021-07-01","cited_by_count":6,"area":null},{"id":"2112.02829","title":"SyntEO: Synthetic Data Set Generation for Earth Observation and Deep Learning -- Demonstrated for Offshore Wind Farm Detection","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2210.07332","title":"Secure Multiparty Computation for Synthetic Data Generation from Distributed Data","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2206.03266","title":"Machine Learning Sensors","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2305.13765","title":"Human Body Pose Estimation for Gait Identification: A Comprehensive Survey of Datasets and Models","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2306.16917","title":"The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2403.05164","title":"Synthetic data generation for system identification: leveraging knowledge transfer from similar systems","created":"2024-03-08","cited_by_count":5,"area":null},{"id":"2212.00484","title":"Differentially-Private Data Synthetisation for Efficient Re-Identification Risk Control","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2311.17453","title":"Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directions","created":"2023-11-29","cited_by_count":4,"area":null},{"id":"2408.00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","created":"2024-08-01","cited_by_count":4,"area":"alignment"},{"id":"2411.16719","title":"Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation","created":"2024-11-23","cited_by_count":4,"area":null},{"id":"2504.18762","title":"SynLexLM: Scaling Legal LLMs with Synthetic Data and Curriculum Learning","created":"2025-04-26","cited_by_count":4,"area":"synth"},{"id":"2205.10368","title":"Automatic Generation of Synthetic Colonoscopy Videos for Domain Randomization","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2212.11542","title":"Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks","created":"2022-12-22","cited_by_count":3,"area":null},{"id":"2307.09169","title":"Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2406.00505","title":"Improving Text Generation on Images with Synthetic Captions","created":"2024-06-01","cited_by_count":3,"area":"diffusion"},{"id":"2406.02736","title":"Synthetic Data Outliers: Navigating Identity Disclosure","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2408.08379","title":"Towards Realistic Synthetic User-Generated Content: A Scaffolding Approach to Generating Online Discussions","created":"2024-08-15","cited_by_count":3,"area":null},{"id":"2503.23062","title":"Shape and Texture Recognition in Large Vision-Language Models","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2101.04194","title":"Protecting Big Data Privacy Using Randomized Tensor Network Decomposition and Dispersed Tensor Computation","created":"2021-01-04","cited_by_count":2,"area":null},{"id":"2107.07330","title":"DynaDog+T: A Parametric Animal Model for Synthetic Canine Image Generation","created":"2021-07-15","cited_by_count":2,"area":null},{"id":"2212.02622","title":"Towards a Taxonomy for the Use of Synthetic Data in Advanced Analytics","created":"2022-12-05","cited_by_count":2,"area":null},{"id":"2310.06059","title":"Early Warning Prediction with Automatic Labeling in Epilepsy Patients","created":"2023-10-09","cited_by_count":2,"area":null},{"id":"2310.07310","title":"Deep Aramaic: Towards a Synthetic Data Paradigm Enabling Machine Learning in Epigraphy","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2402.07098","title":"Improving Pallet Detection Using Synthetic Data","created":"2024-02-11","cited_by_count":2,"area":null},{"id":"2403.03309","title":"Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2407.09561","title":"Integrating Deep Learning in Cardiology: A Comprehensive Review of Atrial Fibrillation, Left Atrial Scar Segmentation, and the Frontiers of State-of-the-Art Techniques","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2506.24093","title":"Development of Hybrid Artificial Intelligence Training on Real and Synthetic Data: Benchmark on Two Mixed Training Strategies","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2511.07007","title":"TrueCity: Real and Simulated Urban Data for Cross-Domain 3D Scene Understanding","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2512.19026","title":"Finer-Personalization Rank: Fine-Grained Retrieval Examines Identity Preservation for Personalized Generation","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2105.14149","title":"Log2NS: Enhancing Deep Learning Based Analysis of Logs With Formal to Prevent Survivorship Bias","created":"2021-05-29","cited_by_count":1,"area":null},{"id":"2208.02484","title":"Customs Import Declaration Datasets","created":"2022-08-04","cited_by_count":1,"area":null},{"id":"2210.07466","title":"Synthetic-to-real Composite Semantic Segmentation in Additive Manufacturing","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2212.00911","title":"Navigating causal deep learning","created":"2022-12-01","cited_by_count":1,"area":null},{"id":"2304.07883","title":"Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification","created":"2023-04-16","cited_by_count":1,"area":null},{"id":"2311.06536","title":"CrashCar101: Procedural Generation for Damage Assessment","created":"2023-11-11","cited_by_count":1,"area":null},{"id":"2403.08352","title":"Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2403.16233","title":"An early warning indicator trained on stochastic disease-spreading models with different noises","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2406.17148","title":"MixTeX: Data-Efficient LaTeX OCR via Synthetic Pretraining and Limited Fine-Tuning","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2407.19823","title":"Analyzing and reducing the synthetic-to-real transfer gap in Music Information Retrieval: the task of automatic drum transcription","created":"2024-07-29","cited_by_count":1,"area":null},{"id":"2408.07726","title":"Development of a graph neural network surrogate for travel demand modelling","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2409.02079","title":"Synthetic Data Generation and Automated Multidimensional Data Labeling for AI/ML in General and Circular Coordinates","created":"2024-09-03","cited_by_count":1,"area":null},{"id":"2503.06619","title":"Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2512.01315","title":"FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2512.05937","title":"Measuring the Effect of Background on Classification and Feature Importance in Deep Learning for AV Perception","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2602.15660","title":"Bayesian Optimization for Design Parameters of 3D Image Data Analysis","created":"2026-02-17","cited_by_count":1,"area":null},{"id":"2603.28670","title":"Sim-to-Real Fruit Detection Using Synthetic Data: Quantitative Evaluation and Embedded Deployment with Isaac Sim","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.05627","title":"Leveraging Image Generators to Address Data Scarcity: The Gen4Regen Dataset for Forest Regeneration Mapping","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.17528","title":"CasualSynth: Generating Structurally Sound Synthetic Data","created":"2026-05-17","cited_by_count":1,"area":"synth"},{"id":"2106.15257","title":"Predicting Depth from Semantic Segmentation using Game Engine Dataset","created":"2021-06-12","cited_by_count":0,"area":null},{"id":"2111.08570","title":"Tracking Blobs in the Turbulent Edge Plasma of a Tokamak Fusion Device","created":"2021-11-16","cited_by_count":0,"area":null},{"id":"2205.00538","title":"Can Information Behaviour Inform Machine Learning?","created":"2022-05-01","cited_by_count":0,"area":null},{"id":"2211.10103","title":"Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images","created":"2022-11-18","cited_by_count":0,"area":null},{"id":"2302.10490","title":"Creating Disasters: Recession Forecasting with GAN-Generated Synthetic Time Series Data","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2303.00725","title":"OSRE: Object-to-Spot Rotation Estimation for Bike Parking Assessment","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2303.04265","title":"Comparing PSDNet, pretrained networks, and traditional feature extraction for predicting the particle size distribution of granular materials from photographs","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2303.04269","title":"PSDNet: Determination of Particle Size Distributions Using Synthetic Soil Images and Convolutional Neural Networks","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2303.09056","title":"Generating synthetic multi-dimensional molecular-mediator time series data for artificial intelligence-based disease trajectory forecasting and drug development digital twins: Considerations","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2306.14377","title":"Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2306.14584","title":"Methodology for generating synthetic labeled datasets for visual container inspection","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2311.05371","title":"Training Robust Deep Physiological Measurement Models with Synthetic Video-based Data","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2312.02613","title":"A Unified Simulation Framework for Visual and Behavioral Fidelity in Crowd Analysis","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2401.00072","title":"Machine-learned models for magnetic materials","created":"2023-12-29","cited_by_count":0,"area":null},{"id":"2403.10737","title":"Leveraging Synthetic Data for Generalizable and Fair Facial Action Unit Detection","created":"2024-03-15","cited_by_count":0,"area":null},{"id":"2404.05128","title":"Importance of realism in procedurally-generated synthetic images for deep learning: case studies in maize and canola","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2404.09703","title":"AI Competitions and Benchmarks: Dataset Development","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2408.00701","title":"Joint Neural Networks for One-shot Object Recognition and Detection","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2409.04194","title":"Towards Privacy-Preserving Relational Data Synthesis via Probabilistic Relational Models","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2410.16955","title":"PGCS: Physical Law embedded Generative Cloud Synthesis in Remote Sensing Images","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2503.01266","title":"Voice Cloning for Dysarthric Speech Synthesis: Addressing Data Scarcity in Speech-Language Pathology","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2506.17847","title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2507.10606","title":"DALI-PD: Diffusion-based Synthetic Layout Heatmap Generation for ML in Physical Design","created":"2025-07-13","cited_by_count":0,"area":null},{"id":"2509.02029","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","created":"2025-09-02","cited_by_count":0,"area":null}],"next_cursor":"100"}