{"total":83,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979,"area":"diffusion"},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446,"area":null},{"id":"2201.02609","title":"Generalized Category Discovery","created":"2022-01-07","cited_by_count":211,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137,"area":null},{"id":"2106.08503","title":"Understanding and Evaluating Racial Biases in Image Captioning","created":"2021-06-16","cited_by_count":108,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2310.04432","title":"Training-free Linear Image Inverses via Flows","created":"2023-09-25","cited_by_count":72,"area":"diffusion"},{"id":"2106.04169","title":"On Improving Adversarial Transferability of Vision Transformers","created":"2021-06-08","cited_by_count":70,"area":null},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60,"area":null},{"id":"2406.10328","title":"From Pixels to Prose: A Large Dataset of Dense Image Captions","created":"2024-06-14","cited_by_count":54,"area":"mllm"},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2301.02560","title":"GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition","created":"2023-01-05","cited_by_count":50,"area":null},{"id":"2108.02922","title":"Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers","created":"2021-08-06","cited_by_count":49,"area":null},{"id":"2402.09611","title":"Towards Privacy-Aware Sign Language Translation at Scale","created":"2024-02-14","cited_by_count":44,"area":null},{"id":"2405.11029","title":"Generative Artificial Intelligence: A Systematic Review and Applications","created":"2024-05-17","cited_by_count":37,"area":null},{"id":"2211.12491","title":"ModelDiff: A Framework for Comparing Learning Algorithms","created":"2022-11-22","cited_by_count":30,"area":null},{"id":"2206.13378","title":"Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning","created":"2022-06-27","cited_by_count":26,"area":null},{"id":"2203.16828","title":"Rethinking Portrait Matting with Privacy Preserving","created":"2022-03-31","cited_by_count":25,"area":null},{"id":"2208.11695","title":"Bugs in the Data: How ImageNet Misrepresents Biodiversity","created":"2022-08-24","cited_by_count":24,"area":null},{"id":"2306.08744","title":"High-performance deep spiking neural networks with 0.3 spikes per neuron","created":"2023-06-14","cited_by_count":22,"area":null},{"id":"2203.07845","title":"Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy","created":"2022-03-15","cited_by_count":21,"area":null},{"id":"2303.01112","title":"Visual Atoms: Pre-training Vision Transformers with Sinusoidal Waves","created":"2023-03-02","cited_by_count":20,"area":null},{"id":"2111.04424","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","created":"2021-10-18","cited_by_count":18,"area":null},{"id":"2201.12467","title":"Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters","created":"2022-01-29","cited_by_count":18,"area":null},{"id":"2302.03629","title":"Ethical Considerations for Responsible Data Curation","created":"2023-02-07","cited_by_count":17,"area":null},{"id":"2503.10636","title":"The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation","created":"2025-03-13","cited_by_count":17,"area":"diffusion"},{"id":"2304.13089","title":"Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations","created":"2023-04-25","cited_by_count":16,"area":null},{"id":"2210.06077","title":"Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2306.01181","title":"TMI! Finetuned Models Leak Private Information from their Pretraining Data","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2403.11121","title":"A Versatile Framework for Multi-scene Person Re-identification","created":"2024-03-17","cited_by_count":14,"area":null},{"id":"2112.05760","title":"Learning Representations with Contrastive Self-Supervised Learning for Histopathology Applications","created":"2021-12-10","cited_by_count":12,"area":null},{"id":"2212.12522","title":"An Exact Mapping From ReLU Networks to Spiking Neural Networks","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2306.05135","title":"Does Image Anonymization Impact Computer Vision Training?","created":"2023-06-08","cited_by_count":12,"area":null},{"id":"2203.07613","title":"CARETS: A Consistency And Robustness Evaluative Test Suite for VQA","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2311.13028","title":"DMLR: Data-centric Machine Learning Research -- Past, Present and Future","created":"2023-11-21","cited_by_count":11,"area":null},{"id":"2404.17249","title":"Making Better Use of Unlabelled Data in Bayesian Active Learning","created":"2024-04-26","cited_by_count":10,"area":null},{"id":"2305.02143","title":"GANonymization: A GAN-based Face Anonymization Framework for Preserving Emotional Expressions","created":"2023-05-03","cited_by_count":9,"area":null},{"id":"2402.02103","title":"D\\'ej\\`a Vu Memorization in Vision-Language Models","created":"2024-02-03","cited_by_count":9,"area":"mllm"},{"id":"2303.11643","title":"Manipulating Transfer Learning for Property Inference","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2309.17083","title":"SegRCDB: Semantic Segmentation via Formula-Driven Supervised Learning","created":"2023-09-29","cited_by_count":8,"area":null},{"id":"2207.11677","title":"Learnable Privacy-Preserving Anonymization for Pedestrian Images","created":"2022-07-24","cited_by_count":6,"area":null},{"id":"2208.08090","title":"Progressive Cross-modal Knowledge Distillation for Human Action Recognition","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2303.17176","title":"A View From Somewhere: Human-Centric Face Representations","created":"2023-03-30","cited_by_count":6,"area":null},{"id":"2111.15129","title":"Anonymization for Skeleton Action Recognition","created":"2021-11-30","cited_by_count":5,"area":null},{"id":"2205.07299","title":"Regulating Facial Processing Technologies: Tensions Between Legal and Technical Considerations in the Application of Illinois BIPA","created":"2022-05-15","cited_by_count":5,"area":null},{"id":"2206.10673","title":"Natural Backdoor Datasets","created":"2022-06-21","cited_by_count":5,"area":null},{"id":"2206.13498","title":"Auditing Visualizations: Transparency Methods Struggle to Detect Anomalous Behavior","created":"2022-06-27","cited_by_count":5,"area":null},{"id":"2306.14640","title":"3D-Aware Adversarial Makeup Generation for Facial Privacy Protection","created":"2023-06-26","cited_by_count":5,"area":null},{"id":"2311.06231","title":"Learning Human Action Recognition Representations Without Real Humans","created":"2023-11-10","cited_by_count":5,"area":null},{"id":"2403.02506","title":"Differentially Private Representation Learning via Image Captioning","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2204.12833","title":"Transfer Learning with Pre-trained Conditional Generative Models","created":"2022-04-27","cited_by_count":4,"area":null},{"id":"2304.05369","title":"A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2309.11005","title":"It's Simplex! Disaggregating Measures to Improve Certified Robustness","created":"2023-09-20","cited_by_count":4,"area":null},{"id":"2403.14421","title":"DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning","created":"2024-03-21","cited_by_count":4,"area":"rag"},{"id":"2407.18245","title":"VGGHeads: 3D Multi Head Alignment with a Large-Scale Synthetic Dataset","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2104.11721","title":"Safe Fakes: Evaluating Face Anonymizers for Face Detectors","created":"2021-04-23","cited_by_count":3,"area":null},{"id":"2111.01785","title":"PatchGame: Learning to Signal Mid-level Patches in Referential Games","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2205.10587","title":"A comprehensive survey on semantic facial attribute editing using generative adversarial networks","created":"2022-05-21","cited_by_count":3,"area":null},{"id":"2506.05014","title":"Towards Reasonable Concept Bottleneck Models","created":"2025-06-05","cited_by_count":3,"area":null},{"id":"2201.03353","title":"GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservation","created":"2022-01-10","cited_by_count":2,"area":null},{"id":"2401.00151","title":"CamPro: Camera-based Anti-Facial Recognition","created":"2023-12-30","cited_by_count":2,"area":null},{"id":"2504.05651","title":"Measuring D\\'ej\\`a vu Memorization Efficiently","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.19836","title":"Machine Learning with Privacy for Protected Attributes","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2103.06587","title":"Privacy-preserving Object Detection","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2202.02892","title":"Lossy Compression of Noisy Data for Private and Data-Efficient Learning","created":"2022-02-07","cited_by_count":1,"area":null},{"id":"2204.11143","title":"Supplementing Missing Visions via Dialog for Scene Graph Generations","created":"2022-04-23","cited_by_count":1,"area":null},{"id":"2303.13735","title":"An investigation of licensing of datasets for machine learning based on the GQM model","created":"2023-03-24","cited_by_count":1,"area":null},{"id":"2307.00481","title":"Seeing is not Believing: An Identity Hider for Human Vision Privacy Protection","created":"2023-07-02","cited_by_count":1,"area":null},{"id":"2402.01296","title":"Bi-CryptoNets: Leveraging Different-Level Privacy for Encrypted Inference","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2408.11829","title":"FAKER: Full-body Anonymization with Human Keypoint Extraction for Real-time Video Deidentification","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2106.11339","title":"Understanding top-down attention using task-oriented ablation design","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2207.11325","title":"PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation","created":"2022-07-22","cited_by_count":0,"area":null},{"id":"2211.15060","title":"Interactive Visual Feature Search","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2306.11710","title":"Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis","created":"2023-06-20","cited_by_count":0,"area":null},{"id":"2404.04821","title":"A Data-to-Product Multimodal Conceptual Framework to Achieve Automated Software Evolution for Context-rich Intelligent Applications","created":"2024-04-07","cited_by_count":0,"area":null},{"id":"2405.18800","title":"Face processing emerges from object-trained convolutional neural networks","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2509.09844","title":"Privacy-Preserving Automated Rosacea Detection Based on Medically Inspired Region of Interest Selection","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2512.16086","title":"Privacy Blur: Quantifying Privacy and Utility for Image Data Release","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.17567","title":"Face anonymization preserving facial expressions and photometric realism","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}