{"total":69,"rows":[{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974,"area":null},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2306.09345","title":"Evaluating Data Attribution for Text-to-Image Models","created":"2023-06-15","cited_by_count":45,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2411.00113","title":"A Geometric Framework for Understanding Memorization in Generative Models","created":"2024-10-31","cited_by_count":40,"area":null},{"id":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36,"area":null},{"id":"2605.11061","title":"HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer","created":"2026-05-11","cited_by_count":32,"area":null},{"id":"2401.14732","title":"Residual Quantization with Implicit Neural Codebooks","created":"2024-01-26","cited_by_count":25,"area":null},{"id":"2312.04966","title":"NewMove: Customizing text-to-video models with novel motions","created":"2023-12-07","cited_by_count":18,"area":null},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2304.03378","title":"Self-Supervised Video Similarity Learning","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2402.19119","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2502.12976","title":"Does Training with Synthetic Data Truly Protect Privacy?","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2512.02009","title":"AirSim360: A Panoramic Simulation Platform within Drone View","created":"2025-12-01","cited_by_count":12,"area":null},{"id":"2308.02752","title":"DeDrift: Robust Similarity Search under Content Drift","created":"2023-08-05","cited_by_count":11,"area":null},{"id":"2308.07688","title":"Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images","created":"2023-08-15","cited_by_count":11,"area":null},{"id":"2205.12358","title":"A Benchmark and Asymmetrical-Similarity Learning for Practical Image Copy Detection","created":"2022-05-24","cited_by_count":9,"area":null},{"id":"2306.09489","title":"The 2023 Video Similarity Dataset and Challenge","created":"2023-06-15","cited_by_count":9,"area":null},{"id":"2407.15566","title":"Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval","created":"2024-07-22","cited_by_count":9,"area":null},{"id":"2411.04709","title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2502.04901","title":"On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark","created":"2025-02-07","cited_by_count":9,"area":null},{"id":"2210.10620","title":"Active Image Indexing","created":"2022-10-05","cited_by_count":8,"area":null},{"id":"2305.17048","title":"Intrinsic Self-Supervision for Data Quality Audits","created":"2023-05-26","cited_by_count":8,"area":null},{"id":"2406.15386","title":"U Can't Gen This? A Survey of Intellectual Property Protection Methods for Data in Generative AI","created":"2024-04-22","cited_by_count":7,"area":null},{"id":"2605.30341","title":"GPIC: A Giant Permissive Image Corpus for Visual Generation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2312.00057","title":"VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models","created":"2023-11-29","cited_by_count":5,"area":null},{"id":"2404.13788","title":"AnyPattern: Towards In-context Image Copy Detection","created":"2024-04-21","cited_by_count":5,"area":null},{"id":"2304.02296","title":"Data Leakage Detection and De-duplication in Large Scale Geospatial Image Datasets","created":"2023-04-05","cited_by_count":4,"area":null},{"id":"2408.12396","title":"Cross-Domain Foundation Model Adaptation: Pioneering Computer Vision Models for Geophysical Data Analysis","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2305.12361","title":"A Dual-level Detection Method for Video Copy Detection","created":"2023-05-21","cited_by_count":3,"area":null},{"id":"2412.14432","title":"IntroStyle: Training-Free Introspective Style Attribution using Diffusion Features","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2509.00641","title":"AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2304.11964","title":"3rd Place Solution to Meta AI Video Similarity Challenge","created":"2023-04-24","cited_by_count":2,"area":null},{"id":"2406.13283","title":"Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation","created":"2024-06-19","cited_by_count":2,"area":null},{"id":"2407.11401","title":"EndoFinder: Online Image Retrieval for Explainable Colorectal Polyp Diagnosis","created":"2024-07-16","cited_by_count":2,"area":null},{"id":"2505.09435","title":"Endo-CLIP: Progressive Self-Supervised Pre-training on Raw Colonoscopy Records","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2509.16582","title":"A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis","created":"2025-09-20","cited_by_count":2,"area":null},{"id":"2311.15478","title":"HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2405.17928","title":"Relational Self-supervised Distillation with Compact Descriptors for Image Copy Detection","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2407.03463","title":"Precision at Scale: Domain-Specific Datasets On-Demand","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2411.10087","title":"PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse","created":"2024-11-15","cited_by_count":1,"area":null},{"id":"2501.10479","title":"Lossless Compression of Vector IDs for Approximate Nearest Neighbor Search","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2501.11171","title":"Counteracting temporal attacks in Video Copy Detection","created":"2025-01-19","cited_by_count":1,"area":null},{"id":"2502.16931","title":"Machine learning and high dimensional vector search","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2507.18633","title":"Identifying Prompted Artist Names from Generated Images","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2509.00488","title":"Localizing and Mitigating Memorization in Image Autoregressive Models","created":"2025-08-30","cited_by_count":1,"area":null},{"id":"2510.09171","title":"Instance-Level Generation for Representation Learning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2512.23628","title":"Memorization in 3D Shape Generation: An Empirical Study","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2601.22663","title":"Unsupervised Synthetic Image Attribution: Alignment and Disentanglement","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2603.15967","title":"A Comprehensive Benchmark of Histopathology Foundation Models for Kidney Digital Pathology Images","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2606.27371","title":"Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2403.10746","title":"Vector search with small radiuses","created":"2024-03-16","cited_by_count":0,"area":null},{"id":"2408.06157","title":"3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2505.02746","title":"Using Knowledge Graphs to harvest datasets for efficient CLIP model training","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2510.25687","title":"Model Inversion meets Cryptographic Fuzzy Extractors","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2511.18204","title":"Generating Synthetic Human Blastocyst Images for In-Vitro Fertilization Blastocyst Grading","created":"2025-11-22","cited_by_count":0,"area":null},{"id":"2602.07149","title":"Privacy in Image Datasets: A Case Study on Pregnancy Ultrasounds","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.17484","title":"Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2604.05296","title":"From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.06063","title":"EDGE-Shield: Efficient Denoising-staGE Shield for Violative Content Filtering via Scalable Reference-Based Matching","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2607.13728","title":"Cluster with Auctions for Vector Search","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.03101","title":"Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.07063","title":"Soft Redaction of Image Provenance via Zero-Knowledge Proofs","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.14730","title":"IP Protection in the Era of Visual Generative AI: A Survey","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.03615","title":"Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.00251","title":"The Null Is the Hard Part: Exact Tests for Memorization in Generative Models","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}