{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2107.02314","title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","created":"2021-07-05","cited_by_count":518},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514},{"id":"2306.14565","title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","created":"2023-06-26","cited_by_count":445},{"id":"2201.10703","title":"Anomaly Detection via Reverse Distillation from One-Class Embedding","created":"2022-01-26","cited_by_count":421},{"id":"2207.14315","title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","created":"2022-07-28","cited_by_count":400},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"1805.10917","title":"Deep Anomaly Detection Using Geometric Transformations","created":"2018-05-28","cited_by_count":269},{"id":"2303.15140","title":"SimpleNet: A Simple Network for Image Anomaly Detection and Localization","created":"2023-03-27","cited_by_count":256},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160},{"id":"2305.17382","title":"APRIL-GAN: A Zero-/Few-Shot Anomaly Classification and Segmentation Method for CVPR 2023 VAND Workshop Challenge Tracks 1&2: 1st Place on Zero-shot AD and 4th Place on Few-shot AD","created":"2023-05-27","cited_by_count":130},{"id":"2407.15795","title":"AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection","created":"2024-07-22","cited_by_count":127},{"id":"2403.05897","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","created":"2024-03-09","cited_by_count":116},{"id":"2310.08825","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","created":"2023-10-13","cited_by_count":98},{"id":"2404.05231","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","created":"2024-04-08","cited_by_count":98},{"id":"2107.13118","title":"Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection","created":"2021-07-28","cited_by_count":83},{"id":"2301.12082","title":"Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore","created":"2023-01-28","cited_by_count":75},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73},{"id":"2211.12634","title":"PNI : Industrial Anomaly Detection using Position and Neighborhood Information","created":"2022-11-22","cited_by_count":69},{"id":"2308.13712","title":"Residual Denoising Diffusion Models","created":"2023-08-25","cited_by_count":69},{"id":"2403.12570","title":"Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images","created":"2024-03-19","cited_by_count":69},{"id":"2502.07601","title":"Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models","created":"2025-02-11","cited_by_count":54},{"id":"2406.07487","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","created":"2024-06-11","cited_by_count":42},{"id":"2303.03373","title":"Detecting Human-Object Contact in Images","created":"2023-03-06","cited_by_count":41},{"id":"2305.16713","title":"ReConPatch : Contrastive Patch Representation Learning for Industrial Anomaly Detection","created":"2023-05-26","cited_by_count":30},{"id":"2407.12427","title":"GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features","created":"2024-07-17","cited_by_count":29},{"id":"2412.03342","title":"UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection","created":"2024-12-04","cited_by_count":28},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26},{"id":"2403.09303","title":"Rethinking Autoencoders for Medical Anomaly Detection from A Theoretical Perspective","created":"2024-03-14","cited_by_count":23},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","cited_by_count":21},{"id":"2209.12441","title":"Visual Anomaly Detection Via Partition Memory Bank Module and Error Estimation","created":"2022-09-26","cited_by_count":20},{"id":"2312.13783","title":"Few Shot Part Segmentation Reveals Compositional Logic for Industrial Anomaly Detection","created":"2023-12-21","cited_by_count":19},{"id":"2307.03101","title":"Contextual Affinity Distillation for Image Anomaly Detection","created":"2023-07-06","cited_by_count":18},{"id":"2412.17458","title":"Progressive Boundary Guided Anomaly Synthesis for Industrial Anomaly Detection","created":"2024-12-23","cited_by_count":17},{"id":"2406.00625","title":"SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection","created":"2024-06-02","cited_by_count":14},{"id":"2503.19357","title":"Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection","created":"2025-03-25","cited_by_count":11},{"id":"2408.03888","title":"Dual-Modeling Decouple Distillation for Unsupervised Anomaly Detection","created":"2024-08-07","cited_by_count":10},{"id":"2503.20252","title":"LogicQA: Logical Anomaly Detection with Vision Language Model Generated Questions","created":"2025-03-26","cited_by_count":9},{"id":"2405.06875","title":"LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization","created":"2024-05-11","cited_by_count":7},{"id":"2411.05822","title":"SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications","created":"2024-11-05","cited_by_count":2}],"next_cursor":null}