{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2011.08785","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","created":"2020-11-17","cited_by_count":594},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2104.04015","title":"CutPaste: Self-Supervised Learning for Anomaly Detection and Localization","created":"2021-04-08","cited_by_count":531},{"id":"2108.07610","title":"DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection","created":"2021-08-17","cited_by_count":514},{"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":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2005.02357","title":"Sub-Image Anomaly Detection with Deep Pyramid Correspondences","created":"2020-05-05","cited_by_count":300},{"id":"2310.18961","title":"AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection","created":"2023-10-29","cited_by_count":271},{"id":"2206.03687","title":"A Unified Model for Multi-class Anomaly Detection","created":"2022-06-08","cited_by_count":268},{"id":"2006.16067","title":"Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation","created":"2020-06-29","cited_by_count":212},{"id":"2008.12577","title":"Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows","created":"2020-08-28","cited_by_count":212},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160},{"id":"2211.11317","title":"DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection","created":"2022-11-21","cited_by_count":154},{"id":"2207.07361","title":"Registration based Few-Shot Anomaly Detection","created":"2022-07-15","cited_by_count":133},{"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":"2404.06564","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","created":"2024-04-09","cited_by_count":113},{"id":"2312.05767","title":"AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model","created":"2023-12-10","cited_by_count":111},{"id":"2208.01521","title":"DSR -- A dual subspace re-projection network for surface anomaly detection","created":"2022-08-02","cited_by_count":90},{"id":"2403.06495","title":"Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Prompts","created":"2024-03-11","cited_by_count":89},{"id":"2205.00908","title":"MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities","created":"2022-05-02","cited_by_count":68},{"id":"2303.02389","title":"Few-Shot Defect Image Generation via Defect-Aware Feature Manipulation","created":"2023-03-04","cited_by_count":67},{"id":"2405.00915","title":"EchoScene: Indoor Scene Generation via Information Echo over Scene Graph Diffusion","created":"2024-05-02","cited_by_count":67},{"id":"2310.14228","title":"Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection","created":"2023-10-22","cited_by_count":66},{"id":"2507.19468","title":"Back to the Features: DINO as a Foundation for Video World Models","created":"2025-07-25","cited_by_count":58},{"id":"2305.16283","title":"CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion","created":"2023-05-25","cited_by_count":54},{"id":"2311.11125","title":"SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation","created":"2023-11-18","cited_by_count":53},{"id":"2405.14529","title":"AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2","created":"2024-05-23","cited_by_count":53},{"id":"2303.08730","title":"DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection","created":"2023-03-15","cited_by_count":46},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45},{"id":"2407.12427","title":"GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features","created":"2024-07-17","cited_by_count":29},{"id":"2505.09926","title":"AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection","created":"2025-05-15","cited_by_count":29},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26},{"id":"2406.08810","title":"Few-Shot Anomaly Detection via Category-Agnostic Registration Learning","created":"2024-06-13","cited_by_count":6},{"id":"2408.01960","title":"AnomalySD: Few-Shot Multi-Class Anomaly Detection with Stable Diffusion Model","created":"2024-08-04","cited_by_count":6}],"next_cursor":null}