{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"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":"1703.05921","title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","created":"2017-03-17","cited_by_count":566},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"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":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2107.12571","title":"CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows","created":"2021-07-27","cited_by_count":321},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2302.12242","title":"Side Adapter Network for Open-Vocabulary Semantic Segmentation","created":"2023-02-23","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":"2303.15140","title":"SimpleNet: A Simple Network for Image Anomaly Detection and Localization","created":"2023-03-27","cited_by_count":256},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2301.00785","title":"CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection","created":"2023-01-02","cited_by_count":224},{"id":"2104.10036","title":"VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization","created":"2021-04-20","cited_by_count":223},{"id":"1612.00799","title":"A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images","created":"2016-12-02","cited_by_count":221},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2211.11317","title":"DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection","created":"2022-11-21","cited_by_count":154},{"id":"2103.04257","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","created":"2021-03-07","cited_by_count":146},{"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":"2012.02364","title":"Deep Learning for Medical Anomaly Detection -- A Survey","created":"2020-12-04","cited_by_count":127},{"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":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2212.09506","title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","created":"2022-12-16","cited_by_count":118},{"id":"2308.10916","title":"Diffusion Model as Representation Learner","created":"2023-08-21","cited_by_count":95},{"id":"2305.07304","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","created":"2023-05-12","cited_by_count":83},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"2205.13115","title":"Fine-grained Image Captioning with CLIP Reward","created":"2022-05-26","cited_by_count":69},{"id":"2309.13625","title":"GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph","created":"2023-09-24","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":"2310.14228","title":"Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection","created":"2023-10-22","cited_by_count":66},{"id":"2305.10724","title":"Segment Any Anomaly without Training via Hybrid Prompt Regularization","created":"2023-05-18","cited_by_count":60},{"id":"2311.00453","title":"CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection","created":"2023-11-01","cited_by_count":58},{"id":"2407.12276","title":"VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation","created":"2024-07-17","cited_by_count":50},{"id":"2009.06456","title":"Label-Free Segmentation of COVID-19 Lesions in Lung CT","created":"2020-09-08","cited_by_count":37},{"id":"2312.06607","title":"DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection","created":"2023-12-11","cited_by_count":33},{"id":"2209.01816","title":"ADTR: Anomaly Detection Transformer with Feature Reconstruction","created":"2022-09-05","cited_by_count":31},{"id":"2212.12043","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","created":"2022-12-22","cited_by_count":23},{"id":"2409.06809","title":"DetailCLIP: Detail-Oriented CLIP for Fine-Grained Tasks","created":"2024-09-10","cited_by_count":15},{"id":"2501.12295","title":"Towards Accurate Unified Anomaly Segmentation","created":"2025-01-21","cited_by_count":7},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4},{"id":"2312.01679","title":"Adversarial Medical Image with Hierarchical Feature Hiding","created":"2023-12-04","cited_by_count":3}],"next_cursor":null}