{"list":"other","total":88,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"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":"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"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":"1911.02357","title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","created":"2019-11-06","cited_by_count":386},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315},{"id":"2305.16986","title":"NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models","created":"2023-05-26","cited_by_count":280},{"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":"2203.04306","title":"Diffusion Models for Medical Anomaly Detection","created":"2022-03-08","cited_by_count":232},{"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":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2112.09045","title":"The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization","created":"2021-12-16","cited_by_count":178},{"id":"2308.15366","title":"AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models","created":"2023-08-29","cited_by_count":171},{"id":"2211.11317","title":"DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection","created":"2022-11-21","cited_by_count":154},{"id":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","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":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2311.00899","title":"RoboVQA: Multimodal Long-Horizon Reasoning for Robotics","created":"2023-11-01","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":"2403.05897","title":"RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection","created":"2024-03-09","cited_by_count":116},{"id":"2404.05231","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","created":"2024-04-08","cited_by_count":98},{"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":"2106.03844","title":"Mean-Shifted Contrastive Loss for Anomaly Detection","created":"2021-06-07","cited_by_count":88},{"id":"2309.13226","title":"Real3D-AD: A Dataset of Point Cloud Anomaly Detection","created":"2023-09-23","cited_by_count":87},{"id":"2107.13118","title":"Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection","created":"2021-07-28","cited_by_count":83},{"id":"2306.11876","title":"BMAD: Benchmarks for Medical Anomaly Detection","created":"2023-06-20","cited_by_count":82},{"id":"2301.12082","title":"Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore","created":"2023-01-28","cited_by_count":75},{"id":"2407.09359","title":"A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization","created":"2024-07-12","cited_by_count":74},{"id":"2311.18836","title":"ChatPose: Chatting about 3D Human Pose","created":"2023-11-30","cited_by_count":72},{"id":"2403.12570","title":"Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images","created":"2024-03-19","cited_by_count":69},{"id":"2101.10043","title":"Deep One-Class Classification via Interpolated Gaussian Descriptor","created":"2021-01-25","cited_by_count":67},{"id":"2311.14897","title":"Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network","created":"2023-11-25","cited_by_count":67},{"id":"2404.13671","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","created":"2024-04-21","cited_by_count":51},{"id":"2007.13559","title":"MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction","created":"2020-07-24","cited_by_count":50},{"id":"2405.13800","title":"Dense Connector for MLLMs","created":"2024-05-22","cited_by_count":49},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47},{"id":"2311.09999","title":"TransFusion -- A Transparency-Based Diffusion Model for Anomaly Detection","created":"2023-11-16","cited_by_count":43},{"id":"2404.16670","title":"EmoVIT: Revolutionizing Emotion Insights with Visual Instruction Tuning","created":"2024-04-25","cited_by_count":43},{"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":"2404.09654","title":"Do LLMs Understand Visual Anomalies? Uncovering LLM's Capabilities in Zero-shot Anomaly Detection","created":"2024-04-15","cited_by_count":36},{"id":"1807.02894","title":"Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images","created":"2018-07-08","cited_by_count":35},{"id":"2303.13845","title":"Anomaly Detection under Distribution Shift","created":"2023-03-24","cited_by_count":35},{"id":"2306.14899","title":"FunQA: Towards Surprising Video Comprehension","created":"2023-06-26","cited_by_count":35},{"id":"2405.11315","title":"MediCLIP: Adapting CLIP for Few-shot Medical Image Anomaly Detection","created":"2024-05-18","cited_by_count":35},{"id":"2211.14307","title":"MAEDAY: MAE for few and zero shot AnomalY-Detection","created":"2022-11-25","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":"2403.13349","title":"Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection","created":"2024-03-20","cited_by_count":28},{"id":"2312.08917","title":"An Incremental Unified Framework for Small Defect Inspection","created":"2023-12-14","cited_by_count":25},{"id":"2108.11168","title":"Adversarially Robust One-class Novelty Detection","created":"2021-08-25","cited_by_count":24},{"id":"2410.10289","title":"Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection","created":"2024-10-14","cited_by_count":22},{"id":"2303.15167","title":"Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features","created":"2023-03-27","cited_by_count":21},{"id":"2403.11561","title":"Learning Unified Reference Representation for Unsupervised Multi-class Anomaly Detection","created":"2024-03-18","cited_by_count":19},{"id":"2403.20236","title":"Long-Tailed Anomaly Detection with Learnable Class Names","created":"2024-03-29","cited_by_count":14},{"id":"2302.12464","title":"RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection","created":"2023-02-24","cited_by_count":12},{"id":"2310.05872","title":"ViCor: Bridging Visual Understanding and Commonsense Reasoning with Large Language Models","created":"2023-10-09","cited_by_count":12},{"id":"2403.06247","title":"Text-Guided Variational Image Generation for Industrial Anomaly Detection and Segmentation","created":"2024-03-10","cited_by_count":11},{"id":"2409.00304","title":"StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models","created":"2024-08-31","cited_by_count":8},{"id":"2407.15763","title":"Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis","created":"2024-07-22","cited_by_count":4}],"next_cursor":null}