{"list":"other","total":157,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"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":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"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":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"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":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2106.08265","title":"Towards Total Recall in Industrial Anomaly Detection","created":"2021-06-15","cited_by_count":776},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642},{"id":"2011.08785","title":"PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization","created":"2020-11-17","cited_by_count":594},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"1904.02639","title":"Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection","created":"2019-04-04","cited_by_count":564},{"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":"1911.02357","title":"Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings","created":"2019-11-06","cited_by_count":386},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1901.03407","title":"Deep Learning for Anomaly Detection: A Survey","created":"2019-01-10","cited_by_count":358},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2011.11108","title":"Multiresolution Knowledge Distillation for Anomaly Detection","created":"2020-11-22","cited_by_count":285},{"id":"2304.13785","title":"Customized Segment Anything Model for Medical Image Segmentation","created":"2023-04-26","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":"1604.04574","title":"Learning Temporal Regularity in Video Sequences","created":"2016-04-15","cited_by_count":254},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235},{"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":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220},{"id":"2008.12577","title":"Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows","created":"2020-08-28","cited_by_count":212},{"id":"2202.11539","title":"Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut","created":"2022-02-23","cited_by_count":167},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"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":"2011.07491","title":"Anomaly Detection in Video via Self-Supervised and Multi-Task Learning","created":"2020-11-15","cited_by_count":148},{"id":"2301.11514","title":"Deep Industrial Image Anomaly Detection: A Survey","created":"2023-01-27","cited_by_count":148},{"id":"2103.04257","title":"Student-Teacher Feature Pyramid Matching for Anomaly Detection","created":"2021-03-07","cited_by_count":146},{"id":"2207.07361","title":"Registration based Few-Shot Anomaly Detection","created":"2022-07-15","cited_by_count":133},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131},{"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":"2308.11681","title":"VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection","created":"2023-08-22","cited_by_count":123},{"id":"2111.09099","title":"Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection","created":"2021-11-17","cited_by_count":119},{"id":"1911.07389","title":"Towards Visually Explaining Variational Autoencoders","created":"2019-11-18","cited_by_count":113},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"1901.08954","title":"Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detection","created":"2019-01-25","cited_by_count":100},{"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":"2104.13897","title":"Inpainting Transformer for Anomaly Detection","created":"2021-04-28","cited_by_count":91},{"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":"2404.01014","title":"Harnessing Large Language Models for Training-free Video Anomaly Detection","created":"2024-04-01","cited_by_count":87},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84},{"id":"1708.09644","title":"Abnormal Event Detection in Videos using Generative Adversarial Nets","created":"2017-08-31","cited_by_count":82},{"id":"2203.00259","title":"Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection","created":"2022-03-01","cited_by_count":80},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75},{"id":"2206.02904","title":"The Creativity of Text-to-Image Generation","created":"2022-05-13","cited_by_count":73},{"id":"2104.06689","title":"Learning Normal Dynamics in Videos with Meta Prototype Network","created":"2021-04-14","cited_by_count":71},{"id":"2211.12634","title":"PNI : Industrial Anomaly Detection using Position and Neighborhood Information","created":"2022-11-22","cited_by_count":69},{"id":"2203.00759","title":"HyperPrompt: Prompt-based Task-Conditioning of Transformers","created":"2022-03-01","cited_by_count":67},{"id":"2212.05136","title":"CLIP-TSA: CLIP-Assisted Temporal Self-Attention for Weakly-Supervised Video Anomaly Detection","created":"2022-12-09","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":"2302.05087","title":"Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models","created":"2023-02-10","cited_by_count":59},{"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":"2306.05067","title":"Improving Visual Prompt Tuning for Self-supervised Vision Transformers","created":"2023-06-08","cited_by_count":57}],"next_cursor":"100"}