{"list":"other","total":81,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"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":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1908.07919","title":"Deep High-Resolution Representation Learning for Visual Recognition","created":"2019-08-20","cited_by_count":1420},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"1904.01941","title":"Character Region Awareness for Text Detection","created":"2019-04-03","cited_by_count":278},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"1704.03155","title":"EAST: An Efficient and Accurate Scene Text Detector","created":"2017-04-11","cited_by_count":248},{"id":"2308.13418","title":"Nougat: Neural Optical Understanding for Academic Documents","created":"2023-08-25","cited_by_count":245},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"2307.02499","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","created":"2023-07-04","cited_by_count":168},{"id":"1805.04953","title":"Learning Rich Features for Image Manipulation Detection","created":"2018-05-13","cited_by_count":154},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"1903.12473","title":"Shape Robust Text Detection with Progressive Scale Expansion Network","created":"2019-03-28","cited_by_count":147},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"2112.08935","title":"MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection","created":"2021-12-16","cited_by_count":117},{"id":"2007.09482","title":"Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting","created":"2020-07-18","cited_by_count":114},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96},{"id":"2108.12947","title":"Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization","created":"2021-08-30","cited_by_count":78},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2004.04940","title":"ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection","created":"2020-04-10","cited_by_count":69},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"1903.02495","title":"Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries","created":"2019-03-06","cited_by_count":59},{"id":"2310.16809","title":"Exploring OCR Capabilities of GPT-4V(ision) : A Quantitative and In-depth Evaluation","created":"2023-10-25","cited_by_count":46},{"id":"1905.05980","title":"Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation","created":"2019-05-15","cited_by_count":45},{"id":"2011.14021","title":"Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach","created":"2020-11-27","cited_by_count":45},{"id":"2112.07917","title":"SPTS: Single-Point Text Spotting","created":"2021-12-15","cited_by_count":45},{"id":"2207.11463","title":"When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition","created":"2022-07-23","cited_by_count":35},{"id":"1903.04092","title":"MTRNet: A Generic Scene Text Eraser","created":"2019-03-11","cited_by_count":29},{"id":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29},{"id":"1812.00723","title":"EnsNet: Ensconce Text in the Wild","created":"2018-12-03","cited_by_count":27},{"id":"1705.02772","title":"Scene Text Eraser","created":"2017-05-08","cited_by_count":26},{"id":"1912.07183","title":"MTRNet++: One-stage Mask-based Scene Text Eraser","created":"2019-12-16","cited_by_count":24},{"id":"2104.11493","title":"Stroke-Based Scene Text Erasing Using Synthetic Data for Training","created":"2021-04-23","cited_by_count":20},{"id":"2011.09768","title":"Scene text removal via cascaded text stroke detection and erasing","created":"2020-11-19","cited_by_count":18},{"id":"2207.10273","title":"Don't Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context","created":"2022-07-21","cited_by_count":18},{"id":"2207.14801","title":"Recognition of Handwritten Chinese Text by Segmentation: A Segment-annotation-free Approach","created":"2022-07-29","cited_by_count":15},{"id":"1911.09026","title":"Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation","created":"2019-11-19","cited_by_count":14},{"id":"2210.07489","title":"The Surprisingly Straightforward Scene Text Removal Method With Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis","created":"2022-10-14","cited_by_count":13},{"id":"2306.09593","title":"FETNet: Feature Erasing and Transferring Network for Scene Text Removal","created":"2023-06-16","cited_by_count":12},{"id":"2306.12106","title":"ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining","created":"2023-06-21","cited_by_count":12},{"id":"2204.12743","title":"Self-Supervised Text Erasing with Controllable Image Synthesis","created":"2022-04-27","cited_by_count":9},{"id":"2207.11469","title":"Progressive Scene Text Erasing with Self-Supervision","created":"2022-07-23","cited_by_count":9},{"id":"2306.07842","title":"PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network","created":"2023-06-13","cited_by_count":9},{"id":"1807.07696","title":"Automatic Semantic Content Removal by Learning to Neglect","created":"2018-07-20","cited_by_count":8},{"id":"2207.14807","title":"PageNet: Towards End-to-End Weakly Supervised Page-Level Handwritten Chinese Text Recognition","created":"2022-07-29","cited_by_count":8}],"next_cursor":null}