{"list":"other","total":60,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"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":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"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":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2106.11539","title":"DocFormer: End-to-End Transformer for Document Understanding","created":"2021-06-22","cited_by_count":256},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2110.00061","title":"PubTables-1M: Towards comprehensive table extraction from unstructured documents","created":"2021-09-30","cited_by_count":126},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2101.00529","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","created":"2021-01-02","cited_by_count":110},{"id":"2110.08484","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","created":"2021-10-16","cited_by_count":101},{"id":"2101.09465","title":"WebSRC: A Dataset for Web-Based Structural Reading Comprehension","created":"2021-01-23","cited_by_count":100},{"id":"2010.04295","title":"Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements","created":"2020-10-08","cited_by_count":95},{"id":"2107.13731","title":"UIBert: Learning Generic Multimodal Representations for UI Understanding","created":"2021-07-29","cited_by_count":95},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72},{"id":"2103.16110","title":"Kaleido-BERT: Vision-Language Pre-training on Fashion Domain","created":"2021-03-30","cited_by_count":67},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67},{"id":"2209.14927","title":"Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus","created":"2022-09-29","cited_by_count":62},{"id":"2206.08358","title":"MixGen: A New Multi-Modal Data Augmentation","created":"2022-06-16","cited_by_count":61},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45},{"id":"2402.05472","title":"Question Aware Vision Transformer for Multimodal Reasoning","created":"2024-02-08","cited_by_count":32},{"id":"1906.05896","title":"Learning Instance Occlusion for Panoptic Segmentation","created":"2019-06-13","cited_by_count":30},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15},{"id":"2109.12178","title":"MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling","created":"2021-09-24","cited_by_count":11},{"id":"2403.02249","title":"Non-autoregressive Sequence-to-Sequence Vision-Language Models","created":"2024-03-04","cited_by_count":5},{"id":"2305.07019","title":"Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts","created":"2023-05-11","cited_by_count":3}],"next_cursor":null}