{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"1909.11059","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","created":"2019-09-24","cited_by_count":494},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"2106.14463","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","created":"2021-06-28","cited_by_count":319},{"id":"1901.07441","title":"PadChest: A large chest x-ray image dataset with multi-label annotated reports","created":"2019-01-22","cited_by_count":309},{"id":"1805.07932","title":"Bilinear Attention Networks","created":"2018-05-21","cited_by_count":280},{"id":"1511.02274","title":"Stacked Attention Networks for Image Question Answering","created":"2015-11-07","cited_by_count":273},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"1606.01847","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","created":"2016-06-06","cited_by_count":243},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"id":"2104.03135","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","created":"2021-04-07","cited_by_count":187},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"1805.08298","title":"Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation","created":"2018-05-21","cited_by_count":141},{"id":"1705.06676","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","created":"2017-05-18","cited_by_count":137},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"2209.07098","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","created":"2022-09-15","cited_by_count":104},{"id":"1903.10122","title":"Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation","created":"2019-03-25","cited_by_count":102},{"id":"2006.01174","title":"BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients","created":"2020-06-01","cited_by_count":82},{"id":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76},{"id":"1909.11867","title":"Overcoming Data Limitation in Medical Visual Question Answering","created":"2019-09-26","cited_by_count":71},{"id":"2010.06000","title":"MedICaT: A Dataset of Medical Images, Captions, and Textual References","created":"2020-10-12","cited_by_count":71},{"id":"2104.01394","title":"MMBERT: Multimodal BERT Pretraining for Improved Medical VQA","created":"2021-04-03","cited_by_count":68},{"id":"2004.12274","title":"Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports","created":"2020-04-26","cited_by_count":58},{"id":"2209.07118","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","created":"2022-09-15","cited_by_count":51},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47},{"id":"2105.00136","title":"Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering","created":"2021-05-01","cited_by_count":26},{"id":"2103.16022","title":"Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays","created":"2021-03-30","cited_by_count":16},{"id":"1811.08615","title":"Unsupervised Multimodal Representation Learning across Medical Images and Reports","created":"2018-11-21","cited_by_count":15}],"next_cursor":null}