{"list":"other","total":94,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"1901.07042","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","created":"2019-01-21","cited_by_count":597},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2004.09167","title":"CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT","created":"2020-04-20","cited_by_count":337},{"id":"1904.03582","title":"Multi-Label Image Recognition with Graph Convolutional Networks","created":"2019-04-07","cited_by_count":322},{"id":"2106.14463","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","created":"2021-06-28","cited_by_count":319},{"id":"2304.13785","title":"Customized Segment Anything Model for Medical Image Segmentation","created":"2023-04-26","cited_by_count":280},{"id":"1902.07669","title":"ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing","created":"2019-02-20","cited_by_count":244},{"id":"1612.01887","title":"Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning","created":"2016-12-06","cited_by_count":232},{"id":"1711.08195","title":"On the Automatic Generation of Medical Imaging Reports","created":"2017-11-22","cited_by_count":216},{"id":"2204.13258","title":"Cross-modal Memory Networks for Radiology Report Generation","created":"2022-04-28","cited_by_count":185},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154},{"id":"2002.08277","title":"When Radiology Report Generation Meets Knowledge Graph","created":"2020-02-19","cited_by_count":145},{"id":"1805.08298","title":"Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation","created":"2018-05-21","cited_by_count":141},{"id":"2010.10042","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","created":"2020-10-20","cited_by_count":141},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140},{"id":"1801.04334","title":"TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays","created":"2018-01-12","cited_by_count":139},{"id":"2303.10323","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","created":"2023-03-18","cited_by_count":118},{"id":"1903.10122","title":"Knowledge-driven Encode, Retrieve, Paraphrase for Medical Image Report Generation","created":"2019-03-25","cited_by_count":102},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101},{"id":"2201.09405","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","created":"2022-01-24","cited_by_count":95},{"id":"1412.6632","title":"Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)","created":"2014-12-20","cited_by_count":94},{"id":"2003.13865","title":"COVID-CT-Dataset: A CT Scan Dataset about COVID-19","created":"2020-03-30","cited_by_count":94},{"id":"2108.00316","title":"Chest ImaGenome Dataset for Clinical Reasoning","created":"2021-07-31","cited_by_count":90},{"id":"2210.12186","title":"Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards","created":"2022-10-21","cited_by_count":83},{"id":"1712.05898","title":"NegBio: a high-performance tool for negation and uncertainty detection in radiology reports","created":"2017-12-16","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":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71},{"id":"2203.10095","title":"AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation","created":"2022-03-18","cited_by_count":65},{"id":"2005.01795","title":"Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques","created":"2020-05-04","cited_by_count":64},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62},{"id":"2306.07971","title":"XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models","created":"2023-06-13","cited_by_count":61},{"id":"1907.09085","title":"Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment","created":"2019-07-22","cited_by_count":60},{"id":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59},{"id":"1811.00739","title":"An Empirical Exploration of Curriculum Learning for Neural Machine Translation","created":"2018-11-02","cited_by_count":58},{"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":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47},{"id":"2208.10358","title":"A Medical Semantic-Assisted Transformer for Radiographic Report Generation","created":"2022-08-22","cited_by_count":44},{"id":"2102.09777","title":"Progressive Transformer-Based Generation of Radiology Reports","created":"2021-02-19","cited_by_count":43},{"id":"2306.06466","title":"ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning","created":"2023-06-10","cited_by_count":42},{"id":"2109.12242","title":"Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation","created":"2021-09-25","cited_by_count":41},{"id":"2006.10550","title":"ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities","created":"2020-06-17","cited_by_count":38},{"id":"2212.03099","title":"Semantic-Conditional Diffusion Networks for Image Captioning","created":"2022-12-06","cited_by_count":38},{"id":"2006.03744","title":"Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation","created":"2020-06-06","cited_by_count":35},{"id":"2107.02104","title":"RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting","created":"2021-07-05","cited_by_count":34},{"id":"1905.13302","title":"A Survey on Biomedical Image Captioning","created":"2019-05-26","cited_by_count":30},{"id":"2102.11467","title":"VisualCheXbert: Addressing the Discrepancy Between Radiology Report Labels and Image Labels","created":"2021-02-23","cited_by_count":27},{"id":"1512.08756","title":"Feed-Forward Networks with Attention Can Solve Some Long-Term Memory Problems","created":"2015-12-29","cited_by_count":23},{"id":"2002.12585","title":"Exploring and Distilling Cross-Modal Information for Image Captioning","created":"2020-02-28","cited_by_count":19},{"id":"2010.02467","title":"Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays","created":"2020-10-06","cited_by_count":18},{"id":"2310.12995","title":"Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models","created":"2023-10-04","cited_by_count":18},{"id":"2207.01208","title":"Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation","created":"2022-07-04","cited_by_count":17},{"id":"1908.02123","title":"Addressing Data Bias Problems for Chest X-ray Image Report Generation","created":"2019-08-06","cited_by_count":14},{"id":"2209.13171","title":"RepsNet: Combining Vision with Language for Automated Medical Reports","created":"2022-09-27","cited_by_count":14},{"id":"2309.11758","title":"SAM-OCTA: A Fine-Tuning Strategy for Applying Foundation Model to OCTA Image Segmentation Tasks","created":"2023-09-21","cited_by_count":14},{"id":"2310.18642","title":"One-shot Localization and Segmentation of Medical Images with Foundation Models","created":"2023-10-28","cited_by_count":14},{"id":"2306.17180","title":"Replace and Report: NLP Assisted Radiology Report Generation","created":"2023-06-19","cited_by_count":10},{"id":"2211.11380","title":"Self adaptive global-local feature enhancement for radiology report generation","created":"2022-11-21","cited_by_count":7},{"id":"2101.07299","title":"Diagnostic Captioning: A Survey","created":"2021-01-18","cited_by_count":6},{"id":"2308.09331","title":"SAMedOCT: Adapting Segment Anything Model (SAM) for Retinal OCT","created":"2023-08-18","cited_by_count":6},{"id":"2206.06308","title":"Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictation","created":"2022-06-13","cited_by_count":4},{"id":"2309.08434","title":"Segment Anything Model for Brain Tumor Segmentation","created":"2023-09-15","cited_by_count":4},{"id":"2310.00504","title":"Exploring SAM Ablations for Enhancing Medical Segmentation in Radiology and Pathology","created":"2023-09-30","cited_by_count":4}],"next_cursor":null}