{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"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":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"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":"1612.00563","title":"Self-critical Sequence Training for Image Captioning","created":"2016-12-02","cited_by_count":547},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"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":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"1506.05439","title":"Learning with a Wasserstein Loss","created":"2015-06-17","cited_by_count":196},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"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":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159},{"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":"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":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125},{"id":"2303.10323","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","created":"2023-03-18","cited_by_count":118},{"id":"2308.12604","title":"PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation","created":"2023-08-24","cited_by_count":95},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76},{"id":"2303.13802","title":"Decoupled Multimodal Distilling for Emotion Recognition","created":"2023-03-24","cited_by_count":76},{"id":"2112.15011","title":"Radiology Report Generation with a Learned Knowledge Base and Multi-modal Alignment","created":"2021-12-30","cited_by_count":73},{"id":"2112.15009","title":"Knowledge Matters: Radiology Report Generation with General and Specific Knowledge","created":"2021-12-30","cited_by_count":68},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62},{"id":"1703.06029","title":"Towards Diverse and Natural Image Descriptions via a Conditional GAN","created":"2017-03-17","cited_by_count":59},{"id":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59},{"id":"2401.02015","title":"Improving Diffusion-Based Image Synthesis with Context Prediction","created":"2024-01-04","cited_by_count":32},{"id":"2410.03659","title":"Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models","created":"2024-10-04","cited_by_count":28},{"id":"2312.08078","title":"Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation","created":"2023-12-13","cited_by_count":26},{"id":"2206.01988","title":"Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation","created":"2022-06-04","cited_by_count":24},{"id":"2303.15932","title":"Unify, Align and Refine: Multi-Level Semantic Alignment for Radiology Report Generation","created":"2023-03-28","cited_by_count":23},{"id":"2402.02045","title":"MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning","created":"2024-02-03","cited_by_count":23},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22},{"id":"2311.02329","title":"Complex Organ Mask Guided Radiology Report Generation","created":"2023-11-04","cited_by_count":22},{"id":"1703.01025","title":"A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification","created":"2017-03-03","cited_by_count":13},{"id":"1809.00681","title":"Diverse and Coherent Paragraph Generation from Images","created":"2018-09-03","cited_by_count":13},{"id":"2503.01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","created":"2025-03-02","cited_by_count":11},{"id":"2005.00048","title":"Context based Text-generation using LSTM networks","created":"2020-04-30","cited_by_count":10}],"next_cursor":null}