{"total":20,"rows":[{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162,"area":null},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"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,"area":null},{"id":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2105.07205","title":"Rethinking Skip Connection with Layer Normalization in Transformers and ResNets","created":"2021-05-15","cited_by_count":22,"area":null},{"id":"2108.02359","title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning","created":"2021-08-05","cited_by_count":18,"area":null},{"id":"2404.00588","title":"Memory-based Cross-modal Semantic Alignment Network for Radiology Report Generation","created":"2024-03-31","cited_by_count":11,"area":null},{"id":"2210.10914","title":"Prophet Attention: Predicting Attention with Future Attention for Image Captioning","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2106.10658","title":"Exploring Semantic Relationships for Unpaired Image Captioning","created":"2021-06-20","cited_by_count":6,"area":null},{"id":"2206.05311","title":"Graph-in-Graph Network for Automatic Gene Ontology Description Generation","created":"2022-06-10","cited_by_count":5,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2203.05346","title":"Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling","created":"2022-03-10","cited_by_count":3,"area":null},{"id":"2107.01571","title":"Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model","created":"2021-07-04","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2305.18165","title":"An Emergency Disposal Decision-making Method with Human--Machine Collaboration","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2308.05633","title":"IIHT: Medical Report Generation with Image-to-Indicator Hierarchical Transformer","created":"2023-08-10","cited_by_count":0,"area":null},{"id":"2506.03178","title":"LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2512.23185","title":"EIR: Enhanced Image Representations for Medical Report Generation","created":"2025-12-29","cited_by_count":0,"area":null}],"next_cursor":null}