{"list":"other","total":56,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1812.08434","title":"Graph Neural Networks: A Review of Methods and Applications","created":"2018-12-20","cited_by_count":1576},{"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":"1312.6203","title":"Spectral Networks and Locally Connected Networks on Graphs","created":"2013-12-21","cited_by_count":1102},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2105.14491","title":"How Attentive are Graph Attention Networks?","created":"2021-05-30","cited_by_count":835},{"id":"1912.01991","title":"Self-Supervised Learning of Pretext-Invariant Representations","created":"2019-12-04","cited_by_count":808},{"id":"2111.14791","title":"Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis","created":"2021-11-29","cited_by_count":422},{"id":"2401.04722","title":"U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation","created":"2024-01-09","cited_by_count":419},{"id":"1702.01806","title":"Beam Search Strategies for Neural Machine Translation","created":"2017-02-06","cited_by_count":232},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"id":"2403.17834","title":"Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","created":"2024-03-26","cited_by_count":199},{"id":"2208.09481","title":"Graph neural networks for materials science and chemistry","created":"2022-08-05","cited_by_count":182},{"id":"2302.02941","title":"On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology","created":"2023-02-06","cited_by_count":166},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113},{"id":"2102.11391","title":"MagNet: A Neural Network for Directed Graphs","created":"2021-02-22","cited_by_count":107},{"id":"2406.06512","title":"Merlin: A Computed Tomography Vision-Language Foundation Model and Dataset","created":"2024-06-10","cited_by_count":102},{"id":"2403.06801","title":"CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging","created":"2024-03-11","cited_by_count":96},{"id":"2301.08210","title":"Everything is Connected: Graph Neural Networks","created":"2023-01-19","cited_by_count":85},{"id":"2002.04752","title":"Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes","created":"2020-02-12","cited_by_count":67},{"id":"2105.13137","title":"Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future","created":"2021-05-27","cited_by_count":67},{"id":"2305.16037","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","created":"2023-05-25","cited_by_count":64},{"id":"2501.09001","title":"Vision Foundation Models for Computed Tomography","created":"2025-01-15","cited_by_count":47},{"id":"2502.20056","title":"Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation","created":"2025-02-27","cited_by_count":42},{"id":"1905.13302","title":"A Survey on Biomedical Image Captioning","created":"2019-05-26","cited_by_count":30},{"id":"2406.01317","title":"The Interpretable and Effective Graph Neural Additive Networks","created":"2024-06-03","cited_by_count":20},{"id":"2102.05692","title":"UAV Localization Using Autoencoded Satellite Images","created":"2021-02-10","cited_by_count":18},{"id":"2309.07400","title":"HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis","created":"2023-09-14","cited_by_count":17},{"id":"2411.15802","title":"Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2","created":"2024-11-24","cited_by_count":13},{"id":"2302.04303","title":"Adapting Pre-trained Vision Transformers from 2D to 3D through Weight Inflation Improves Medical Image Segmentation","created":"2023-02-08","cited_by_count":11},{"id":"2508.05375","title":"CT-GRAPH: Hierarchical Graph Attention Network for Anatomy-Guided CT Report Generation","created":"2025-08-07","cited_by_count":8},{"id":"2509.06617","title":"MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis","created":"2025-09-08","cited_by_count":7},{"id":"2505.17167","title":"CRG Score: A Distribution-Aware Clinical Metric for Radiology Report Generation","created":"2025-05-22","cited_by_count":6},{"id":"2407.17219","title":"Graph Neural Networks: A suitable Alternative to MLPs in Latent 3D Medical Image Classification?","created":"2024-07-24","cited_by_count":4},{"id":"2503.20652","title":"Imitating Radiological Scrolling: A Global-Local Attention Model for 3D Chest CT Volumes Multi-Label Anomaly Classification","created":"2025-03-26","cited_by_count":2},{"id":"2508.01045","title":"Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans","created":"2025-08-01","cited_by_count":2}],"next_cursor":null}