{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2301.08243","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","created":"2023-01-19","cited_by_count":1039},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2202.03555","title":"data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language","created":"2022-02-07","cited_by_count":727},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2102.09508","title":"Domain Adaptation for Medical Image Analysis: A Survey","created":"2021-02-18","cited_by_count":352},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"2101.05224","title":"Big Self-Supervised Models Advance Medical Image Classification","created":"2021-01-13","cited_by_count":320},{"id":"2006.10511","title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","created":"2020-06-18","cited_by_count":309},{"id":"2012.15029","title":"VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations","created":"2020-12-30","cited_by_count":239},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132},{"id":"2111.12525","title":"Causality-inspired Single-source Domain Generalization for Medical Image Segmentation","created":"2021-11-24","cited_by_count":119},{"id":"2212.07525","title":"Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language","created":"2022-12-14","cited_by_count":110},{"id":"2403.00504","title":"Learning and Leveraging World Models in Visual Representation Learning","created":"2024-03-01","cited_by_count":72},{"id":"2007.07423","title":"Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations","created":"2020-07-15","cited_by_count":69},{"id":"2203.05573","title":"Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation","created":"2022-03-10","cited_by_count":69},{"id":"2102.10680","title":"Transferable Visual Words: Exploiting the Semantics of Anatomical Patterns for Self-supervised Learning","created":"2021-02-21","cited_by_count":68},{"id":"2012.02383","title":"SAM: Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images","created":"2020-12-04","cited_by_count":67},{"id":"2111.00899","title":"Equivariant Contrastive Learning","created":"2021-10-28","cited_by_count":66},{"id":"2112.09164","title":"High Fidelity Visualization of What Your Self-Supervised Representation Knows About","created":"2021-12-16","cited_by_count":66},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65},{"id":"2306.11925","title":"LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching","created":"2023-06-20","cited_by_count":60},{"id":"2204.10437","title":"DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis","created":"2022-04-21","cited_by_count":48},{"id":"2211.09703","title":"EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones","created":"2022-11-17","cited_by_count":43},{"id":"2403.06726","title":"Probabilistic Contrastive Learning for Long-Tailed Visual Recognition","created":"2024-03-11","cited_by_count":42},{"id":"2007.08826","title":"Revisiting Rubik's Cube: Self-supervised Learning with Volume-wise Transformation for 3D Medical Image Segmentation","created":"2020-07-17","cited_by_count":40},{"id":"2306.09579","title":"MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification","created":"2023-06-16","cited_by_count":38},{"id":"2211.01244","title":"EquiMod: An Equivariance Module to Improve Self-Supervised Learning","created":"2022-11-02","cited_by_count":21},{"id":"2404.15672","title":"Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision","created":"2024-04-24","cited_by_count":13},{"id":"2312.00335","title":"Learning Anatomically Consistent Embedding for Chest Radiography","created":"2023-12-01","cited_by_count":8},{"id":"2302.05098","title":"Confidence-based Reliable Learning under Dual Noises","created":"2023-02-10","cited_by_count":6}],"next_cursor":null}