{"list":"other","total":71,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"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":"1603.07396","title":"A Diagram Is Worth A Dozen Images","created":"2016-03-24","cited_by_count":804},{"id":"1902.03368","title":"Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2019-02-09","cited_by_count":669},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"1811.08839","title":"fastMRI: An Open Dataset and Benchmarks for Accelerated MRI","created":"2018-11-21","cited_by_count":470},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"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":"1912.03098","title":"Connecting Vision and Language with Localized Narratives","created":"2019-12-06","cited_by_count":226},{"id":"2303.07240","title":"PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical Documents","created":"2023-03-13","cited_by_count":212},{"id":"2403.17834","title":"Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","created":"2024-03-26","cited_by_count":199},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194},{"id":"2104.09957","title":"Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset","created":"2021-04-20","cited_by_count":185},{"id":"2008.07360","title":"A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context","created":"2020-08-07","cited_by_count":146},{"id":"2111.08006","title":"Disparities in Dermatology AI: Assessments Using Diverse Clinical Images","created":"2021-11-15","cited_by_count":134},{"id":"1808.04277","title":"BACH: Grand Challenge on Breast Cancer Histology Images","created":"2018-08-13","cited_by_count":131},{"id":"2012.12453","title":"CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80","created":"2020-12-23","cited_by_count":106},{"id":"1912.12142","title":"Lung and Colon Cancer Histopathological Image Dataset (LC25000)","created":"2019-12-16","cited_by_count":89},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86},{"id":"2112.13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","created":"2021-12-27","cited_by_count":85},{"id":"2203.11205","title":"VinDr-Mammo: A large-scale benchmark dataset for computer-aided diagnosis in full-field digital mammography","created":"2022-03-20","cited_by_count":84},{"id":"2408.02900","title":"MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine","created":"2024-08-06","cited_by_count":81},{"id":"1610.02055","title":"Places: An Image Database for Deep Scene Understanding","created":"2016-10-06","cited_by_count":76},{"id":"2010.06000","title":"MedICaT: A Dataset of Medical Images, Captions, and Textual References","created":"2020-10-12","cited_by_count":71},{"id":"2101.12355","title":"A Petri Dish for Histopathology Image Analysis","created":"2021-01-29","cited_by_count":64},{"id":"2103.05121","title":"Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles","created":"2021-03-08","cited_by_count":58},{"id":"2405.10004","title":"ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset","created":"2024-05-16","cited_by_count":54},{"id":"2312.07381","title":"ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image","created":"2023-12-12","cited_by_count":48},{"id":"1711.04322","title":"11K Hands: Gender recognition and biometric identification using a large dataset of hand images","created":"2017-11-12","cited_by_count":46},{"id":"2011.03775","title":"Text-to-Image Generation Grounded by Fine-Grained User Attention","created":"2020-11-07","cited_by_count":36},{"id":"2006.09158","title":"G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection","created":"2020-05-28","cited_by_count":31},{"id":"2411.12814","title":"Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline","created":"2024-11-19","cited_by_count":30},{"id":"2312.08255","title":"OCTDL: Optical Coherence Tomography Dataset for Image-Based Deep Learning Methods","created":"2023-12-13","cited_by_count":28},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27},{"id":"2008.10134","title":"m2caiSeg: Semantic Segmentation of Laparoscopic Images using Convolutional Neural Networks","created":"2020-08-23","cited_by_count":26},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24},{"id":"2005.02134","title":"IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition","created":"2020-04-20","cited_by_count":22},{"id":"2307.08140","title":"GastroVision: A Multi-class Endoscopy Image Dataset for Computer Aided Gastrointestinal Disease Detection","created":"2023-07-16","cited_by_count":20},{"id":"2207.06799","title":"MMOTU: A Multi-Modality Ovarian Tumor Ultrasound Image Dataset for Unsupervised Cross-Domain Semantic Segmentation","created":"2022-07-14","cited_by_count":15},{"id":"2409.06644","title":"EyeCLIP: A visual-language foundation model for multi-modal ophthalmic image analysis","created":"2024-09-10","cited_by_count":15},{"id":"2105.05964","title":"Connecting What to Say With Where to Look by Modeling Human Attention Traces","created":"2021-05-12","cited_by_count":13},{"id":"2307.10698","title":"Reverse Knowledge Distillation: Training a Large Model using a Small One for Retinal Image Matching on Limited Data","created":"2023-07-20","cited_by_count":13},{"id":"2303.08252","title":"Hyperspectral Image Segmentation: A Preliminary Study on the Oral and Dental Spectral Image Database (ODSI-DB)","created":"2023-03-14","cited_by_count":10},{"id":"2106.05923","title":"FetReg: Placental Vessel Segmentation and Registration in Fetoscopy Challenge Dataset","created":"2021-06-10","cited_by_count":9},{"id":"2404.15946","title":"Mammo-CLIP: Leveraging Contrastive Language-Image Pre-training (CLIP) for Enhanced Breast Cancer Diagnosis with Multi-view Mammography","created":"2024-04-24","cited_by_count":9},{"id":"1604.07939","title":"Large-Scale Query-by-Image Video Retrieval Using Bloom Filters","created":"2016-04-27","cited_by_count":6},{"id":"1905.10576","title":"Efficient Object Annotation via Speaking and Pointing","created":"2019-05-25","cited_by_count":6},{"id":"2001.06823","title":"SlideImages: A Dataset for Educational Image Classification","created":"2020-01-19","cited_by_count":5},{"id":"2101.04281","title":"Temporally Guided Articulated Hand Pose Tracking in Surgical Videos","created":"2021-01-12","cited_by_count":2}],"next_cursor":null}