{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"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":"2310.09478","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","created":"2023-10-14","cited_by_count":625},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"2308.01390","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","created":"2023-08-02","cited_by_count":565},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1710.05006","title":"Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)","created":"2017-10-13","cited_by_count":549},{"id":"2107.02314","title":"The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification","created":"2021-07-05","cited_by_count":518},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"2307.15189","title":"Med-Flamingo: a Multimodal Medical Few-shot Learner","created":"2023-07-27","cited_by_count":392},{"id":"1902.09063","title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","created":"2019-02-25","cited_by_count":373},{"id":"2206.08023","title":"AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation","created":"2022-06-16","cited_by_count":351},{"id":"2306.00968","title":"GRES: Generalized Referring Expression Segmentation","created":"2023-06-01","cited_by_count":254},{"id":"2010.14808","title":"AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?","created":"2020-10-28","cited_by_count":224},{"id":"1612.08012","title":"Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge","created":"2016-12-23","cited_by_count":201},{"id":"1605.01397","title":"Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)","created":"2016-05-04","cited_by_count":198},{"id":"1912.01054","title":"The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge","created":"2019-12-02","cited_by_count":190},{"id":"2308.02463","title":"Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data","created":"2023-08-04","cited_by_count":179},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2312.10103","title":"GSVA: Generalized Segmentation via Multimodal Large Language Models","created":"2023-12-15","cited_by_count":154},{"id":"2007.02035","title":"Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains","created":"2020-07-04","cited_by_count":124},{"id":"2308.16184","title":"SAM-Med2D","created":"2023-08-30","cited_by_count":124},{"id":"2001.09193","title":"VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images","created":"2020-01-24","cited_by_count":111},{"id":"2206.06694","title":"ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset","created":"2022-06-14","cited_by_count":106},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2403.20271","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","created":"2024-03-29","cited_by_count":101},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"2402.19474","title":"The All-Seeing Project V2: Towards General Relation Comprehension of the Open World","created":"2024-02-29","cited_by_count":90},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80},{"id":"1812.06587","title":"Grounded Video Description","created":"2018-12-17","cited_by_count":78},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70},{"id":"2404.08506","title":"LaSagnA: Language-based Segmentation Assistant for Complex Queries","created":"2024-04-12","cited_by_count":55},{"id":"2105.14711","title":"CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography","created":"2021-05-31","cited_by_count":46},{"id":"2202.06511","title":"GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges","created":"2022-02-14","cited_by_count":46},{"id":"2012.08721","title":"Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models","created":"2020-12-16","cited_by_count":45},{"id":"2303.01710","title":"BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability","created":"2023-03-03","cited_by_count":42},{"id":"1911.08434","title":"LNDb: A Lung Nodule Database on Computed Tomography","created":"2019-11-19","cited_by_count":28},{"id":"2304.03708","title":"Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge","created":"2023-04-07","cited_by_count":28},{"id":"2401.13307","title":"ChatterBox: Multi-round Multimodal Referring and Grounding","created":"2024-01-24","cited_by_count":24},{"id":"2104.13395","title":"ACDC: The Adverse Conditions Dataset with Correspondences for Robust Semantic Driving Scene Perception","created":"2021-04-27","cited_by_count":21},{"id":"2304.10691","title":"SkinGPT-4: An Interactive Dermatology Diagnostic System with Visual Large Language Model","created":"2023-04-21","cited_by_count":18},{"id":"2306.10765","title":"Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost","created":"2023-06-19","cited_by_count":12},{"id":"2303.05745","title":"Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway Segmentation","created":"2023-03-10","cited_by_count":9},{"id":"2209.01212","title":"AutoPET Challenge 2022: Automatic Segmentation of Whole-body Tumor Lesion Based on Deep Learning and FDG PET/CT","created":"2022-08-31","cited_by_count":5},{"id":"2209.10648","title":"Automated segmentation of intracranial hemorrhages from 3D CT","created":"2022-09-21","cited_by_count":2}],"next_cursor":null}