{"list":"other","total":90,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2309.15817","title":"Identifying the Risks of LM Agents with an LM-Emulated Sandbox","created":"2023-09-25","cited_by_count":548},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2207.08051","title":"SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery","created":"2022-07-17","cited_by_count":408},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"1805.06561","title":"DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images","created":"2018-05-17","cited_by_count":277},{"id":"2110.08733","title":"LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation","created":"2021-10-17","cited_by_count":261},{"id":"2103.16607","title":"Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data","created":"2021-03-30","cited_by_count":215},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"id":"2003.07333","title":"RSVQA: Visual Question Answering for Remote Sensing Data","created":"2020-03-16","cited_by_count":203},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2401.16822","title":"EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain","created":"2024-01-30","cited_by_count":184},{"id":"2012.02951","title":"FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding","created":"2020-12-05","cited_by_count":181},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"2312.10032","title":"Osprey: Pixel Understanding with Visual Instruction Tuning","created":"2023-12-15","cited_by_count":159},{"id":"2311.17179","title":"SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery","created":"2023-11-28","cited_by_count":151},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"1911.09296","title":"xBD: A Dataset for Assessing Building Damage from Satellite Imagery","created":"2019-11-21","cited_by_count":139},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"1810.08468","title":"Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks","created":"2018-10-19","cited_by_count":110},{"id":"2302.04476","title":"Towards Geospatial Foundation Models via Continual Pretraining","created":"2023-02-09","cited_by_count":109},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2406.10100","title":"SkySenseGPT: A Fine-Grained Instruction Tuning Dataset and Model for Remote Sensing Vision-Language Understanding","created":"2024-06-14","cited_by_count":104},{"id":"2403.16971","title":"AIOS: LLM Agent Operating System","created":"2024-03-25","cited_by_count":97},{"id":"2305.00729","title":"What Do Self-Supervised Vision Transformers Learn?","created":"2023-05-01","cited_by_count":93},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2203.12560","title":"DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation","created":"2022-03-23","cited_by_count":78},{"id":"2107.09244","title":"S2Looking: A Satellite Side-Looking Dataset for Building Change Detection","created":"2021-07-20","cited_by_count":77},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63},{"id":"2010.00243","title":"MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding","created":"2020-10-01","cited_by_count":59},{"id":"2306.04898","title":"Understanding Masked Autoencoders via Hierarchical Latent Variable Models","created":"2023-06-08","cited_by_count":39},{"id":"2401.09083","title":"Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models","created":"2024-01-17","cited_by_count":32},{"id":"2404.15500","title":"GeoLLM-Engine: A Realistic Environment for Building Geospatial Copilots","created":"2024-04-23","cited_by_count":30},{"id":"2408.06687","title":"Masked Image Modeling: A Survey","created":"2024-08-13","cited_by_count":29},{"id":"2304.05995","title":"APPLeNet: Visual Attention Parameterized Prompt Learning for Few-Shot Remote Sensing Image Generalization using CLIP","created":"2023-04-12","cited_by_count":24},{"id":"2501.06809","title":"RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models","created":"2025-01-12","cited_by_count":22},{"id":"2303.06670","title":"Extending global-local view alignment for self-supervised learning with remote sensing imagery","created":"2023-03-12","cited_by_count":20},{"id":"2507.20776","title":"RingMo-Agent: A Unified Remote Sensing Foundation Model for Multi-Platform and Multi-Modal Reasoning","created":"2025-07-28","cited_by_count":20},{"id":"2409.13366","title":"RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learning","created":"2024-09-20","cited_by_count":15},{"id":"2303.07035","title":"FireRisk: A Remote Sensing Dataset for Fire Risk Assessment with Benchmarks Using Supervised and Self-supervised Learning","created":"2023-03-13","cited_by_count":14},{"id":"2310.04698","title":"Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis","created":"2023-10-07","cited_by_count":14},{"id":"2510.18318","title":"Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning","created":"2025-10-21","cited_by_count":13},{"id":"2406.04111","title":"UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mapping","created":"2024-06-06","cited_by_count":11},{"id":"2410.13384","title":"RescueADI: Adaptive Disaster Interpretation in Remote Sensing Images with Autonomous Agents","created":"2024-10-17","cited_by_count":11},{"id":"2410.17031","title":"GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks","created":"2024-10-22","cited_by_count":11},{"id":"2501.08111","title":"EarthView: A Large Scale Remote Sensing Dataset for Self-Supervision","created":"2025-01-14","cited_by_count":11},{"id":"2504.04319","title":"Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows","created":"2025-04-06","cited_by_count":11},{"id":"2509.20998","title":"CORE: Full-Path Evaluation of LLM Agents Beyond Final State","created":"2025-09-25","cited_by_count":9},{"id":"2508.04719","title":"GeoFlow: Agentic Workflow Automation for Geospatial Tasks","created":"2025-08-05","cited_by_count":8},{"id":"2412.17339","title":"MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models","created":"2024-12-23","cited_by_count":7},{"id":"2503.16326","title":"OmniGeo: Towards a Multimodal Large Language Models for Geospatial Artificial Intelligence","created":"2025-03-20","cited_by_count":7},{"id":"2503.12490","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","created":"2025-03-16","cited_by_count":6},{"id":"2508.05432","title":"Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI","created":"2025-08-07","cited_by_count":6},{"id":"2407.11014","title":"Geode: A Zero-shot Geospatial Question-Answering Agent with Explicit Reasoning and Precise Spatio-Temporal Retrieval","created":"2024-06-26","cited_by_count":5},{"id":"2411.16018","title":"Style-Pro: Style-Guided Prompt Learning for Generalizable Vision-Language Models","created":"2024-11-25","cited_by_count":5},{"id":"2411.16049","title":"ROADS: Robust Prompt-driven Multi-Class Anomaly Detection under Domain Shift","created":"2024-11-25","cited_by_count":5},{"id":"2510.19661","title":"AgentSense: LLMs Empower Generalizable and Explainable Web-Based Participatory Urban Sensing","created":"2025-10-22","cited_by_count":5},{"id":"2505.09936","title":"CartoAgent: a multimodal large language model-powered multi-agent cartographic framework for map style transfer and evaluation","created":"2025-05-15","cited_by_count":4},{"id":"2505.19373","title":"DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models","created":"2025-05-26","cited_by_count":4}],"next_cursor":null}