{"list":"other","total":91,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"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":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"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":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2408.13257","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","created":"2024-08-23","cited_by_count":292},{"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":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"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":"1712.07835","title":"Exploring Models and Data for Remote Sensing Image Caption Generation","created":"2017-12-21","cited_by_count":197},{"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":"2311.00566","title":"CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders","created":"2023-11-01","cited_by_count":169},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"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":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123},{"id":"2406.12384","title":"VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding","created":"2024-06-18","cited_by_count":121},{"id":"2401.09712","title":"SkyEyeGPT: Unifying Remote Sensing Vision-Language Tasks via Instruction Tuning with Large Language Model","created":"2024-01-18","cited_by_count":113},{"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":"1706.03424","title":"PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval","created":"2017-06-11","cited_by_count":97},{"id":"2403.20213","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","created":"2024-03-29","cited_by_count":86},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85},{"id":"2210.10732","title":"OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping","created":"2022-10-19","cited_by_count":82},{"id":"2107.09244","title":"S2Looking: A Satellite Side-Looking Dataset for Building Change Detection","created":"2021-07-20","cited_by_count":77},{"id":"2312.12470","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","created":"2023-12-19","cited_by_count":76},{"id":"2406.04334","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","created":"2024-06-06","cited_by_count":75},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63},{"id":"2006.10027","title":"Deep Learning Meets SAR","created":"2020-06-17","cited_by_count":60},{"id":"2306.08625","title":"RRSIS: Referring Remote Sensing Image Segmentation","created":"2023-06-14","cited_by_count":59},{"id":"2312.12222","title":"EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering","created":"2023-12-19","cited_by_count":52},{"id":"2503.23771","title":"XLRS-Bench: Could Your Multimodal LLMs Understand Extremely Large Ultra-High-Resolution Remote Sensing Imagery?","created":"2025-03-31","cited_by_count":51},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48},{"id":"2411.11904","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","created":"2024-11-16","cited_by_count":47},{"id":"2505.21375","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","created":"2025-05-27","cited_by_count":44},{"id":"2311.12751","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","created":"2023-11-21","cited_by_count":42},{"id":"2202.12361","title":"RescueNet: A High Resolution UAV Semantic Segmentation Benchmark Dataset for Natural Disaster Damage Assessment","created":"2022-02-24","cited_by_count":40},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39},{"id":"2505.21089","title":"DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response","created":"2025-05-27","cited_by_count":36},{"id":"2204.03245","title":"HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection","created":"2022-04-07","cited_by_count":34},{"id":"2011.03247","title":"Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery","created":"2020-11-06","cited_by_count":33},{"id":"2407.13596","title":"EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing","created":"2024-07-18","cited_by_count":29},{"id":"2408.17267","title":"UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios","created":"2024-08-30","cited_by_count":28},{"id":"2103.08259","title":"The QXS-SAROPT Dataset for Deep Learning in SAR-Optical Data Fusion","created":"2021-03-15","cited_by_count":27},{"id":"2410.08613","title":"Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation","created":"2024-10-11","cited_by_count":26},{"id":"2402.11325","title":"ChatEarthNet: A Global-Scale Image-Text Dataset Empowering Vision-Language Geo-Foundation Models","created":"2024-02-17","cited_by_count":24},{"id":"2409.08582","title":"ChangeChat: An Interactive Model for Remote Sensing Change Analysis via Multimodal Instruction Tuning","created":"2024-09-13","cited_by_count":23},{"id":"2511.12267","title":"ZoomEarth: Active Perception for Ultra-High-Resolution Geospatial Vision-Language Tasks","created":"2025-11-15","cited_by_count":21},{"id":"2001.11394","title":"ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos","created":"2020-01-30","cited_by_count":18},{"id":"2505.21076","title":"DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding","created":"2025-05-27","cited_by_count":18},{"id":"2506.01667","title":"EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM","created":"2025-06-02","cited_by_count":18},{"id":"2508.07918","title":"RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering","created":"2025-08-11","cited_by_count":17},{"id":"2504.03254","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","created":"2025-04-04","cited_by_count":16},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14},{"id":"2410.19552","title":"GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing","created":"2024-10-25","cited_by_count":13},{"id":"2506.03583","title":"Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation","created":"2025-06-04","cited_by_count":12},{"id":"2507.14449","title":"IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark","created":"2025-07-19","cited_by_count":12},{"id":"2208.10004","title":"A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extraction","created":"2022-08-22","cited_by_count":10},{"id":"2406.12479","title":"RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding","created":"2024-06-18","cited_by_count":10},{"id":"2511.23332","title":"UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes","created":"2025-11-28","cited_by_count":10},{"id":"2502.01002","title":"Multi-Resolution SAR and Optical Remote Sensing Image Registration Methods: A Review, Datasets, and Future Perspectives","created":"2025-02-03","cited_by_count":9},{"id":"2501.10075","title":"Robust Change Captioning in Remote Sensing: SECOND-CC Dataset and MModalCC Framework","created":"2025-01-17","cited_by_count":8},{"id":"2507.16716","title":"Enhancing Remote Sensing Vision-Language Models Through MLLM and LLM-Based High-Quality Image-Text Dataset Generation","created":"2025-07-22","cited_by_count":8},{"id":"2411.15770","title":"Text-Guided Coarse-to-Fine Fusion Network for Robust Remote Sensing Visual Question Answering","created":"2024-11-24","cited_by_count":5},{"id":"2503.23106","title":"A large-scale image-text dataset benchmark for farmland segmentation","created":"2025-03-29","cited_by_count":5},{"id":"2509.25654","title":"DescribeEarth: Describe Anything for Remote Sensing Images","created":"2025-09-30","cited_by_count":5},{"id":"2508.03127","title":"Landsat30-AU: A Vision-Language Dataset for Australian Landsat Imagery","created":"2025-08-05","cited_by_count":4},{"id":"2601.00998","title":"DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models","created":"2026-01-02","cited_by_count":4},{"id":"2507.18743","title":"SAR-TEXT: A Large-Scale SAR Image-Text Dataset Built with SAR-Narrator and A Progressive Learning Strategy for Downstream Tasks","created":"2025-07-24","cited_by_count":3},{"id":"2506.18862","title":"TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models","created":"2025-06-23","cited_by_count":2}],"next_cursor":null}