{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"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":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"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":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"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":"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":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"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":"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":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138},{"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":"1807.05713","title":"Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models","created":"2018-07-16","cited_by_count":119},{"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":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"id":"2412.15190","title":"EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues","created":"2024-12-19","cited_by_count":85},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80},{"id":"2309.02773","title":"Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter","created":"2023-09-06","cited_by_count":76},{"id":"2312.12470","title":"Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation","created":"2023-12-19","cited_by_count":76},{"id":"2406.11519","title":"HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Model","created":"2024-06-17","cited_by_count":73},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2306.08625","title":"RRSIS: Referring Remote Sensing Image Segmentation","created":"2023-06-14","cited_by_count":59},{"id":"2501.13925","title":"GeoPixel: Pixel Grounding Large Multimodal Model in Remote Sensing","created":"2025-01-23","cited_by_count":57},{"id":"2307.00764","title":"Hierarchical Open-vocabulary Universal Image Segmentation","created":"2023-07-03","cited_by_count":54},{"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":"2408.09110","title":"Locate Anything on Earth: Advancing Open-Vocabulary Object Detection for Remote Sensing Community","created":"2024-08-17","cited_by_count":50},{"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":"2504.09644","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","created":"2025-04-13","cited_by_count":42},{"id":"2310.13336","title":"FLAIR: a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery","created":"2023-10-20","cited_by_count":41},{"id":"2505.18022","title":"RemoteSAM: Towards Segment Anything for Earth Observation","created":"2025-05-23","cited_by_count":39},{"id":"2209.00727","title":"Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery","created":"2022-09-01","cited_by_count":31},{"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":"2010.07830","title":"Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study","created":"2020-10-15","cited_by_count":28},{"id":"2507.19280","title":"RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow","created":"2025-07-25","cited_by_count":28},{"id":"2410.22629","title":"CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation","created":"2024-10-30","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":"2007.06102","title":"SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes","created":"2020-07-12","cited_by_count":22},{"id":"2501.06809","title":"RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models","created":"2025-01-12","cited_by_count":22},{"id":"2312.15043","title":"GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection","created":"2023-12-22","cited_by_count":20},{"id":"2510.23116","title":"Residual Diffusion Bridge Model for Image Restoration","created":"2025-10-27","cited_by_count":15},{"id":"2407.05352","title":"Exploring Phrase-Level Grounding with Text-to-Image Diffusion Model","created":"2024-07-07","cited_by_count":13},{"id":"2505.02829","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","created":"2025-05-05","cited_by_count":13},{"id":"2406.08020","title":"Generalizable Disaster Damage Assessment via Change Detection with Vision Foundation Model","created":"2024-06-12","cited_by_count":10},{"id":"2509.18711","title":"RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images","created":"2025-09-23","cited_by_count":8},{"id":"2310.14374","title":"OV-VG: A Benchmark for Open-Vocabulary Visual Grounding","created":"2023-10-22","cited_by_count":7},{"id":"2409.17453","title":"AgMTR: Agent Mining Transformer for Few-shot Segmentation in Remote Sensing","created":"2024-09-26","cited_by_count":6},{"id":"2504.21487","title":"DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration","created":"2025-04-30","cited_by_count":5},{"id":"2505.08723","title":"TiMo: Spatiotemporal Foundation Model for Satellite Image Time Series","created":"2025-05-13","cited_by_count":5},{"id":"2507.16251","title":"HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery","created":"2025-07-22","cited_by_count":4},{"id":"2508.05202","title":"SPEX: A Vision-Language Model for Land Cover Extraction on Spectral Remote Sensing Images","created":"2025-08-07","cited_by_count":3},{"id":"2508.12409","title":"S5: Scalable Semi-Supervised Semantic Segmentation in Remote Sensing","created":"2025-08-17","cited_by_count":3},{"id":"2109.00918","title":"Multi-task learning from fixed-wing UAV images for 2D/3D city modeling","created":"2021-08-25","cited_by_count":2}],"next_cursor":null}