{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2307.15266","title":"RSGPT: A Remote Sensing Vision Language Model and Benchmark","created":"2023-07-28","cited_by_count":207},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"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":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","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":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"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":"2008.01187","title":"PhraseCut: Language-based Image Segmentation in the Wild","created":"2020-08-03","cited_by_count":116},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2403.14598","title":"PSALM: Pixelwise SegmentAtion with Large Multi-Modal Model","created":"2024-03-21","cited_by_count":101},{"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":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77},{"id":"2403.02330","title":"RegionGPT: Towards Region Understanding Vision Language Model","created":"2024-03-04","cited_by_count":71},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"id":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68},{"id":"2410.09855","title":"Text4Seg: Reimagining Image Segmentation as Text Generation","created":"2024-10-13","cited_by_count":61},{"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":"2404.08506","title":"LaSagnA: Language-based Segmentation Assistant for Complex Queries","created":"2024-04-12","cited_by_count":55},{"id":"2408.03464","title":"Vision Foundation Models in Remote Sensing: A Survey","created":"2024-08-06","cited_by_count":54},{"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":"2411.19325","title":"GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks","created":"2024-11-28","cited_by_count":51},{"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":"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":"2411.17606","title":"HyperSeg: Towards Universal Visual Segmentation with Large Language Model","created":"2024-11-26","cited_by_count":33},{"id":"2412.14006","title":"InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models","created":"2024-12-18","cited_by_count":31},{"id":"2508.04655","title":"X-SAM: From Segment Anything to Any Segmentation","created":"2025-08-06","cited_by_count":30},{"id":"2412.05679","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","created":"2024-12-07","cited_by_count":29},{"id":"2503.11070","title":"Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)","created":"2025-03-14","cited_by_count":28},{"id":"2503.13881","title":"MMR: A Large-scale Benchmark Dataset for Multi-target and Multi-granularity Reasoning Segmentation","created":"2025-03-18","cited_by_count":28},{"id":"2507.19280","title":"RemoteReasoner: Towards Unifying Geospatial Reasoning Workflow","created":"2025-07-25","cited_by_count":28},{"id":"2410.08613","title":"Cross-Modal Bidirectional Interaction Model for Referring Remote Sensing Image Segmentation","created":"2024-10-11","cited_by_count":26},{"id":"2411.09301","title":"LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation","created":"2024-11-14","cited_by_count":25},{"id":"2403.06199","title":"Mipha: A Comprehensive Overhaul of Multimodal Assistant with Small Language Models","created":"2024-03-10","cited_by_count":24},{"id":"2409.13637","title":"Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image Segmentation","created":"2024-09-20","cited_by_count":24},{"id":"2411.18145","title":"CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models","created":"2024-11-27","cited_by_count":22},{"id":"2501.12931","title":"DynamicEarth: How Far are We from Open-Vocabulary Change Detection?","created":"2025-01-22","cited_by_count":21},{"id":"2509.21976","title":"Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning","created":"2025-09-26","cited_by_count":20},{"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":"2505.02829","title":"LISAT: Language-Instructed Segmentation Assistant for Satellite Imagery","created":"2025-05-05","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":"2503.10596","title":"GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding","created":"2025-03-13","cited_by_count":11},{"id":"2509.06321","title":"Text4Seg++: Advancing Image Segmentation via Generative Language Modeling","created":"2025-09-08","cited_by_count":9},{"id":"2508.18067","title":"Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images","created":"2025-08-25","cited_by_count":8},{"id":"2507.05887","title":"GeoMag: A Vision-Language Model for Pixel-level Fine-Grained Remote Sensing Image Parsing","created":"2025-07-08","cited_by_count":5},{"id":"2505.13788","title":"Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels","created":"2025-05-20","cited_by_count":4},{"id":"2507.16213","title":"Advancing Visual Large Language Model for Multi-granular Versatile Perception","created":"2025-07-22","cited_by_count":3}],"next_cursor":null}