{"list":"other","total":66,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"1905.05055","title":"Object Detection in 20 Years: A Survey","created":"2019-05-13","cited_by_count":531},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"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":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2306.16269","title":"RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model","created":"2023-06-28","cited_by_count":181},{"id":"2111.01998","title":"OpenPrompt: An Open-source Framework for Prompt-learning","created":"2021-11-03","cited_by_count":148},{"id":"2010.00514","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","created":"2020-10-01","cited_by_count":131},{"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":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"2403.19654","title":"RSMamba: Remote Sensing Image Classification with State Space Model","created":"2024-03-28","cited_by_count":95},{"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":"2308.13853","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","created":"2023-08-26","cited_by_count":68},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"2406.20076","title":"EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model","created":"2024-06-28","cited_by_count":65},{"id":"2403.19646","title":"Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis","created":"2024-03-28","cited_by_count":63},{"id":"2307.11545","title":"Bridging Vision and Language Encoders: Parameter-Efficient Tuning for Referring Image Segmentation","created":"2023-07-21","cited_by_count":61},{"id":"2306.08625","title":"RRSIS: Referring Remote Sensing Image Segmentation","created":"2023-06-14","cited_by_count":59},{"id":"2209.09554","title":"Towards Robust Referring Image Segmentation","created":"2022-09-20","cited_by_count":49},{"id":"2406.04207","title":"CDMamba: Incorporating Local Clues into Mamba for Remote Sensing Image Binary Change Detection","created":"2024-06-06","cited_by_count":48},{"id":"2501.00895","title":"Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model","created":"2025-01-01","cited_by_count":48},{"id":"2301.09506","title":"OvarNet: Towards Open-vocabulary Object Attribute Recognition","created":"2023-01-23","cited_by_count":43},{"id":"2504.09644","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","created":"2025-04-13","cited_by_count":42},{"id":"2107.05276","title":"Geographical Knowledge-driven Representation Learning for Remote Sensing Images","created":"2021-07-12","cited_by_count":37},{"id":"2402.01188","title":"Segment Any Change","created":"2024-02-02","cited_by_count":35},{"id":"2404.18895","title":"RSCaMa: Remote Sensing Image Change Captioning with State Space Model","created":"2024-04-29","cited_by_count":35},{"id":"2312.16202","title":"Time Travelling Pixels: Bitemporal Features Integration with Foundation Model for Remote Sensing Image Change Detection","created":"2023-12-23","cited_by_count":27},{"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":"2409.13637","title":"Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image Segmentation","created":"2024-09-20","cited_by_count":24},{"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":"2408.07539","title":"Cross-aware Early Fusion with Stage-divided Vision and Language Transformer Encoders for Referring Image Segmentation","created":"2024-08-14","cited_by_count":21},{"id":"2302.08046","title":"Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space","created":"2023-02-16","cited_by_count":18},{"id":"2504.03166","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","created":"2025-04-04","cited_by_count":16},{"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":"2501.00851","title":"Scale-wise Bidirectional Alignment Network for Referring Remote Sensing Image Segmentation","created":"2025-01-01","cited_by_count":11},{"id":"2502.08486","title":"Referring Remote Sensing Image Segmentation via Bidirectional Alignment Guided Joint Prediction","created":"2025-02-12","cited_by_count":9},{"id":"2503.23456","title":"CADFormer: Fine-Grained Cross-modal Alignment and Decoding Transformer for Referring Remote Sensing Image Segmentation","created":"2025-03-30","cited_by_count":9},{"id":"2506.18946","title":"DiffRIS: Enhancing Referring Remote Sensing Image Segmentation with Pre-trained Text-to-Image Diffusion Models","created":"2025-06-23","cited_by_count":6},{"id":"2502.16680","title":"AeroReformer: Aerial Referring Transformer for UAV-based Referring Image Segmentation","created":"2025-02-23","cited_by_count":5},{"id":"2503.11183","title":"Multimodal-Aware Fusion Network for Referring Remote Sensing Image Segmentation","created":"2025-03-14","cited_by_count":5},{"id":"2503.07266","title":"RS2-SAM2: Customized SAM2 for Referring Remote Sensing Image Segmentation","created":"2025-03-10","cited_by_count":4},{"id":"2505.23010","title":"SeG-SR: Integrating Semantic Knowledge into Remote Sensing Image Super-Resolution via Vision-Language Model","created":"2025-05-29","cited_by_count":3},{"id":"2202.13336","title":"Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast","created":"2022-02-27","cited_by_count":2},{"id":"2506.10503","title":"Semantic Localization Guiding Segment Anything Model For Reference Remote Sensing Image Segmentation","created":"2025-06-12","cited_by_count":2}],"next_cursor":null}