{"list":"other","total":69,"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":"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":"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"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":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"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":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"1809.07041","title":"Exploring Visual Relationship for Image Captioning","created":"2018-09-19","cited_by_count":215},{"id":"2003.14080","title":"X-Linear Attention Networks for Image Captioning","created":"2020-03-31","cited_by_count":198},{"id":"1712.07835","title":"Exploring Models and Data for Remote Sensing Image Caption Generation","created":"2017-12-21","cited_by_count":197},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2109.08937","title":"UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery","created":"2021-09-18","cited_by_count":167},{"id":"2402.14289","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","created":"2024-02-22","cited_by_count":164},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"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":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"1904.00560","title":"Scene Graph Generation with External Knowledge and Image Reconstruction","created":"2019-04-01","cited_by_count":102},{"id":"1704.03114","title":"Detecting Visual Relationships with Deep Relational Networks","created":"2017-04-11","cited_by_count":97},{"id":"2504.16072","title":"Describe Anything: Detailed Localized Image and Video Captioning","created":"2025-04-22","cited_by_count":84},{"id":"1811.10787","title":"Unsupervised Image Captioning","created":"2018-11-27","cited_by_count":79},{"id":"2402.01444","title":"Mission Critical -- Satellite Data is a Distinct Modality in Machine Learning","created":"2024-02-02","cited_by_count":77},{"id":"1611.01646","title":"Boosting Image Captioning with Attributes","created":"2016-11-05","cited_by_count":76},{"id":"2410.06234","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","created":"2024-10-08","cited_by_count":70},{"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":"2003.01473","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","created":"2020-03-03","cited_by_count":51},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51},{"id":"1611.08002","title":"Semantic Compositional Networks for Visual Captioning","created":"2016-11-23","cited_by_count":50},{"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":"2201.12944","title":"Deep Learning Approaches on Image Captioning: A Review","created":"2022-01-31","cited_by_count":43},{"id":"2304.01091","title":"Changes to Captions: An Attentive Network for Remote Sensing Change Captioning","created":"2023-04-03","cited_by_count":41},{"id":"1506.01144","title":"What value do explicit high level concepts have in vision to language problems?","created":"2015-06-03","cited_by_count":31},{"id":"2305.14095","title":"S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions","created":"2023-05-23","cited_by_count":30},{"id":"2310.16069","title":"CPSeg: Finer-grained Image Semantic Segmentation via Chain-of-Thought Language Prompting","created":"2023-10-24","cited_by_count":28},{"id":"1709.03376","title":"Stack-Captioning: Coarse-to-Fine Learning for Image Captioning","created":"2017-09-11","cited_by_count":27},{"id":"1803.05526","title":"Unpaired Image Captioning by Language Pivoting","created":"2018-03-14","cited_by_count":27},{"id":"1803.09189","title":"Scene Graph Parsing as Dependency Parsing","created":"2018-03-25","cited_by_count":21},{"id":"1805.07112","title":"Improving Image Captioning with Conditional Generative Adversarial Nets","created":"2018-05-18","cited_by_count":14},{"id":"2301.04283","title":"MGeo: Multi-Modal Geographic Pre-Training Method","created":"2023-01-11","cited_by_count":12},{"id":"2505.05804","title":"Describe Anything in Medical Images","created":"2025-05-09","cited_by_count":10},{"id":"2406.01906","title":"ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization","created":"2024-06-04","cited_by_count":6},{"id":"2507.12441","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","created":"2025-07-16","cited_by_count":5},{"id":"2506.05399","title":"Attention-based transformer models for image captioning across languages: An in-depth survey and evaluation","created":"2025-06-03","cited_by_count":1}],"next_cursor":null}