{"list":"other","total":73,"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":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"1905.07129","title":"ERNIE: Enhanced Language Representation with Informative Entities","created":"2019-05-17","cited_by_count":528},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2303.05511","title":"Scaling up GANs for Text-to-Image Synthesis","created":"2023-03-09","cited_by_count":492},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1608.05167","title":"AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification","created":"2016-08-18","cited_by_count":347},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2201.08860","title":"GreaseLM: Graph REASoning Enhanced Language Models for Question Answering","created":"2022-01-21","cited_by_count":171},{"id":"2210.09338","title":"Deep Bidirectional Language-Knowledge Graph Pretraining","created":"2022-10-17","cited_by_count":156},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"2010.04389","title":"A Survey of Knowledge-Enhanced Text Generation","created":"2020-10-09","cited_by_count":120},{"id":"1611.00020","title":"Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision","created":"2016-10-31","cited_by_count":103},{"id":"2003.00824","title":"Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells","created":"2020-02-16","cited_by_count":90},{"id":"2010.08168","title":"A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery","created":"2020-10-16","cited_by_count":88},{"id":"2012.02825","title":"A Survey on Deep Learning for Human Mobility","created":"2020-12-04","cited_by_count":88},{"id":"1804.11238","title":"Privacy Preserving Machine Learning: Threats and Solutions","created":"2018-03-27","cited_by_count":79},{"id":"2010.06988","title":"Using satellite imagery to understand and promote sustainable development","created":"2020-09-23","cited_by_count":71},{"id":"2012.00489","title":"Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information","created":"2020-12-01","cited_by_count":58},{"id":"2006.10521","title":"LSTM-TrajGAN: A Deep Learning Approach to Trajectory Privacy Protection","created":"2020-06-14","cited_by_count":57},{"id":"2111.04006","title":"A Review of Location Encoding for GeoAI: Methods and Applications","created":"2021-11-07","cited_by_count":54},{"id":"1901.04713","title":"Global-to-local Memory Pointer Networks for Task-Oriented Dialogue","created":"2019-01-15","cited_by_count":47},{"id":"2007.14189","title":"TrajGAIL: Generating Urban Vehicle Trajectories using Generative Adversarial Imitation Learning","created":"2020-07-28","cited_by_count":47},{"id":"2003.11547","title":"A Survey on Trajectory Data Management, Analytics, and Learning","created":"2020-03-25","cited_by_count":41},{"id":"1910.08435","title":"Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs","created":"2019-10-18","cited_by_count":38},{"id":"2105.09392","title":"Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directions","created":"2021-05-19","cited_by_count":24},{"id":"2004.14171","title":"SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting","created":"2020-04-25","cited_by_count":23},{"id":"2209.15458","title":"Towards General-Purpose Representation Learning of Polygonal Geometries","created":"2022-09-29","cited_by_count":22},{"id":"2106.11485","title":"Spatial-Temporal Super-Resolution of Satellite Imagery via Conditional Pixel Synthesis","created":"2021-06-22","cited_by_count":20},{"id":"2007.04524","title":"Enhancing spatial and textual analysis with EUPEG: an extensible and unified platform for evaluating geoparsers","created":"2020-07-09","cited_by_count":9},{"id":"1910.00084","title":"Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs","created":"2019-09-30","cited_by_count":8},{"id":"2105.09908","title":"Classification of Urban Morphology with Deep Learning: Application on Urban Vitality","created":"2021-05-07","cited_by_count":8},{"id":"2103.02155","title":"Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases","created":"2021-03-03","cited_by_count":7},{"id":"2009.12914","title":"How do people describe locations during a natural disaster: an analysis of tweets from Hurricane Harvey","created":"2020-09-27","cited_by_count":6},{"id":"2304.04893","title":"EVKG: An Interlinked and Interoperable Electric Vehicle Knowledge Graph for Smart Transportation System","created":"2023-04-10","cited_by_count":6},{"id":"1809.05636","title":"Geo-Text Data and Data-Driven Geospatial Semantics","created":"2018-09-15","cited_by_count":4},{"id":"1812.03625","title":"A context-based geoprocessing framework for optimizing meetup location of multiple moving objects along road networks","created":"2018-12-10","cited_by_count":1},{"id":"2006.08661","title":"Predicting Livelihood Indicators from Community-Generated Street-Level Imagery","created":"2020-06-15","cited_by_count":1}],"next_cursor":null}