{"list":"other","total":51,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"1710.11063","title":"Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks","created":"2017-10-30","cited_by_count":939},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","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":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1604.06646","title":"Synthetic Data for Text Localisation in Natural Images","created":"2016-04-22","cited_by_count":396},{"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":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307},{"id":"1810.08462","title":"Fully Convolutional Siamese Networks for Change Detection","created":"2018-10-19","cited_by_count":306},{"id":"2103.00208","title":"Remote Sensing Image Change Detection with Transformers","created":"2021-02-27","cited_by_count":306},{"id":"2201.09873","title":"Transformers in Medical Imaging: A Survey","created":"2022-01-24","cited_by_count":245},{"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":"2107.02988","title":"SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers","created":"2021-07-07","cited_by_count":169},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"1710.03959","title":"Deep learning in remote sensing: a review","created":"2017-10-11","cited_by_count":128},{"id":"1810.08468","title":"Urban Change Detection for Multispectral Earth Observation Using Convolutional Neural Networks","created":"2018-10-19","cited_by_count":110},{"id":"2204.02825","title":"An Empirical Study of Remote Sensing Pretraining","created":"2022-04-06","cited_by_count":105},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"2107.09244","title":"S2Looking: A Satellite Side-Looking Dataset for Building Change Detection","created":"2021-07-20","cited_by_count":77},{"id":"2003.03608","title":"DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images","created":"2020-03-07","cited_by_count":75},{"id":"2005.09973","title":"Dynamic Refinement Network for Oriented and Densely Packed Object Detection","created":"2020-05-20","cited_by_count":72},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65},{"id":"2203.16952","title":"Multimodal Fusion Transformer for Remote Sensing Image Classification","created":"2022-03-31","cited_by_count":64},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55},{"id":"2203.02503","title":"HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening","created":"2022-03-04","cited_by_count":32},{"id":"2104.07784","title":"A survey of active learning algorithms for supervised remote sensing image classification","created":"2021-04-15","cited_by_count":27},{"id":"1310.5107","title":"Advances in Hyperspectral Image Classification: Earth monitoring with statistical learning methods","created":"2013-10-18","cited_by_count":26},{"id":"2111.15637","title":"Building extraction with vision transformer","created":"2021-11-29","cited_by_count":22},{"id":"2106.03146","title":"Oriented Object Detection with Transformer","created":"2021-06-06","cited_by_count":20},{"id":"2203.02916","title":"PanFormer: a Transformer Based Model for Pan-sharpening","created":"2022-03-06","cited_by_count":18},{"id":"1907.01821","title":"Super-Resolution of PROBA-V Images Using Convolutional Neural Networks","created":"2019-07-03","cited_by_count":17},{"id":"2201.09355","title":"Transformer-based SAR Image Despeckling","created":"2022-01-23","cited_by_count":15},{"id":"2205.14328","title":"Point RCNN: An Angle-Free Framework for Rotated Object Detection","created":"2022-05-28","cited_by_count":6},{"id":"2203.04771","title":"Multiscale Convolutional Transformer with Center Mask Pretraining for Hyperspectral Image Classification","created":"2022-03-09","cited_by_count":4}],"next_cursor":null}