{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2012.15840","title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers","created":"2020-12-31","cited_by_count":1369},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"2103.00112","title":"Transformer in Transformer","created":"2021-02-27","cited_by_count":633},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2011.14503","title":"End-to-End Video Instance Segmentation with Transformers","created":"2020-11-30","cited_by_count":443},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"1409.5185","title":"Deeply-Supervised Nets","created":"2014-09-18","cited_by_count":367},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"1605.09673","title":"Dynamic Filter Networks","created":"2016-05-31","cited_by_count":319},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1604.00923","title":"Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning","created":"2016-04-04","cited_by_count":286},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170},{"id":"2104.12533","title":"Visformer: The Vision-friendly Transformer","created":"2021-04-26","cited_by_count":137},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117},{"id":"2106.03746","title":"Efficient Training of Visual Transformers with Small Datasets","created":"2021-06-07","cited_by_count":108},{"id":"2007.03496","title":"AutoAssign: Differentiable Label Assignment for Dense Object Detection","created":"2020-07-07","cited_by_count":100},{"id":"1909.02466","title":"FreeAnchor: Learning to Match Anchors for Visual Object Detection","created":"2019-09-05","cited_by_count":90},{"id":"1901.03278","title":"Region Proposal by Guided Anchoring","created":"2019-01-10","cited_by_count":87},{"id":"2109.07036","title":"PnP-DETR: Towards Efficient Visual Analysis with Transformers","created":"2021-09-15","cited_by_count":52},{"id":"2105.15168","title":"MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens","created":"2021-05-31","cited_by_count":46},{"id":"2112.02582","title":"PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation","created":"2021-12-05","cited_by_count":36},{"id":"2201.10728","title":"Training Vision Transformers with Only 2040 Images","created":"2022-01-26","cited_by_count":23},{"id":"1807.00980","title":"MetaAnchor: Learning to Detect Objects with Customized Anchors","created":"2018-07-03","cited_by_count":21},{"id":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21}],"next_cursor":null}