{"list":"other","total":56,"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":"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":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1605.06409","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","created":"2016-05-20","cited_by_count":414},{"id":"1904.11492","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","created":"2019-04-25","cited_by_count":331},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1904.07392","title":"NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection","created":"2019-04-16","cited_by_count":291},{"id":"1611.02167","title":"Designing Neural Network Architectures using Reinforcement Learning","created":"2016-11-07","cited_by_count":279},{"id":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"1904.05049","title":"Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution","created":"2019-04-10","cited_by_count":140},{"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":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"1607.07155","title":"A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection","created":"2016-07-25","cited_by_count":83},{"id":"1811.04533","title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","created":"2018-11-12","cited_by_count":76},{"id":"1812.00442","title":"Deep Cosine Metric Learning for Person Re-Identification","created":"2018-12-02","cited_by_count":73},{"id":"1505.01749","title":"Object detection via a multi-region & semantic segmentation-aware CNN model","created":"2015-05-07","cited_by_count":47},{"id":"2003.00425","title":"Learning When and Where to Zoom with Deep Reinforcement Learning","created":"2020-03-01","cited_by_count":43},{"id":"2203.09507","title":"Towards Data-Efficient Detection Transformers","created":"2022-03-17","cited_by_count":34},{"id":"1707.01691","title":"RON: Reverse Connection with Objectness Prior Networks for Object Detection","created":"2017-07-06","cited_by_count":27},{"id":"1704.04224","title":"Spatial Memory for Context Reasoning in Object Detection","created":"2017-04-13","cited_by_count":22},{"id":"2112.04632","title":"Recurrent Glimpse-based Decoder for Detection with Transformer","created":"2021-12-09","cited_by_count":21},{"id":"1703.09844","title":"Multi-Scale Dense Networks for Resource Efficient Image Classification","created":"2017-03-29","cited_by_count":16},{"id":"1606.04446","title":"Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization","created":"2016-06-14","cited_by_count":15},{"id":"2004.03580","title":"Feature Pyramid Grids","created":"2020-04-07","cited_by_count":13},{"id":"1610.02579","title":"Crafting GBD-Net for Object Detection","created":"2016-10-08","cited_by_count":6}],"next_cursor":null}