{"list":"other","total":52,"rows":[{"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":"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":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"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":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"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":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"1904.01169","title":"Res2Net: A New Multi-scale Backbone Architecture","created":"2019-04-02","cited_by_count":470},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"1904.02701","title":"Libra R-CNN: Towards Balanced Learning for Object Detection","created":"2019-04-04","cited_by_count":255},{"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":"1901.01892","title":"Scale-Aware Trident Networks for Object Detection","created":"2019-01-07","cited_by_count":159},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2207.03620","title":"More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity","created":"2022-07-07","cited_by_count":142},{"id":"1903.00621","title":"Feature Selective Anchor-Free Module for Single-Shot Object Detection","created":"2019-03-02","cited_by_count":139},{"id":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"1811.12030","title":"Grid R-CNN","created":"2018-11-29","cited_by_count":85},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77},{"id":"2012.03544","title":"End-to-End Object Detection with Fully Convolutional Network","created":"2020-12-07","cited_by_count":70},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50},{"id":"2012.05780","title":"What Makes for End-to-End Object Detection?","created":"2020-12-10","cited_by_count":49},{"id":"2110.03921","title":"ViDT: An Efficient and Effective Fully Transformer-based Object Detector","created":"2021-10-08","cited_by_count":46},{"id":"1909.03625","title":"CBNet: A Novel Composite Backbone Network Architecture for Object Detection","created":"2019-09-09","cited_by_count":44},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44},{"id":"1911.12448","title":"Soft Anchor-Point Object Detection","created":"2019-11-27","cited_by_count":42},{"id":"2307.12612","title":"Less is More: Focus Attention for Efficient DETR","created":"2023-07-24","cited_by_count":38},{"id":"1904.03797","title":"FoveaBox: Beyond Anchor-based Object Detector","created":"2019-04-08","cited_by_count":37},{"id":"2303.07335","title":"Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR","created":"2023-03-13","cited_by_count":36},{"id":"2003.11818","title":"Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection","created":"2020-03-26","cited_by_count":32},{"id":"1904.08900","title":"CornerNet-Lite: Efficient Keypoint Based Object Detection","created":"2019-04-18","cited_by_count":24}],"next_cursor":null}