{"list":"other","total":57,"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2009.14119","title":"Asymmetric Loss For Multi-Label Classification","created":"2020-09-29","cited_by_count":381},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1711.07319","title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","created":"2017-11-20","cited_by_count":341},{"id":"1908.10357","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","created":"2019-08-27","cited_by_count":247},{"id":"2101.07448","title":"Fast Convergence of DETR with Spatially Modulated Co-Attention","created":"2021-01-19","cited_by_count":176},{"id":"1910.06278","title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","created":"2019-10-14","cited_by_count":165},{"id":"2011.10881","title":"Rethinking Transformer-based Set Prediction for Object Detection","created":"2020-11-21","cited_by_count":156},{"id":"1803.08225","title":"PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model","created":"2018-03-22","cited_by_count":133},{"id":"2107.10834","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","created":"2021-07-22","cited_by_count":128},{"id":"1903.06593","title":"PifPaf: Composite Fields for Human Pose Estimation","created":"2019-03-15","cited_by_count":120},{"id":"2106.05656","title":"MST: Masked Self-Supervised Transformer for Visual Representation","created":"2021-06-10","cited_by_count":114},{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99},{"id":"2108.11353","title":"Multi-Task Self-Training for Learning General Representations","created":"2021-08-25","cited_by_count":85},{"id":"2111.12933","title":"ML-Decoder: Scalable and Versatile Classification Head","created":"2021-11-25","cited_by_count":79},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68},{"id":"2007.01755","title":"Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition","created":"2020-07-03","cited_by_count":50},{"id":"1911.07451","title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","created":"2019-11-18","cited_by_count":49},{"id":"2107.14467","title":"DPT: Deformable Patch-based Transformer for Visual Recognition","created":"2021-07-30","cited_by_count":43},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43},{"id":"2203.06965","title":"UniVIP: A Unified Framework for Self-Supervised Visual Pre-training","created":"2022-03-14","cited_by_count":31},{"id":"2103.12115","title":"End-to-End Trainable Multi-Instance Pose Estimation with Transformers","created":"2021-03-22","cited_by_count":30},{"id":"2106.06195","title":"MlTr: Multi-label Classification with Transformer","created":"2021-06-11","cited_by_count":21},{"id":"2203.12054","title":"Self-supervision through Random Segments with Autoregressive Coding (RandSAC)","created":"2022-03-22","cited_by_count":16},{"id":"2208.14706","title":"Transfering Low-Frequency Features for Domain Adaptation","created":"2022-08-31","cited_by_count":5}],"next_cursor":null}