{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2011.09157","title":"Dense Contrastive Learning for Self-Supervised Visual Pre-Training","created":"2020-11-18","cited_by_count":512},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"1808.01050","title":"Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds","created":"2018-08-02","cited_by_count":186},{"id":"2103.05950","title":"FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding","created":"2021-03-10","cited_by_count":168},{"id":"1908.03684","title":"Bayesian Loss for Crowd Count Estimation with Point Supervision","created":"2019-08-10","cited_by_count":162},{"id":"2107.12746","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","created":"2021-07-27","cited_by_count":152},{"id":"2001.03360","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","created":"2020-01-10","cited_by_count":151},{"id":"1811.10452","title":"Context-Aware Crowd Counting","created":"2018-11-26","cited_by_count":150},{"id":"1903.03303","title":"Learning from Synthetic Data for Crowd Counting in the Wild","created":"2019-03-08","cited_by_count":148},{"id":"2009.13077","title":"Distribution Matching for Crowd Counting","created":"2020-09-28","cited_by_count":143},{"id":"2104.13415","title":"Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank","created":"2021-04-27","cited_by_count":125},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114},{"id":"2106.02637","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","created":"2021-06-04","cited_by_count":110},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"1708.00199","title":"Switching Convolutional Neural Network for Crowd Counting","created":"2017-08-01","cited_by_count":93},{"id":"2202.13065","title":"An End-to-End Transformer Model for Crowd Localization","created":"2022-02-26","cited_by_count":74},{"id":"1906.07538","title":"Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection","created":"2019-06-18","cited_by_count":73},{"id":"2203.02636","title":"Boosting Crowd Counting via Multifaceted Attention","created":"2022-03-05","cited_by_count":73},{"id":"1612.04402","title":"Finding Tiny Faces","created":"2016-12-13","cited_by_count":72},{"id":"2012.12482","title":"Localization in the Crowd with Topological Constraints","created":"2020-12-23","cited_by_count":68},{"id":"2104.09116","title":"TransCrowd: weakly-supervised crowd counting with transformers","created":"2021-04-19","cited_by_count":61},{"id":"1807.09856","title":"Where are the Blobs: Counting by Localization with Point Supervision","created":"2018-07-25","cited_by_count":54},{"id":"2206.05253","title":"Rethinking Spatial Invariance of Convolutional Networks for Object Counting","created":"2022-06-10","cited_by_count":54},{"id":"2203.05046","title":"Adaptive Trajectory Prediction via Transferable GNN","created":"2022-03-09","cited_by_count":51},{"id":"1811.11968","title":"ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding","created":"2018-11-29","cited_by_count":45},{"id":"2007.12831","title":"A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds","created":"2020-07-25","cited_by_count":36},{"id":"2102.07925","title":"Focal Inverse Distance Transform Maps for Crowd Localization","created":"2021-02-16","cited_by_count":36},{"id":"1912.09632","title":"AutoScale: Learning to Scale for Crowd Counting and Localization","created":"2019-12-20","cited_by_count":35},{"id":"1907.10255","title":"HA-CCN: Hierarchical Attention-based Crowd Counting Network","created":"2019-07-24","cited_by_count":32},{"id":"1912.03677","title":"Domain-adaptive Crowd Counting via High-quality Image Translation and Density Reconstruction","created":"2019-12-08","cited_by_count":26},{"id":"2012.04164","title":"Learning Independent Instance Maps for Crowd Localization","created":"2020-12-08","cited_by_count":24},{"id":"2003.05586","title":"Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting","created":"2020-03-12","cited_by_count":22},{"id":"2007.09509","title":"Tracking-by-Counting: Using Network Flows on Crowd Density Maps for Tracking Multiple Targets","created":"2020-07-18","cited_by_count":18},{"id":"2208.02894","title":"Redesigning Multi-Scale Neural Network for Crowd Counting","created":"2022-08-04","cited_by_count":17},{"id":"1811.02805","title":"PaDNet: Pan-Density Crowd Counting","created":"2018-11-07","cited_by_count":16},{"id":"2202.13660","title":"FusionCount: Efficient Crowd Counting via Multiscale Feature Fusion","created":"2022-02-28","cited_by_count":13},{"id":"2206.05717","title":"Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher","created":"2022-06-12","cited_by_count":12},{"id":"2007.06146","title":"Fine-Grained Crowd Counting","created":"2020-07-13","cited_by_count":9},{"id":"2206.10075","title":"Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation","created":"2022-06-21","cited_by_count":8},{"id":"1507.08445","title":"People Counting in High Density Crowds from Still Images","created":"2015-07-30","cited_by_count":4}],"next_cursor":null}