{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1802.10062","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","created":"2018-02-27","cited_by_count":267},{"id":"2112.14757","title":"A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model","created":"2021-12-29","cited_by_count":223},{"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":"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":"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":"2112.05219","title":"CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions","created":"2021-12-09","cited_by_count":78},{"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":"2012.12482","title":"Localization in the Crowd with Topological Constraints","created":"2020-12-23","cited_by_count":68},{"id":"1904.01333","title":"Point in, Box out: Beyond Counting Persons in Crowds","created":"2019-04-02","cited_by_count":62},{"id":"2104.09116","title":"TransCrowd: weakly-supervised crowd counting with transformers","created":"2021-04-19","cited_by_count":61},{"id":"1803.03095","title":"Leveraging Unlabeled Data for Crowd Counting by Learning to Rank","created":"2018-03-08","cited_by_count":57},{"id":"2205.08535","title":"AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars","created":"2022-05-17","cited_by_count":55},{"id":"1902.06285","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","created":"2019-02-17","cited_by_count":52},{"id":"1908.06473","title":"From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer","created":"2019-08-15","cited_by_count":48},{"id":"2206.02338","title":"OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression","created":"2022-06-06","cited_by_count":44},{"id":"2201.06696","title":"ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues","created":"2022-01-18","cited_by_count":42},{"id":"1707.09605","title":"CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting","created":"2017-07-30","cited_by_count":41},{"id":"2107.13271","title":"Spatial Uncertainty-Aware Semi-Supervised Crowd Counting","created":"2021-07-28","cited_by_count":38},{"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":"2007.03207","title":"Semi-Supervised Crowd Counting via Self-Training on Surrogate Tasks","created":"2020-07-07","cited_by_count":35},{"id":"1903.12206","title":"Counting with Focus for Free","created":"2019-03-28","cited_by_count":33},{"id":"2003.00164","title":"Towards Using Count-level Weak Supervision for Crowd Counting","created":"2020-02-29","cited_by_count":33},{"id":"1907.12428","title":"Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting","created":"2019-07-29","cited_by_count":32},{"id":"2105.02440","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","created":"2021-05-06","cited_by_count":31},{"id":"1707.01202","title":"A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation","created":"2017-07-05","cited_by_count":29},{"id":"2006.09853","title":"Shallow Feature Based Dense Attention Network for Crowd Counting","created":"2020-06-17","cited_by_count":28},{"id":"2009.06420","title":"Completely Self-Supervised Crowd Counting via Distribution Matching","created":"2020-09-14","cited_by_count":22},{"id":"2107.12518","title":"Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP","created":"2021-07-26","cited_by_count":21},{"id":"2107.12619","title":"Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting","created":"2021-07-27","cited_by_count":20},{"id":"2207.09865","title":"Discrete-Constrained Regression for Local Counting Models","created":"2022-07-20","cited_by_count":19},{"id":"2209.02955","title":"Semi-supervised Crowd Counting via Density Agency","created":"2022-09-07","cited_by_count":18},{"id":"2002.12256","title":"ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images","created":"2020-02-27","cited_by_count":17},{"id":"1705.10118","title":"Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks - Counting, Detection, and Tracking","created":"2017-05-29","cited_by_count":15},{"id":"2108.08023","title":"Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting","created":"2021-08-18","cited_by_count":15},{"id":"2012.08149","title":"Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting","created":"2020-12-15","cited_by_count":10},{"id":"2107.12858","title":"Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network","created":"2021-07-27","cited_by_count":10},{"id":"1908.02797","title":"Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs","created":"2019-08-07","cited_by_count":3},{"id":"2303.06925","title":"Super-Resolution Information Enhancement For Crowd Counting","created":"2023-03-13","cited_by_count":2}],"next_cursor":null}