{"list":"other","total":72,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1609.05158","title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network","created":"2016-09-16","cited_by_count":1204},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"1811.11168","title":"Deformable ConvNets v2: More Deformable, Better Results","created":"2018-11-27","cited_by_count":670},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2003.08505","title":"A Metric Learning Reality Check","created":"2020-03-18","cited_by_count":321},{"id":"1812.05050","title":"Fast Online Object Tracking and Segmentation: A Unifying Approach","created":"2018-12-12","cited_by_count":272},{"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":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"1707.05972","title":"Drone-based Object Counting by Spatially Regularized Regional Proposal Network","created":"2017-07-19","cited_by_count":156},{"id":"1901.08043","title":"Bottom-up Object Detection by Grouping Extreme and Center Points","created":"2019-01-23","cited_by_count":156},{"id":"1811.10452","title":"Context-Aware Crowd Counting","created":"2018-11-26","cited_by_count":150},{"id":"2104.08391","title":"Learning To Count Everything","created":"2021-04-16","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":"1711.09081","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","created":"2017-11-24","cited_by_count":127},{"id":"1708.00199","title":"Switching Convolutional Neural Network for Crowd Counting","created":"2017-08-01","cited_by_count":93},{"id":"1811.00472","title":"Class-Agnostic Counting","created":"2018-11-01","cited_by_count":85},{"id":"2305.07304","title":"CLIP-Count: Towards Text-Guided Zero-Shot Object Counting","created":"2023-05-12","cited_by_count":83},{"id":"2203.08354","title":"Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting","created":"2022-03-16","cited_by_count":80},{"id":"2208.13721","title":"CounTR: Transformer-based Generalised Visual Counting","created":"2022-08-29","cited_by_count":79},{"id":"2211.08217","title":"A Low-Shot Object Counting Network With Iterative Prototype Adaptation","created":"2022-11-15","cited_by_count":65},{"id":"2201.08959","title":"Few-shot Object Counting with Similarity-Aware Feature Enhancement","created":"2022-01-22","cited_by_count":62},{"id":"2303.02001","title":"Zero-shot Object Counting","created":"2023-03-03","cited_by_count":57},{"id":"1608.06197","title":"CrowdNet: A Deep Convolutional Network for Dense Crowd Counting","created":"2016-08-22","cited_by_count":52},{"id":"2404.16622","title":"DAVE -- A Detect-and-Verify Paradigm for Low-Shot Counting","created":"2024-04-25","cited_by_count":49},{"id":"2312.16580","title":"VLCounter: Text-aware Visual Representation for Zero-Shot Object Counting","created":"2023-12-27","cited_by_count":45},{"id":"2003.12783","title":"CNN-based Density Estimation and Crowd Counting: A Survey","created":"2020-03-28","cited_by_count":43},{"id":"2205.10203","title":"Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision","created":"2022-05-20","cited_by_count":41},{"id":"2306.01851","title":"Open-world Text-specified Object Counting","created":"2023-06-02","cited_by_count":41},{"id":"2311.12386","title":"Point, Segment and Count: A Generalized Framework for Object Counting","created":"2023-11-21","cited_by_count":39},{"id":"2307.00038","title":"Training-free Object Counting with Prompts","created":"2023-06-30","cited_by_count":34},{"id":"2205.14212","title":"Exemplar Free Class Agnostic Counting","created":"2022-05-27","cited_by_count":32},{"id":"1703.08710","title":"Count-ception: Counting by Fully Convolutional Redundant Counting","created":"2017-03-25","cited_by_count":30},{"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":"1707.09476","title":"FCN-rLSTM: Deep Spatio-Temporal Neural Networks for Vehicle Counting in City Cameras","created":"2017-07-29","cited_by_count":27},{"id":"1707.02290","title":"TasselNet: Counting maize tassels in the wild via local counts regression network","created":"2017-07-07","cited_by_count":26},{"id":"2305.04440","title":"Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting","created":"2023-05-08","cited_by_count":25},{"id":"2407.04948","title":"Zero-shot Object Counting with Good Exemplars","created":"2024-07-06","cited_by_count":21},{"id":"1903.02025","title":"Crowd Counting Using Scale-Aware Attention Networks","created":"2019-03-05","cited_by_count":20},{"id":"1903.07427","title":"Crowd Counting with Decomposed Uncertainty","created":"2019-03-15","cited_by_count":20},{"id":"2209.07271","title":"Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives","created":"2022-09-14","cited_by_count":16},{"id":"2403.05435","title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","created":"2024-03-08","cited_by_count":16},{"id":"2309.04820","title":"ABC Easy as 123: A Blind Counter for Exemplar-Free Multi-Class Class-agnostic Counting","created":"2023-09-09","cited_by_count":13},{"id":"2403.04943","title":"AFreeCA: Annotation-Free Counting for All","created":"2024-03-07","cited_by_count":12},{"id":"2409.15953","title":"Mind the Prompt: A Novel Benchmark for Prompt-based Class-Agnostic Counting","created":"2024-09-24","cited_by_count":11},{"id":"2403.10236","title":"A Fixed-Point Approach to Unified Prompt-Based Counting","created":"2024-03-15","cited_by_count":10},{"id":"2106.02842","title":"Multi-Camera Vehicle Counting Using Edge-AI","created":"2021-06-05","cited_by_count":7},{"id":"2311.16122","title":"Semantic Generative Augmentations for Few-Shot Counting","created":"2023-10-26","cited_by_count":6},{"id":"2012.15685","title":"A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal","created":"2020-12-31","cited_by_count":5},{"id":"2307.08727","title":"Learning to Count without Annotations","created":"2023-07-17","cited_by_count":5},{"id":"2405.11770","title":"Learning Spatial Similarity Distribution for Few-shot Object Counting","created":"2024-05-20","cited_by_count":5},{"id":"2208.11339","title":"A Spatio-Temporal Attentive Network for Video-Based Crowd Counting","created":"2022-08-24","cited_by_count":4},{"id":"2302.05132","title":"GCNet: Probing Self-Similarity Learning for Generalized Counting Network","created":"2023-02-10","cited_by_count":4}],"next_cursor":null}