{"total":30,"rows":[{"id":"2104.06976","title":"Pose Recognition with Cascade Transformers","created":"2021-04-14","cited_by_count":99,"area":null},{"id":"2207.10988","title":"Few-shot Object Counting and Detection","created":"2022-07-22","cited_by_count":55,"area":null},{"id":"2308.10468","title":"STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning","created":"2023-08-21","cited_by_count":41,"area":null},{"id":"2105.02440","title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","created":"2021-05-06","cited_by_count":31,"area":null},{"id":"2103.16291","title":"Leveraging Self-Supervision for Cross-Domain Crowd Counting","created":"2021-03-30","cited_by_count":24,"area":null},{"id":"2207.09295","title":"The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting","created":"2022-07-19","cited_by_count":24,"area":null},{"id":"2203.12335","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","created":"2022-03-23","cited_by_count":18,"area":null},{"id":"2107.08645","title":"Video Crowd Localization with Multi-focus Gaussian Neighborhood Attention and a Large-Scale Benchmark","created":"2021-07-19","cited_by_count":13,"area":null},{"id":"2108.00584","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","created":"2021-08-02","cited_by_count":11,"area":null},{"id":"2506.15368","title":"Open-World Object Counting in Videos","created":"2025-06-18","cited_by_count":11,"area":null},{"id":"2101.12439","title":"Spatiotemporal Dilated Convolution with Uncertain Matching for Video-based Crowd Estimation","created":"2021-01-29","cited_by_count":9,"area":null},{"id":"2107.08766","title":"VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results","created":"2021-07-19","cited_by_count":5,"area":null},{"id":"2312.05923","title":"Weakly Supervised Video Individual CountingWeakly Supervised Video Individual Counting","created":"2023-12-10","cited_by_count":5,"area":null},{"id":"2208.11339","title":"A Spatio-Temporal Attentive Network for Video-Based Crowd Counting","created":"2022-08-24","cited_by_count":4,"area":null},{"id":"2503.10701","title":"Video Individual Counting for Moving Drones","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2110.04727","title":"LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2110.14613","title":"International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines","created":"2021-10-27","cited_by_count":3,"area":null},{"id":"2208.12644","title":"Why is the video analytics accuracy fluctuating, and what can we do about it?","created":"2022-08-23","cited_by_count":3,"area":null},{"id":"2104.13946","title":"Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting","created":"2021-04-28","cited_by_count":2,"area":null},{"id":"2206.08084","title":"An Improved Normed-Deformable Convolution for Crowd Counting","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2404.13992","title":"Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2506.13067","title":"Video Individual Counting With Implicit One-to-Many Matching","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2601.01192","title":"Crowded Video Individual Counting Informed by Social Grouping and Spatial-Temporal Displacement Priors","created":"2026-01-03","cited_by_count":2,"area":null},{"id":"2401.07586","title":"Curriculum for Crowd Counting -- Is it Worthy?","created":"2024-01-15","cited_by_count":1,"area":null},{"id":"2403.03461","title":"A Density-Guided Temporal Attention Transformer for Indiscernible Object Counting in Underwater Video","created":"2024-03-06","cited_by_count":1,"area":null},{"id":"2407.14725","title":"CrowdMAC: Masked Crowd Density Completion for Robust Crowd Density Forecasting","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2411.13056","title":"Efficient Masked AutoEncoder for Video Object Counting and A Large-Scale Benchmark","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2503.08152","title":"Depth-Assisted Network for Indiscernible Marine Object Counting with Adaptive Motion-Differentiated Feature Encoding","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2204.04653","title":"Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches","created":"2022-04-10","cited_by_count":0,"area":null},{"id":"2212.04061","title":"Elixir: A system to enhance data quality for multiple analytics on a video stream","created":"2022-12-08","cited_by_count":0,"area":null}],"next_cursor":null}