{"list":"other","total":55,"rows":[{"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"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":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2106.13797","title":"PVT v2: Improved Baselines with Pyramid Vision Transformer","created":"2021-06-25","cited_by_count":751},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"1909.00133","title":"Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark","created":"2019-08-31","cited_by_count":340},{"id":"2106.09018","title":"End-to-End Semi-Supervised Object Detection with Soft Teacher","created":"2021-06-16","cited_by_count":316},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"1805.00123","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","created":"2018-04-30","cited_by_count":284},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2312.10115","title":"SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery","created":"2023-12-15","cited_by_count":205},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"2011.09980","title":"Geography-Aware Self-Supervised Learning","created":"2020-11-19","cited_by_count":190},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"id":"2211.15660","title":"SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding","created":"2022-11-28","cited_by_count":167},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"2004.03597","title":"JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method","created":"2020-04-07","cited_by_count":109},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66},{"id":"1904.00853","title":"Precise Detection in Densely Packed Scenes","created":"2019-04-01","cited_by_count":63},{"id":"1912.10664","title":"Scale Match for Tiny Person Detection","created":"2019-12-23","cited_by_count":61},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56},{"id":"2203.16317","title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","created":"2022-03-30","cited_by_count":51},{"id":"2208.08738","title":"RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection","created":"2022-08-18","cited_by_count":51},{"id":"2403.06534","title":"SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection","created":"2024-03-11","cited_by_count":48},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43},{"id":"2204.04716","title":"TOV: The Original Vision Model for Optical Remote Sensing Image Understanding via Self-supervised Learning","created":"2022-04-10","cited_by_count":35},{"id":"2207.06827","title":"Point-to-Box Network for Accurate Object Detection via Single Point Supervision","created":"2022-07-14","cited_by_count":31},{"id":"2012.01950","title":"Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection","created":"2020-12-03","cited_by_count":29},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27},{"id":"2412.10116","title":"HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection","created":"2024-12-13","cited_by_count":22},{"id":"2207.09697","title":"Robust Object Detection With Inaccurate Bounding Boxes","created":"2022-07-20","cited_by_count":20},{"id":"1803.09256","title":"Detecting Heads using Feature Refine Net and Cascaded Multi-Scale Architecture","created":"2018-03-25","cited_by_count":18},{"id":"2403.05416","title":"SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection","created":"2024-03-08","cited_by_count":17},{"id":"2201.04620","title":"SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining","created":"2022-01-12","cited_by_count":14},{"id":"2410.08210","title":"PointOBB-v2: Towards Simpler, Faster, and Stronger Single Point Supervised Oriented Object Detection","created":"2024-10-10","cited_by_count":13},{"id":"2303.07582","title":"Calibrated Teacher for Sparsely Annotated Object Detection","created":"2023-03-14","cited_by_count":10},{"id":"2307.12101","title":"Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes","created":"2023-07-22","cited_by_count":9},{"id":"2501.13898","title":"PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection","created":"2025-01-23","cited_by_count":9},{"id":"2407.02394","title":"Similarity Distance-Based Label Assignment for Tiny Object Detection","created":"2024-07-02","cited_by_count":5},{"id":"2401.08056","title":"Robust Tiny Object Detection in Aerial Images amidst Label Noise","created":"2024-01-16","cited_by_count":4},{"id":"2407.04590","title":"SH17: A Dataset for Human Safety and Personal Protective Equipment Detection in Manufacturing Industry","created":"2024-07-05","cited_by_count":4},{"id":"2412.11582","title":"Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning","created":"2024-12-16","cited_by_count":3},{"id":"2308.12116","title":"The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures","created":"2023-08-23","cited_by_count":2},{"id":"2412.05837","title":"Tiny Object Detection with Single Point Supervision","created":"2024-12-08","cited_by_count":2},{"id":"2509.26281","title":"Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization","created":"2025-09-30","cited_by_count":2},{"id":"2505.20687","title":"VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images","created":"2025-05-27","cited_by_count":1}],"next_cursor":null}