{"total":45,"rows":[{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823,"area":null},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515,"area":null},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2111.14330","title":"Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity","created":"2021-11-29","cited_by_count":98,"area":null},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98,"area":null},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96,"area":null},{"id":"2211.14843","title":"Learning Object-Language Alignments for Open-Vocabulary Object Detection","created":"2022-11-27","cited_by_count":96,"area":null},{"id":"2303.12776","title":"Dense Distinct Query for End-to-End Object Detection","created":"2023-03-22","cited_by_count":77,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2205.12785","title":"AO2-DETR: Arbitrary-Oriented Object Detection Transformer","created":"2022-05-25","cited_by_count":55,"area":null},{"id":"2311.02738","title":"Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion","created":"2023-11-05","cited_by_count":47,"area":null},{"id":"2304.04742","title":"Detection Transformer with Stable Matching","created":"2023-04-10","cited_by_count":44,"area":null},{"id":"2303.15334","title":"ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box","created":"2023-03-27","cited_by_count":20,"area":null},{"id":"2212.05505","title":"Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detection","created":"2022-12-11","cited_by_count":19,"area":null},{"id":"2305.18452","title":"Generating Driving Scenes with Diffusion","created":"2023-05-29","cited_by_count":16,"area":null},{"id":"2407.05909","title":"Multi-clue Consistency Learning to Bridge Gaps Between General and Oriented Object in Semi-supervised Detection","created":"2024-07-08","cited_by_count":11,"area":null},{"id":"2109.05986","title":"Mutual Supervision for Dense Object Detection","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2401.16424","title":"Computer Vision for Primate Behavior Analysis in the Wild","created":"2024-01-29","cited_by_count":10,"area":null},{"id":"2211.02006","title":"SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency","created":"2022-11-03","cited_by_count":9,"area":null},{"id":"2209.05774","title":"PointScatter: Point Set Representation for Tubular Structure Extraction","created":"2022-09-13","cited_by_count":8,"area":null},{"id":"2212.04067","title":"Consistency-Aware Anchor Pyramid Network for Crowd Localization","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2303.11567","title":"One-to-Few Label Assignment for End-to-End Dense Detection","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2304.04978","title":"StageInteractor: Query-based Object Detector with Cross-stage Interaction","created":"2023-04-11","cited_by_count":8,"area":null},{"id":"2303.12976","title":"NVAutoNet: Fast and Accurate 360$^{\\circ}$ 3D Visual Perception For Self Driving","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2211.14522","title":"Visual Fault Detection of Multi-scale Key Components in Freight Trains","created":"2022-11-26","cited_by_count":5,"area":null},{"id":"2211.06588","title":"DEYO: DETR with YOLO for Step-by-Step Object Detection","created":"2022-11-12","cited_by_count":4,"area":null},{"id":"2211.13859","title":"DATE: Dual Assignment for End-to-End Fully Convolutional Object Detection","created":"2022-11-25","cited_by_count":4,"area":null},{"id":"2301.01019","title":"Correlation Loss: Enforcing Correlation between Classification and Localization","created":"2023-01-03","cited_by_count":4,"area":null},{"id":"2305.10801","title":"Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection","created":"2023-05-18","cited_by_count":3,"area":null},{"id":"2507.02751","title":"Partial Weakly-Supervised Oriented Object Detection","created":"2025-07-03","cited_by_count":3,"area":null},{"id":"2307.13310","title":"CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer","created":"2023-07-25","cited_by_count":2,"area":null},{"id":"2312.13735","title":"DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2312.00699","title":"Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2411.01499","title":"Polar R-CNN: End-to-End Lane Detection with Fewer Anchors","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2509.08738","title":"CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2112.00342","title":"Confidence Propagation Cluster: Unleash Full Potential of Object Detectors","created":"2021-12-01","cited_by_count":0,"area":null},{"id":"2203.06424","title":"VariabilityTrack:Multi-Object Tracking with Variable Speed Object Movement","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2205.12458","title":"A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains","created":"2022-05-25","cited_by_count":0,"area":null},{"id":"2310.15725","title":"Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection","created":"2023-10-24","cited_by_count":0,"area":null},{"id":"2312.02821","title":"RotaTR: Detection Transformer for Dense and Rotated Object","created":"2023-12-05","cited_by_count":0,"area":null},{"id":"2602.03634","title":"SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2605.00362","title":"Time-series Meets Complex Motion Modeling: Robust and Computational-effective Motion Predictor for Multi-object Tracking","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2610.05191","title":"Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.19369","title":"The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}