{"total":89,"rows":[{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962,"area":null},{"id":"2207.02696","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","created":"2022-07-06","cited_by_count":982,"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":"2203.11082","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2022-03-21","cited_by_count":281,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"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":"2204.02136","title":"Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation","created":"2022-04-05","cited_by_count":72,"area":null},{"id":"2206.09500","title":"Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free and Anchor-based Detectors","created":"2022-06-19","cited_by_count":69,"area":null},{"id":"2201.02593","title":"Equalized Focal Loss for Dense Long-Tailed Object Detection","created":"2022-01-07","cited_by_count":46,"area":null},{"id":"2106.00168","title":"Rethinking Pseudo Labels for Semi-Supervised Object Detection","created":"2021-06-01","cited_by_count":45,"area":null},{"id":"2303.14488","title":"Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images","created":"2023-03-25","cited_by_count":41,"area":null},{"id":"2203.15345","title":"Task-specific Inconsistency Alignment for Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":38,"area":null},{"id":"2401.03989","title":"MS-DETR: Efficient DETR Training with Mixed Supervision","created":"2024-01-08","cited_by_count":35,"area":null},{"id":"2112.10415","title":"UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery","created":"2021-12-20","cited_by_count":34,"area":null},{"id":"2212.06137","title":"NMS Strikes Back","created":"2022-12-12","cited_by_count":33,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2408.04804","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","created":"2024-08-09","cited_by_count":29,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28,"area":null},{"id":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","cited_by_count":26,"area":null},{"id":"2212.08472","title":"One-Stage Cascade Refinement Networks for Infrared Small Target Detection","created":"2022-12-16","cited_by_count":25,"area":null},{"id":"2207.02466","title":"GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation","created":"2022-07-06","cited_by_count":24,"area":null},{"id":"2207.09332","title":"Rethinking IoU-based Optimization for Single-stage 3D Object Detection","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2307.00934","title":"Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration","created":"2023-07-03","cited_by_count":19,"area":null},{"id":"2307.11035","title":"Cascade-DETR: Delving into High-Quality Universal Object Detection","created":"2023-07-20","cited_by_count":19,"area":null},{"id":"2108.10520","title":"Improving Object Detection by Label Assignment Distillation","created":"2021-08-24","cited_by_count":17,"area":null},{"id":"2202.04256","title":"GiraffeDet: A Heavy-Neck Paradigm for Object Detection","created":"2022-02-09","cited_by_count":17,"area":null},{"id":"2111.13336","title":"MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2203.06844","title":"RecursiveMix: Mixed Learning with History","created":"2022-03-14","cited_by_count":15,"area":null},{"id":"2409.19833","title":"HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes","created":"2024-09-30","cited_by_count":15,"area":null},{"id":"2303.02165","title":"DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network","created":"2023-03-05","cited_by_count":14,"area":null},{"id":"2207.05536","title":"DTG-SSOD: Dense Teacher Guidance for Semi-Supervised Object Detection","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2407.19696","title":"Cross-Layer Feature Pyramid Transformer for Small Object Detection in Aerial Images","created":"2024-07-29","cited_by_count":11,"area":null},{"id":"2206.13728","title":"Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection","created":"2022-06-28","cited_by_count":10,"area":null},{"id":"2308.09564","title":"Deep Equilibrium Object Detection","created":"2023-08-18","cited_by_count":10,"area":null},{"id":"2204.08394","title":"CenterNet++ for Object Detection","created":"2022-04-18","cited_by_count":9,"area":null},{"id":"2309.13242","title":"UniHead: Unifying Multi-Perception for Detection Heads","created":"2023-09-23","cited_by_count":9,"area":null},{"id":"2311.05237","title":"Widely Applicable Strong Baseline for Sports Ball Detection and Tracking","created":"2023-11-09","cited_by_count":9,"area":null},{"id":"2311.17085","title":"Beyond Visual Cues: Synchronously Exploring Target-Centric Semantics for Vision-Language Tracking","created":"2023-11-28","cited_by_count":9,"area":null},{"id":"2104.04899","title":"Location-Sensitive Visual Recognition with Cross-IOU Loss","created":"2021-04-11","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":"2309.12585","title":"BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection","created":"2023-09-22","cited_by_count":7,"area":null},{"id":"2201.09396","title":"Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs","created":"2022-01-23","cited_by_count":6,"area":null},{"id":"2206.03064","title":"A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector","created":"2022-06-07","cited_by_count":6,"area":null},{"id":"2312.10390","title":"Not Every Side Is Equal: Localization Uncertainty Estimation for Semi-Supervised 3D Object Detection","created":"2023-12-16","cited_by_count":6,"area":null},{"id":"2106.08061","title":"Relation Modeling in Spatio-Temporal Action Localization","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2109.08963","title":"SDTP: Semantic-aware Decoupled Transformer Pyramid for Dense Image Prediction","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2410.11774","title":"Fractal Calibration for long-tailed object detection","created":"2024-10-15","cited_by_count":5,"area":null},{"id":"2206.01232","title":"What Are Expected Queries in End-to-End Object Detection?","created":"2022-06-02","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":"2308.05881","title":"Aphid Cluster Recognition and Detection in the Wild Using Deep Learning Models","created":"2023-08-10","cited_by_count":4,"area":null},{"id":"2407.08460","title":"Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer","created":"2024-07-11","cited_by_count":4,"area":null},{"id":"2303.01047","title":"Task-Specific Context Decoupling for Object Detection","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2307.05929","title":"A New Dataset and Comparative Study for Aphid Cluster Detection","created":"2023-07-12","cited_by_count":3,"area":null},{"id":"2403.03390","title":"Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detection","created":"2024-03-06","cited_by_count":3,"area":null},{"id":"2405.04305","title":"A New Dataset and Comparative Study for Aphid Cluster Detection and Segmentation in Sorghum Fields","created":"2024-05-07","cited_by_count":3,"area":null},{"id":"2109.03596","title":"Learn2Agree: Fitting with Multiple Annotators without Objective Ground Truth","created":"2021-09-08","cited_by_count":2,"area":null},{"id":"2208.11050","title":"Tunable Hybrid Proposal Networks for the Open World","created":"2022-08-23","cited_by_count":2,"area":null},{"id":"2211.03407","title":"3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for V2X Orchestration","created":"2022-11-07","cited_by_count":2,"area":null},{"id":"2405.00442","title":"Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration","created":"2024-05-01","cited_by_count":2,"area":null},{"id":"2108.12176","title":"Rethinking the Misalignment Problem in Dense Object Detection","created":"2021-08-27","cited_by_count":1,"area":null},{"id":"2112.05138","title":"Searching Parameterized AP Loss for Object Detection","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2207.03520","title":"Should All Proposals be Treated Equally in Object Detection?","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2210.10526","title":"Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothing","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2309.02903","title":"Towards Efficient Training with Negative Samples in Visual Tracking","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2403.05155","title":"LanePtrNet: Revisiting Lane Detection as Point Voting and Grouping on Curves","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2406.11739","title":"V3Det Challenge 2024 on Vast Vocabulary and Open Vocabulary Object Detection: Methods and Results","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2412.13006","title":"What is YOLOv6? A Deep Insight into the Object Detection Model","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2503.04308","title":"Shaken, Not Stirred: A Novel Dataset for Visual Understanding of Glasses in Human-Robot Bartending Tasks","created":"2025-03-06","cited_by_count":1,"area":null},{"id":"2506.13027","title":"DETRPose: Real-Time End-to-End Multi-Person Pose Estimation via Modified Transformer Decoder and Novel Denoising Keypoints","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2509.18387","title":"BlurBall: Joint Ball and Motion Blur Estimation for Table Tennis Ball Tracking","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2109.07217","title":"Progressive Hard-case Mining across Pyramid Levels for Object Detection","created":"2021-09-15","cited_by_count":0,"area":null},{"id":"2112.08902","title":"Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2302.02814","title":"MixFormer: End-to-End Tracking with Iterative Mixed Attention","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2303.10411","title":"Multi-Semantic Interactive Learning for Object Detection","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2309.13269","title":"Being Aware of Localization Accuracy By Generating Predicted-IoU-Guided Quality Scores","created":"2023-09-23","cited_by_count":0,"area":null},{"id":"2408.17182","title":"Hybrid Classification-Regression Adaptive Loss for Dense Object Detection","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2511.08186","title":"Pixel-level Quality Assessment for Oriented Object Detection","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.21984","title":"A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation","created":"2025-12-26","cited_by_count":0,"area":null},{"id":"2601.01240","title":"RFAssigner: A Generic Label Assignment Strategy for Dense Object Detection","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2602.13378","title":"LAF-YOLOv10 with Partial Convolution Backbone, Attention-Guided Feature Pyramid, Auxiliary P2 Head, and Wise-IoU Loss for Small Object Detection in Drone Aerial Imagery","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.25555","title":"Towards Comprehensive Real-Time Scene Understanding in Ophthalmic Surgery through Multimodal Image Fusion","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.10210","title":"A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2607.00734","title":"ConRTF: Edge-Constrained Boundary Distribution Refinement for Realtime TransFormer Table Structure Recognition","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.14560","title":"Small Object Detection in Drone Aerial Imagery with LAF-YOLOv10","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}