{"total":82,"rows":[{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"area":null},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424,"area":null},{"id":"2103.17154","title":"Learning Spatio-Temporal Transformer for Visual Tracking","created":"2021-03-31","cited_by_count":350,"area":null},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"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":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55,"area":"distill"},{"id":"2209.01814","title":"RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection","created":"2022-09-05","cited_by_count":55,"area":null},{"id":"2103.11617","title":"Anchor-Free Person Search","created":"2021-03-22","cited_by_count":42,"area":null},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"area":null},{"id":"2203.12338","title":"Real-time Object Detection for Streaming Perception","created":"2022-03-23","cited_by_count":30,"area":null},{"id":"2101.06849","title":"CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images","created":"2021-01-18","cited_by_count":29,"area":null},{"id":"2308.10147","title":"ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer","created":"2023-08-20","cited_by_count":29,"area":null},{"id":"2307.03407","title":"Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2306.04670","title":"Object Detection with Transformers: A Review","created":"2023-06-07","cited_by_count":22,"area":null},{"id":"2203.09510","title":"DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection","created":"2022-03-17","cited_by_count":20,"area":null},{"id":"2204.05957","title":"Localization Distillation for Object Detection","created":"2022-04-12","cited_by_count":19,"area":"distill"},{"id":"2110.13675","title":"Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression","created":"2021-10-26","cited_by_count":18,"area":null},{"id":"2207.12926","title":"A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2506.04623","title":"VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection","created":"2025-06-05","cited_by_count":13,"area":null},{"id":"2103.03768","title":"VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges","created":"2021-03-05","cited_by_count":11,"area":null},{"id":"2308.12477","title":"American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers","created":"2023-08-24","cited_by_count":11,"area":null},{"id":"2103.14027","title":"USB: Universal-Scale Object Detection Benchmark","created":"2021-03-25","cited_by_count":10,"area":null},{"id":"2109.05986","title":"Mutual Supervision for Dense Object Detection","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2304.02737","title":"Efficient OCR for Building a Diverse Digital History","created":"2023-04-05","cited_by_count":10,"area":null},{"id":"2108.04644","title":"FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network","created":"2021-08-10","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":"2304.11805","title":"OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images","created":"2023-04-24","cited_by_count":8,"area":null},{"id":"2310.15955","title":"Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection","created":"2023-10-24","cited_by_count":8,"area":null},{"id":"2207.10433","title":"StreamYOLO: Real-time Object Detection for Streaming Perception","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2312.14471","title":"Prototype-based Cross-Modal Object Tracking","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2210.06008","title":"BoxMask: Revisiting Bounding Box Supervision for Video Object Detection","created":"2022-10-12","cited_by_count":6,"area":null},{"id":"2510.22675","title":"DAMap: Distance-aware MapNet for High Quality HD Map Construction","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2104.13876","title":"PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling","created":"2021-04-28","cited_by_count":5,"area":null},{"id":"2109.00211","title":"Efficient Person Search: An Anchor-Free Approach","created":"2021-09-01","cited_by_count":5,"area":null},{"id":"2206.06829","title":"Efficient Decoder-free Object Detection with Transformers","created":"2022-06-14","cited_by_count":5,"area":null},{"id":"2207.05334","title":"Cycle Self-Training for Semi-Supervised Object Detection with Distribution Consistency Reweighting","created":"2022-07-12","cited_by_count":5,"area":"distill"},{"id":"2110.12130","title":"RCNet: Reverse Feature Pyramid and Cross-scale Shift Network for Object Detection","created":"2021-10-23","cited_by_count":4,"area":null},{"id":"2207.08185","title":"Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised Object Detection","created":"2022-07-17","cited_by_count":4,"area":null},{"id":"2209.12343","title":"Paraphrasing Is All You Need for Novel Object Captioning","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2210.11078","title":"Large-batch Optimization for Dense Visual Predictions","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2202.00866","title":"Decoupled IoU Regression for Object Detection","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2204.00794","title":"R(Det)^2: Randomized Decision Routing for Object Detection","created":"2022-04-02","cited_by_count":3,"area":null},{"id":"2208.08630","title":"Unifying Visual Perception by Dispersible Points Learning","created":"2022-08-18","cited_by_count":3,"area":null},{"id":"2209.10391","title":"IoU-Enhanced Attention for End-to-End Task Specific Object Detection","created":"2022-09-21","cited_by_count":3,"area":null},{"id":"2303.01047","title":"Task-Specific Context Decoupling for Object Detection","created":"2023-03-02","cited_by_count":3,"area":null},{"id":"2505.07040","title":"Differentiable NMS via Sinkhorn Matching for End-to-End Fabric Defect Detection","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2106.13933","title":"Inverting and Understanding Object Detectors","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2202.09048","title":"Task Specific Attention is one more thing you need for object detection","created":"2022-02-18","cited_by_count":2,"area":null},{"id":"2209.03157","title":"FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications","created":"2022-09-07","cited_by_count":2,"area":null},{"id":"2212.06335","title":"CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2309.00348","title":"MuraNet: Multi-task Floor Plan Recognition with Relation Attention","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2502.02850","title":"RS-YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images","created":"2025-02-05","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":"2110.14773","title":"SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation","created":"2021-10-27","cited_by_count":1,"area":null},{"id":"2111.13888","title":"Head and Body: Unified Detector and Graph Network for Person Search in Media","created":"2021-11-27","cited_by_count":1,"area":null},{"id":"2207.04693","title":"Exploring Contextual Relationships for Cervical Abnormal Cell Detection","created":"2022-07-11","cited_by_count":1,"area":null},{"id":"2208.04352","title":"Rethinking Robust Representation Learning Under Fine-grained Noisy Faces","created":"2022-08-08","cited_by_count":1,"area":null},{"id":"2301.12219","title":"Towards Accurate Acne Detection via Decoupled Sequential Detection Head","created":"2023-01-28","cited_by_count":1,"area":null},{"id":"2412.10453","title":"Analysis of Object Detection Models for Tiny Object in Satellite Imagery: A Dataset-Centric Approach","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2104.12245","title":"Single Stage Class Agnostic Common Object Detection: A Simple Baseline","created":"2021-04-25","cited_by_count":0,"area":null},{"id":"2104.14066","title":"Objects as Extreme Points","created":"2021-04-29","cited_by_count":0,"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":"2110.07994","title":"Pyramid Correlation based Deep Hough Voting for Visual Object Tracking","created":"2021-10-15","cited_by_count":0,"area":null},{"id":"2110.11894","title":"Towards Using Clothes Style Transfer for Scenario-aware Person Video Generation","created":"2021-10-14","cited_by_count":0,"area":null},{"id":"2110.12194","title":"RPT++: Customized Feature Representation for Siamese Visual Tracking","created":"2021-10-23","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":"2206.08227","title":"Delving into the Scale Variance Problem in Object Detection","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2207.11325","title":"PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation","created":"2022-07-22","cited_by_count":0,"area":null},{"id":"2209.02200","title":"Task-wise Sampling Convolutions for Arbitrary-Oriented Object Detection in Aerial Images","created":"2022-09-06","cited_by_count":0,"area":null},{"id":"2212.00313","title":"Concealed Object Detection for Passive Millimeter-Wave Security Imaging Based on Task-Aligned Detection Transformer","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2305.00620","title":"Refined Response Distillation for Class-Incremental Player Detection","created":"2023-05-01","cited_by_count":0,"area":null},{"id":"2306.05262","title":"EXOT: Exit-aware Object Tracker for Safe Robotic Manipulation of Moving Object","created":"2023-06-08","cited_by_count":0,"area":null},{"id":"2401.18032","title":"DROP: Decouple Re-Identification and Human Parsing with Task-specific Features for Occluded Person Re-identification","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2404.16633","title":"Self-Balanced R-CNN for Instance Segmentation","created":"2024-04-25","cited_by_count":0,"area":null},{"id":"2407.19698","title":"Classification Matters: Improving Video Action Detection with Class-Specific Attention","created":"2024-07-29","cited_by_count":0,"area":null},{"id":"2408.03559","title":"Enhanced hermit crabs detection using super-resolution reconstruction and improved YOLOv8 on UAV-captured imagery","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2506.08612","title":"Data-Efficient Challenges in Visual Inductive Priors: A Retrospective","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2508.11478","title":"TACR-YOLO: A Real-time Detection Framework for Abnormal Human Behaviors Enhanced with Coordinate and Task-Aware Representations","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2609.23061","title":"HDMamba-YOLO: Efficient State-Space Perception and Local Spatial Reconstruction for UAV Small Object","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}