{"total":207,"rows":[{"id":"2107.08430","title":"YOLOX: Exceeding YOLO Series in 2021","created":"2021-07-18","cited_by_count":1071,"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":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"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":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170,"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":"2206.08171","title":"K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions","created":"2022-06-16","cited_by_count":108,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2205.01491","title":"A Comprehensive Survey of Image Augmentation Techniques for Deep Learning","created":"2022-05-03","cited_by_count":97,"area":null},{"id":"2106.05786","title":"CAT: Cross Attention in Vision Transformer","created":"2021-06-10","cited_by_count":92,"area":null},{"id":"2105.04206","title":"You Only Learn One Representation: Unified Network for Multiple Tasks","created":"2021-05-10","cited_by_count":86,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2107.00420","title":"CBNet: A Composite Backbone Network Architecture for Object Detection","created":"2021-07-01","cited_by_count":77,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2107.12283","title":"Continental-Scale Building Detection from High Resolution Satellite Imagery","created":"2021-07-26","cited_by_count":50,"area":null},{"id":"2202.11983","title":"GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021","created":"2022-02-24","cited_by_count":46,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"area":null},{"id":"2108.04814","title":"R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes","created":"2021-08-10","cited_by_count":36,"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":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"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":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2104.10419","title":"PP-YOLOv2: A Practical Object Detector","created":"2021-04-21","cited_by_count":30,"area":null},{"id":"2102.02956","title":"DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks","created":"2021-02-05","cited_by_count":29,"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":"2205.13618","title":"Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectors","created":"2022-05-26","cited_by_count":28,"area":null},{"id":"2205.14550","title":"Machine Learning for Microcontroller-Class Hardware: A Review","created":"2022-05-29","cited_by_count":28,"area":null},{"id":"2208.03641","title":"No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects","created":"2022-08-07","cited_by_count":27,"area":null},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"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":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2204.10380","title":"The 6th AI City Challenge","created":"2022-04-21","cited_by_count":23,"area":null},{"id":"2111.08557","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","created":"2021-11-16","cited_by_count":20,"area":null},{"id":"2105.13965","title":"Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulation","created":"2021-05-28","cited_by_count":19,"area":null},{"id":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18,"area":null},{"id":"2206.08304","title":"Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey","created":"2022-06-16","cited_by_count":17,"area":null},{"id":"2203.07808","title":"Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNs","created":"2022-03-15","cited_by_count":16,"area":null},{"id":"2304.05552","title":"DynamicDet: A Unified Dynamic Architecture for Object Detection","created":"2023-04-12","cited_by_count":15,"area":null},{"id":"2305.01074","title":"Physical Adversarial Attacks for Surveillance: A Survey","created":"2023-05-01","cited_by_count":15,"area":null},{"id":"2407.16424","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2110.07641","title":"Non-deep Networks","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2310.01641","title":"You Only Look at Once for Real-time and Generic Multi-Task","created":"2023-10-02","cited_by_count":14,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2211.14125","title":"PoET: Pose Estimation Transformer for Single-View, Multi-Object 6D Pose Estimation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2110.13713","title":"YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs","created":"2021-10-26","cited_by_count":12,"area":null},{"id":"2205.08099","title":"Dimensionality Reduced Training by Pruning and Freezing Parts of a Deep Neural Network, a Survey","created":"2022-05-17","cited_by_count":12,"area":null},{"id":"2111.03281","title":"Recognizing Vector Graphics without Rasterization","created":"2021-11-05","cited_by_count":11,"area":null},{"id":"2205.03582","title":"Unified Chinese License Plate Detection and Recognition with High Efficiency","created":"2022-05-07","cited_by_count":11,"area":null},{"id":"2202.13096","title":"Continuous Human Action Recognition for Human-Machine Interaction: A Review","created":"2022-02-26","cited_by_count":10,"area":null},{"id":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","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":"2303.11923","title":"Performance-aware Approximation of Global Channel Pruning for Multitask CNNs","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2308.04054","title":"An Empirical Analysis of Range for 3D Object Detection","created":"2023-08-08","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":"2105.06808","title":"Waste detection in Pomerania: non-profit project for detecting waste in environment","created":"2021-05-12","cited_by_count":8,"area":null},{"id":"2307.09143","title":"MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results","created":"2023-07-18","cited_by_count":8,"area":null},{"id":"2109.08880","title":"Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision","created":"2021-09-18","cited_by_count":7,"area":null},{"id":"2202.10881","title":"Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Tracking","created":"2022-02-22","cited_by_count":7,"area":null},{"id":"2203.10747","title":"EAutoDet: Efficient Architecture Search for Object Detection","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2208.03727","title":"Robust Multi-Object Tracking by Marginal Inference","created":"2022-08-07","cited_by_count":7,"area":null},{"id":"2210.04024","title":"Demand Layering for Real-Time DNN Inference with Minimized Memory Usage","created":"2022-10-08","cited_by_count":7,"area":null},{"id":"2210.16574","title":"Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervision","created":"2022-10-29","cited_by_count":7,"area":null},{"id":"2304.02101","title":"MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations","created":"2023-04-04","cited_by_count":7,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2601.07671","title":"Advancing Multinational License Plate Recognition Through Synthetic and Real Data Fusion: A Comprehensive Evaluation","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2103.04580","title":"Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2106.05261","title":"We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2312.10930","title":"Deep Learning Approaches for Seizure Video Analysis: A Review","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2312.11973","title":"Continual Learning: Forget-free Winning Subnetworks for Video Representations","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2106.05665","title":"Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception","created":"2021-06-10","cited_by_count":5,"area":null},{"id":"2209.13933","title":"DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2312.15219","title":"Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery","created":"2023-12-23","cited_by_count":5,"area":null},{"id":"2312.16438","title":"Visual Spatial Attention and Proprioceptive Data-Driven Reinforcement Learning for Robust Peg-in-Hole Task Under Variable Conditions","created":"2023-12-27","cited_by_count":5,"area":null},{"id":"2407.19650","title":"Practical Video Object Detection via Feature Selection and Aggregation","created":"2024-07-29","cited_by_count":5,"area":null},{"id":"2410.22952","title":"Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2104.00462","title":"SCALoss: Side and Corner Aligned Loss for Bounding Box Regression","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2205.07085","title":"Monitoring of Pigmented Skin Lesions Using 3D Whole Body Imaging","created":"2022-05-14","cited_by_count":4,"area":null},{"id":"2206.03943","title":"Robust Environment Perception for Automated Driving: A Unified Learning Pipeline for Visual-Infrared Object Detection","created":"2022-06-08","cited_by_count":4,"area":null},{"id":"2305.04170","title":"YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidification","created":"2023-05-07","cited_by_count":4,"area":null},{"id":"2410.16769","title":"DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2411.12943","title":"Enhancing Thermal MOT: A Novel Box Association Method Leveraging Thermal Identity and Motion Similarity","created":"2024-11-20","cited_by_count":4,"area":null},{"id":"2412.14790","title":"YOLOv11 Optimization for Efficient Resource Utilization","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2201.03246","title":"Vision in adverse weather: Augmentation using CycleGANs with various object detectors for robust perception in autonomous racing","created":"2022-01-10","cited_by_count":3,"area":null},{"id":"2202.11490","title":"Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2206.12912","title":"Woodscape Fisheye Object Detection for Autonomous Driving -- CVPR 2022 OmniCV Workshop Challenge","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2301.01441","title":"Automatically Prepare Training Data for YOLO Using Robotic In-Hand Observation and Synthesis","created":"2023-01-04","cited_by_count":3,"area":null},{"id":"2302.06821","title":"Model-Based Underwater 6D Pose Estimation from RGB","created":"2023-02-14","cited_by_count":3,"area":null},{"id":"2303.11267","title":"Rethinking the backbone architecture for tiny object detection","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2401.06374","title":"SamLP: A Customized Segment Anything Model for License Plate Detection","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2405.11677","title":"Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometries","created":"2024-05-19","cited_by_count":3,"area":null},{"id":"2411.02794","title":"Real-Time Text Detection with Similar Mask in Traffic, Industrial, and Natural Scenes","created":"2024-11-05","cited_by_count":3,"area":null},{"id":"2504.18586","title":"A Decade of You Only Look Once (YOLO) for Object Detection: A Review","created":"2025-04-24","cited_by_count":3,"area":null},{"id":"2601.18597","title":"EFSI-DETR: Efficient Frequency-Semantic Integration for Real-Time Small Object Detection in UAV Imagery","created":"2026-01-26","cited_by_count":3,"area":null}],"next_cursor":"100"}