{"total":430,"rows":[{"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":"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":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346,"area":null},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311,"area":null},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305,"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":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156,"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":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2104.09804","title":"SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud","created":"2021-04-20","cited_by_count":119,"area":null},{"id":"2205.07403","title":"PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection","created":"2022-05-16","cited_by_count":99,"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":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2204.01680","title":"TALLFormer: Temporal Action Localization with a Long-memory Transformer","created":"2022-04-04","cited_by_count":79,"area":null},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73,"area":null},{"id":"2403.19366","title":"Infrared Small Target Detection with Scale and Location Sensitivity","created":"2024-03-28","cited_by_count":73,"area":null},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68,"area":null},{"id":"2211.14317","title":"Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space","created":"2022-11-24","cited_by_count":66,"area":null},{"id":"2308.11062","title":"UnLoc: A Unified Framework for Video Localization Tasks","created":"2023-08-21","cited_by_count":66,"area":null},{"id":"2312.06505","title":"Grounded Question-Answering in Long Egocentric Videos","created":"2023-12-11","cited_by_count":64,"area":null},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62,"area":null},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57,"area":null},{"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,"area":null},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53,"area":null},{"id":"2205.12740","title":"SIoU Loss: More Powerful Learning for Bounding Box Regression","created":"2022-05-25","cited_by_count":49,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2203.04275","title":"Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap","created":"2022-03-08","cited_by_count":44,"area":null},{"id":"2312.08952","title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","created":"2023-12-14","cited_by_count":44,"area":null},{"id":"2302.02367","title":"FastPillars: A Deployment-friendly Pillar-based 3D Detector","created":"2023-02-05","cited_by_count":39,"area":null},{"id":"2107.02963","title":"Disentangle Your Dense Object Detector","created":"2021-07-07","cited_by_count":37,"area":null},{"id":"2209.10839","title":"Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization","created":"2022-09-22","cited_by_count":36,"area":null},{"id":"2404.02257","title":"SnAG: Scalable and Accurate Video Grounding","created":"2024-04-02","cited_by_count":36,"area":null},{"id":"2406.03459","title":"LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection","created":"2024-06-05","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":"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":"2301.10051","title":"Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism","created":"2023-01-24","cited_by_count":30,"area":null},{"id":"2306.13074","title":"Iterative Scale-Up ExpansionIoU and Deep Features Association for Multi-Object Tracking in Sports","created":"2023-06-22","cited_by_count":29,"area":null},{"id":"2205.02717","title":"BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection","created":"2022-05-05","cited_by_count":28,"area":null},{"id":"2303.09055","title":"TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization","created":"2023-03-16","cited_by_count":28,"area":null},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","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":"2404.01614","title":"LR-FPN: Enhancing Remote Sensing Object Detection with Location Refined Feature Pyramid Network","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27,"area":null},{"id":"2108.04602","title":"Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving","created":"2021-08-10","cited_by_count":26,"area":null},{"id":"2201.07425","title":"WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking","created":"2022-01-19","cited_by_count":26,"area":null},{"id":"2111.00902","title":"PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2205.14942","title":"Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles","created":"2022-05-30","cited_by_count":22,"area":null},{"id":"2108.12711","title":"Learning to Track Objects from Unlabeled Videos","created":"2021-08-28","cited_by_count":21,"area":null},{"id":"2102.04700","title":"Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search","created":"2021-02-09","cited_by_count":20,"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":"2202.04781","title":"Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios","created":"2022-02-10","cited_by_count":20,"area":null},{"id":"2202.05126","title":"Deep Learning for Computational Cytology: A Survey","created":"2022-02-10","cited_by_count":20,"area":null},{"id":"2205.11796","title":"G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection","created":"2022-05-24","cited_by_count":20,"area":null},{"id":"2103.14026","title":"AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks","created":"2021-03-25","cited_by_count":19,"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":"2303.11732","title":"Multi-modal Prompting for Low-Shot Temporal Action Localization","created":"2023-03-21","cited_by_count":19,"area":null},{"id":"2407.03197","title":"DyFADet: Dynamic Feature Aggregation for Temporal Action Detection","created":"2024-07-03","cited_by_count":19,"area":null},{"id":"2103.17242","title":"Dogfight: Detecting Drones from Drones Videos","created":"2021-03-31","cited_by_count":18,"area":null},{"id":"2106.06072","title":"Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection","created":"2021-06-10","cited_by_count":18,"area":null},{"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":"2112.03549","title":"GaTector: A Unified Framework for Gaze Object Prediction","created":"2021-12-07","cited_by_count":18,"area":null},{"id":"2202.13073","title":"Global Instance Tracking: Locating Target More Like Humans","created":"2022-02-26","cited_by_count":18,"area":null},{"id":"2206.06506","title":"Spiking Neural Networks for Frame-based and Event-based Single Object Localization","created":"2022-06-13","cited_by_count":18,"area":null},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18,"area":null},{"id":"2303.04995","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","created":"2023-03-09","cited_by_count":18,"area":null},{"id":"2305.08366","title":"CLRerNet: Improving Confidence of Lane Detection with LaneIoU","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2409.16149","title":"MCTrack: A Unified 3D Multi-Object Tracking Framework for Autonomous Driving","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2107.04362","title":"RGB Stream Is Enough for Temporal Action Detection","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2206.10255","title":"GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles","created":"2022-06-21","cited_by_count":15,"area":null},{"id":"2208.02019","title":"YOLO-FaceV2: A Scale and Occlusion Aware Face Detector","created":"2022-08-03","cited_by_count":15,"area":null},{"id":"2305.10061","title":"Rethinking Boundary Discontinuity Problem for Oriented Object Detection","created":"2023-05-17","cited_by_count":15,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"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":"2404.02405","title":"TE-TAD: Towards Full End-to-End Temporal Action Detection via Time-Aligned Coordinate Expression","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2304.05370","title":"Overload: Latency Attacks on Object Detection for Edge Devices","created":"2023-04-11","cited_by_count":13,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2403.12686","title":"WaterVG: Waterway Visual Grounding based on Text-Guided Vision and mmWave Radar","created":"2024-03-19","cited_by_count":13,"area":null},{"id":"2104.05215","title":"SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching","created":"2021-04-12","cited_by_count":12,"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":"2207.06985","title":"ObjectBox: From Centers to Boxes for Anchor-Free Object Detection","created":"2022-07-14","cited_by_count":12,"area":null},{"id":"2303.11630","title":"BoxSnake: Polygonal Instance Segmentation with Box Supervision","created":"2023-03-21","cited_by_count":12,"area":null},{"id":"2304.05071","title":"Fracture Detection in Pediatric Wrist Trauma X-ray Images Using YOLOv8 Algorithm","created":"2023-04-11","cited_by_count":12,"area":null},{"id":"2308.12111","title":"Cross-Modality Proposal-guided Feature Mining for Unregistered RGB-Thermal Pedestrian Detection","created":"2023-08-23","cited_by_count":12,"area":null},{"id":"2409.09953","title":"Uncertainty-Guided Appearance-Motion Association Network for Out-of-Distribution Action Detection","created":"2024-09-16","cited_by_count":12,"area":null},{"id":"2411.10193","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2112.08782","title":"Improved YOLOv5 network for real-time multi-scale traffic sign detection","created":"2021-12-16","cited_by_count":11,"area":null},{"id":"2205.02958","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","created":"2022-05-05","cited_by_count":11,"area":null},{"id":"2312.06458","title":"ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance Segmentation","created":"2023-12-11","cited_by_count":11,"area":null},{"id":"2312.13641","title":"SPGroup3D: Superpoint Grouping Network for Indoor 3D Object Detection","created":"2023-12-21","cited_by_count":11,"area":null},{"id":"2404.06180","title":"YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2503.12888","title":"UncTrack: Reliable Visual Object Tracking with Uncertainty-Aware Prototype Memory Network","created":"2025-03-17","cited_by_count":11,"area":null},{"id":"2505.04270","title":"Object-Shot Enhanced Grounding Network for Egocentric Video","created":"2025-05-07","cited_by_count":11,"area":null},{"id":"2111.09460","title":"Large-scale Building Height Retrieval from Single SAR Imagery based on Bounding Box Regression Networks","created":"2021-11-18","cited_by_count":10,"area":null}],"next_cursor":"100"}