{"total":231,"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":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"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":"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":"2103.10039","title":"RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection","created":"2021-03-18","cited_by_count":140,"area":null},{"id":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127,"area":null},{"id":"2112.00995","title":"SwinTrack: A Simple and Strong Baseline for Transformer Tracking","created":"2021-12-02","cited_by_count":126,"area":null},{"id":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105,"area":null},{"id":"2112.09205","title":"AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds","created":"2021-12-16","cited_by_count":88,"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":"2201.01501","title":"Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation","created":"2022-01-05","cited_by_count":82,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70,"area":null},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68,"area":null},{"id":"2102.12252","title":"Localization Distillation for Dense Object Detection","created":"2021-02-24","cited_by_count":55,"area":"distill"},{"id":"2203.16317","title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","created":"2022-03-30","cited_by_count":51,"area":null},{"id":"2310.08854","title":"Rank-DETR for High Quality Object Detection","created":"2023-10-13","cited_by_count":50,"area":null},{"id":"2112.04840","title":"Knowledge Distillation for Object Detection via Rank Mimicking and Prediction-guided Feature Imitation","created":"2021-12-09","cited_by_count":40,"area":"distill"},{"id":"2309.08816","title":"EgoObjects: A Large-Scale Egocentric Dataset for Fine-Grained Object Understanding","created":"2023-09-15","cited_by_count":40,"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":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2207.00141","title":"A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos","created":"2022-07-01","cited_by_count":32,"area":null},{"id":"2301.12689","title":"Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2403.00326","title":"DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2407.11699","title":"Relation DETR: Exploring Explicit Position Relation Prior for Object Detection","created":"2024-07-16","cited_by_count":28,"area":null},{"id":"2302.13840","title":"Target-Aware Tracking with Long-term Context Attention","created":"2023-02-27","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":"2203.09730","title":"A Dual Weighting Label Assignment Scheme for Object Detection","created":"2022-03-18","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":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2311.04894","title":"DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets","created":"2023-11-08","cited_by_count":23,"area":"moe"},{"id":"2401.13554","title":"PanAf20K: A Large Video Dataset for Wild Ape Detection and Behaviour Recognition","created":"2024-01-24","cited_by_count":22,"area":null},{"id":"2204.02620","title":"Towards Robust Adaptive Object Detection under Noisy Annotations","created":"2022-04-06","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":"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":"2212.07593","title":"Enhanced Training of Query-Based Object Detection via Selective Query Recollection","created":"2022-12-15","cited_by_count":18,"area":null},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17,"area":"moe"},{"id":"2412.16955","title":"NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors","created":"2024-12-22","cited_by_count":17,"area":null},{"id":"2211.13508","title":"1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results","created":"2022-11-24","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":"2203.05469","title":"Prediction-Guided Distillation for Dense Object Detection","created":"2022-03-10","cited_by_count":14,"area":"distill"},{"id":"2303.14960","title":"Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection","created":"2023-03-27","cited_by_count":14,"area":null},{"id":"2301.09724","title":"Long-tail Detection with Effective Class-Margins","created":"2023-01-23","cited_by_count":13,"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":"2104.02230","title":"Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning","created":"2021-04-06","cited_by_count":12,"area":null},{"id":"2111.04885","title":"Lymph Node Detection in T2 MRI with Transformers","created":"2021-11-09","cited_by_count":12,"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":"2207.06985","title":"ObjectBox: From Centers to Boxes for Anchor-Free Object Detection","created":"2022-07-14","cited_by_count":12,"area":null},{"id":"2304.04248","title":"Curricular Object Manipulation in LiDAR-based Object Detection","created":"2023-04-09","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":"2203.14438","title":"Optimal Correction Cost for Object Detection Evaluation","created":"2022-03-28","cited_by_count":11,"area":null},{"id":"2210.16467","title":"ImplantFormer: Vision Transformer based Implant Position Regression Using Dental CBCT Data","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2305.10044","title":"Two-Stream Regression Network for Dental Implant Position Prediction","created":"2023-05-17","cited_by_count":11,"area":null},{"id":"2306.14406","title":"TCEIP: Text Condition Embedded Regression Network for Dental Implant Position Prediction","created":"2023-06-26","cited_by_count":11,"area":null},{"id":"2405.20459","title":"On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines","created":"2024-05-30","cited_by_count":11,"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":"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":"2109.05986","title":"Mutual Supervision for Dense Object Detection","created":"2021-09-13","cited_by_count":10,"area":null},{"id":"2201.11620","title":"Domain generalization in deep learning-based mass detection in mammography: A large-scale multi-center study","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2203.15353","title":"SIOD: Single Instance Annotated Per Category Per Image for Object Detection","created":"2022-03-29","cited_by_count":10,"area":null},{"id":"2205.11761","title":"Ranking-Based Siamese Visual Tracking","created":"2022-05-24","cited_by_count":10,"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":"2407.20078","title":"Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection","created":"2024-07-29","cited_by_count":9,"area":null},{"id":"2111.04886","title":"Universal Lesion Detection in CT Scans using Neural Network Ensembles","created":"2021-11-09","cited_by_count":8,"area":null},{"id":"2203.07973","title":"MOBDrone: a Drone Video Dataset for Man OverBoard Rescue","created":"2022-03-15","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":"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":"2402.08017","title":"Lumos : Empowering Multimodal LLMs with Scene Text Recognition","created":"2024-02-12","cited_by_count":8,"area":"mllm"},{"id":"2406.02833","title":"DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2503.21659","title":"InteractionMap: Improving Online Vectorized HDMap Construction with Interaction","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2108.04584","title":"UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks","created":"2021-08-10","cited_by_count":7,"area":null},{"id":"2110.01025","title":"DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images","created":"2021-10-03","cited_by_count":7,"area":null},{"id":"2206.12128","title":"Excavating RoI Attention for Underwater Object Detection","created":"2022-06-24","cited_by_count":7,"area":null},{"id":"2211.08248","title":"3D Cascade RCNN: High Quality Object Detection in Point Clouds","created":"2022-11-15","cited_by_count":7,"area":null},{"id":"2302.13519","title":"CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World","created":"2023-02-27","cited_by_count":7,"area":null},{"id":"2308.05355","title":"TCSloT: Text Guided 3D Context and Slope Aware Triple Network for Dental Implant Position Prediction","created":"2023-08-10","cited_by_count":7,"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":"2310.13215","title":"Zone Evaluation: Revealing Spatial Bias in Object Detection","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2311.14762","title":"The 2nd Workshop on Maritime Computer Vision (MaCVi) 2024","created":"2023-11-23","cited_by_count":7,"area":null},{"id":"2402.07677","title":"GBOT: Graph-Based 3D Object Tracking for Augmented Reality-Assisted Assembly Guidance","created":"2024-02-12","cited_by_count":7,"area":null},{"id":"2406.03095","title":"EgoSurgery-Tool: A Dataset of Surgical Tool and Hand Detection from Egocentric Open Surgery Videos","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2407.04305","title":"Towards Stable 3D Object Detection","created":"2024-07-05","cited_by_count":7,"area":null},{"id":"2110.15045","title":"LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image","created":"2021-10-28","cited_by_count":6,"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":"2409.06259","title":"ALSS-YOLO: An Adaptive Lightweight Channel Split and Shuffling Network for TIR Wildlife Detection in UAV Imagery","created":"2024-09-10","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":"2102.12808","title":"SCD: A Stacked Carton Dataset for Detection and Segmentation","created":"2021-02-25","cited_by_count":5,"area":null},{"id":"2112.09569","title":"CPPE-5: Medical Personal Protective Equipment Dataset","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2112.13608","title":"An Empirical Study of Adder Neural Networks for Object Detection","created":"2021-12-27","cited_by_count":5,"area":null},{"id":"2204.00622","title":"Universal Lymph Node Detection in T2 MRI using Neural Networks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2204.08745","title":"Augmentation of Atmospheric Turbulence Effects on Thermal Adapted Object Detection Models","created":"2022-04-19","cited_by_count":5,"area":null},{"id":"2304.05417","title":"The MONET dataset: Multimodal drone thermal dataset recorded in rural scenarios","created":"2023-04-11","cited_by_count":5,"area":null},{"id":"2304.07527","title":"Align-DETR: Enhancing End-to-end Object Detection with Aligned Loss","created":"2023-04-15","cited_by_count":5,"area":null},{"id":"2305.00675","title":"End-to-End Lane detection with One-to-Several Transformer","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2306.12111","title":"A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking","created":"2023-06-21","cited_by_count":5,"area":null},{"id":"2309.04702","title":"A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos","created":"2023-09-09","cited_by_count":5,"area":null},{"id":"2311.10437","title":"DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection","created":"2023-11-17","cited_by_count":5,"area":null}],"next_cursor":"100"}