{"list":"other","total":71,"rows":[{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1512.02325","title":"SSD: Single Shot MultiBox Detector","created":"2015-12-08","cited_by_count":3130},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"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},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"1904.08189","title":"CenterNet: Keypoint Triplets for Object Detection","created":"2019-04-17","cited_by_count":654},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"2201.12329","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","created":"2022-01-28","cited_by_count":573},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1804.06208","title":"Simple Baselines for Human Pose Estimation and Tracking","created":"2018-04-17","cited_by_count":502},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"2204.12484","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","created":"2022-04-26","cited_by_count":456},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428},{"id":"2402.13616","title":"YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information","created":"2024-02-21","cited_by_count":425},{"id":"2006.04388","title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","created":"2020-06-08","cited_by_count":409},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"1312.4659","title":"DeepPose: Human Pose Estimation via Deep Neural Networks","created":"2013-12-17","cited_by_count":305},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2502.12524","title":"YOLOv12: Attention-Centric Real-Time Object Detectors","created":"2025-02-18","cited_by_count":305},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"id":"2307.04767","title":"Semantic-SAM: Segment and Recognize Anything at Any Granularity","created":"2023-07-10","cited_by_count":185},{"id":"1703.01086","title":"Arbitrary-Oriented Scene Text Detection via Rotation Proposals","created":"2017-03-03","cited_by_count":176},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150},{"id":"2107.11291","title":"Human Pose Regression with Residual Log-likelihood Estimation","created":"2021-07-23","cited_by_count":131},{"id":"2405.10300","title":"Grounding DINO 1.5: Advance the \"Edge\" of Open-Set Object Detection","created":"2024-05-16","cited_by_count":122},{"id":"2212.00280","title":"GRiT: A Generative Region-to-text Transformer for Object Understanding","created":"2022-12-01","cited_by_count":121},{"id":"2204.13317","title":"MMRotate: A Rotated Object Detection Benchmark using PyTorch","created":"2022-04-28","cited_by_count":115},{"id":"2207.13085","title":"Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment","created":"2022-07-26","cited_by_count":98},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96},{"id":"2403.14610","title":"T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy","created":"2024-03-21","cited_by_count":94},{"id":"2407.17140","title":"RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformer","created":"2024-07-24","cited_by_count":91},{"id":"2511.09554","title":"RF-DETR: Neural Architecture Search for Real-Time Detection Transformers","created":"2025-11-12","cited_by_count":75},{"id":"2410.13842","title":"D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement","created":"2024-10-17","cited_by_count":74},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73},{"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},{"id":"2412.04234","title":"DEIM: DETR with Improved Matching for Fast Convergence","created":"2024-12-05","cited_by_count":68},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2311.13601","title":"Visual In-Context Prompting","created":"2023-11-22","cited_by_count":52},{"id":"2404.09216","title":"DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection","created":"2024-04-14","cited_by_count":48},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44},{"id":"2211.06368","title":"Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection","created":"2022-11-11","cited_by_count":43},{"id":"2403.10191","title":"Generative Region-Language Pretraining for Open-Ended Object Detection","created":"2024-03-15","cited_by_count":29},{"id":"2509.20787","title":"Real-Time Object Detection Meets DINOv3","created":"2025-09-25","cited_by_count":27},{"id":"2508.20691","title":"MobileCLIP2: Improving Multi-Modal Reinforced Training","created":"2025-08-28","cited_by_count":21},{"id":"2510.25257","title":"RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models","created":"2025-10-29","cited_by_count":15},{"id":"2412.20645","title":"YOLO-UniOW: Efficient Universal Open-World Object Detection","created":"2024-12-30","cited_by_count":9}],"next_cursor":null}