{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"1807.06521","title":"CBAM: Convolutional Block Attention Module","created":"2018-07-17","cited_by_count":2477},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"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":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"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":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"1406.4729","title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","created":"2014-06-18","cited_by_count":720},{"id":"2107.00652","title":"CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows","created":"2021-07-01","cited_by_count":527},{"id":"2203.01305","title":"DN-DETR: Accelerate DETR Training by Introducing Query DeNoising","created":"2022-03-02","cited_by_count":488},{"id":"1911.08287","title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","created":"2019-11-19","cited_by_count":459},{"id":"1704.04503","title":"Soft-NMS -- Improving Object Detection With One Line of Code","created":"2017-04-14","cited_by_count":382},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354},{"id":"2103.02907","title":"Coordinate Attention for Efficient Mobile Network Design","created":"2021-03-04","cited_by_count":241},{"id":"2006.02334","title":"DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution","created":"2020-06-03","cited_by_count":222},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218},{"id":"1802.07856","title":"xView: Objects in Context in Overhead Imagery","created":"2018-02-22","cited_by_count":146},{"id":"2311.11810","title":"DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding","created":"2023-11-20","cited_by_count":106},{"id":"2202.06934","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","created":"2022-02-14","cited_by_count":105},{"id":"2005.03572","title":"Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation","created":"2020-05-07","cited_by_count":98},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93},{"id":"1904.08008","title":"Clustered Object Detection in Aerial Images","created":"2019-04-16","cited_by_count":83},{"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},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"1902.07296","title":"Augmentation for small object detection","created":"2019-02-19","cited_by_count":73},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71},{"id":"2301.01635","title":"SPTS v2: Single-Point Scene Text Spotting","created":"2023-01-04","cited_by_count":66},{"id":"2203.15221","title":"Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection","created":"2022-03-29","cited_by_count":65},{"id":"2404.12803","title":"TextSquare: Scaling up Text-Centric Visual Instruction Tuning","created":"2024-04-19","cited_by_count":62},{"id":"2301.05586","title":"YOLOv6 v3.0: A Full-Scale Reloading","created":"2023-01-13","cited_by_count":58},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57},{"id":"2004.05520","title":"Density Map Guided Object Detection in Aerial Images","created":"2020-04-12","cited_by_count":56},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54},{"id":"2110.13389","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","created":"2021-10-26","cited_by_count":53},{"id":"2311.13120","title":"Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer","created":"2023-11-22","cited_by_count":53},{"id":"1704.03414","title":"A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection","created":"2017-04-11","cited_by_count":43},{"id":"2408.12928","title":"ParGo: Bridging Vision-Language with Partial and Global Views","created":"2024-08-23","cited_by_count":40},{"id":"2204.03245","title":"HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detection","created":"2022-04-07","cited_by_count":34},{"id":"2207.11934","title":"Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning","created":"2022-07-25","cited_by_count":33},{"id":"2410.11538","title":"MCTBench: Multimodal Cognition towards Text-Rich Visual Scenes Benchmark","created":"2024-10-15","cited_by_count":26},{"id":"2505.11015","title":"WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild?","created":"2025-05-16","cited_by_count":26},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22},{"id":"2203.12976","title":"Focus-and-Detect: A Small Object Detection Framework for Aerial Images","created":"2022-03-24","cited_by_count":19},{"id":"1902.09080","title":"SSA-CNN: Semantic Self-Attention CNN for Pedestrian Detection","created":"2019-02-25","cited_by_count":6}],"next_cursor":null}