{"total":32,"rows":[{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2404.11335","title":"SoccerNet Game State Reconstruction: End-to-End Athlete Tracking and Identification on a Minimap","created":"2024-04-17","cited_by_count":34,"area":null},{"id":"2110.12826","title":"TPSNet: Reverse Thinking of Thin Plate Splines for Arbitrary Shape Scene Text Representation","created":"2021-10-25","cited_by_count":26,"area":null},{"id":"2411.05383","title":"Towards Low-Resource Harmful Meme Detection with LMM Agents","created":"2024-11-08","cited_by_count":24,"area":null},{"id":"2307.12270","title":"Context Perception Parallel Decoder for Scene Text Recognition","created":"2023-07-23","cited_by_count":19,"area":null},{"id":"2401.13298","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","created":"2024-01-24","cited_by_count":18,"area":null},{"id":"2207.01342","title":"Explore Faster Localization Learning For Scene Text Detection","created":"2022-07-04","cited_by_count":10,"area":null},{"id":"2210.07903","title":"Text Detection Forgot About Document OCR","created":"2022-10-14","cited_by_count":5,"area":null},{"id":"2403.10047","title":"TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model","created":"2024-03-15","cited_by_count":5,"area":null},{"id":"2404.18722","title":"Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library","created":"2024-04-29","cited_by_count":5,"area":null},{"id":"2212.14674","title":"A Comprehensive Gold Standard and Benchmark for Comics Text Detection and Recognition","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2503.18282","title":"TrackID3x3: A Dataset and Algorithm for Multi-Player Tracking with Identification and Pose Estimation in 3x3 Basketball Full-court Videos","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2508.10582","title":"EvTurb: Event Camera Guided Turbulence Removal","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2204.00298","title":"Unitail: Detecting, Reading, and Matching in Retail Scene","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2208.06031","title":"Handling big tabular data of ICT supply chains: a multi-task, machine-interpretable approach","created":"2022-08-11","cited_by_count":2,"area":null},{"id":"2209.00859","title":"Vision-Language Adaptive Mutual Decoder for OOV-STR","created":"2022-09-02","cited_by_count":2,"area":null},{"id":"2405.11437","title":"The First Swahili Language Scene Text Detection and Recognition Dataset","created":"2024-05-19","cited_by_count":2,"area":null},{"id":"2406.15485","title":"SegHist: A General Segmentation-based Framework for Chinese Historical Document Text Line Detection","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2503.15887","title":"DocVideoQA: Towards Comprehensive Understanding of Document-Centric Videos through Question Answering","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2110.05700","title":"On Exploring and Improving Robustness of Scene Text Detection Models","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2306.03482","title":"Looking and Listening: Audio Guided Text Recognition","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2312.00699","title":"Rethinking Detection Based Table Structure Recognition for Visually Rich Document Images","created":"2023-12-01","cited_by_count":1,"area":null},{"id":"2312.13778","title":"Progressive Evolution from Single-Point to Polygon for Scene Text","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2409.18101","title":"AI-Powered Augmented Reality for Satellite Assembly, Integration and Test","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2509.03615","title":"E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2210.02576","title":"Reading Chinese in Natural Scenes with a Bag-of-Radicals Prior","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2307.15029","title":"Adaptive Segmentation Network for Scene Text Detection","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2404.08785","title":"Under pressure: learning-based analog gauge reading in the wild","created":"2024-04-12","cited_by_count":0,"area":null},{"id":"2408.12870","title":"Can AI Assistance Aid in the Grading of Handwritten Answer Sheets?","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2412.14969","title":"PhotoHolmes: a Python library for forgery detection in digital images","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2412.18505","title":"VORTEX: A Spatial Computing Framework for Optimized Drone Telemetry Extraction from First-Person View Flight Data","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2608.27923","title":"PCBnet: A Dataset and Automatic Construction of SPICE Netlists from Schematic Images","created":"2026-08-28","cited_by_count":0,"area":null}],"next_cursor":null}