{"total":60,"rows":[{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220,"area":null},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114,"area":null},{"id":"2405.11985","title":"MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering","created":"2024-05-20","cited_by_count":93,"area":null},{"id":"2505.14059","title":"Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting","created":"2025-05-20","cited_by_count":79,"area":null},{"id":"2406.01326","title":"TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy","created":"2024-06-03","cited_by_count":71,"area":null},{"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,"area":null},{"id":"2407.16364","title":"Harmonizing Visual Text Comprehension and Generation","created":"2024-07-23","cited_by_count":54,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2409.05137","title":"READoc: A Unified Benchmark for Realistic Document Structured Extraction","created":"2024-09-08","cited_by_count":15,"area":null},{"id":"2412.15678","title":"Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2504.02454","title":"Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation","created":"2025-04-03","cited_by_count":14,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2501.15415","title":"OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery","created":"2025-01-26","cited_by_count":8,"area":null},{"id":"2507.09861","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","created":"2025-07-14","cited_by_count":8,"area":null},{"id":"2409.03365","title":"Spindle: Efficient Distributed Training of Multi-Task Large Models via Wavefront Scheduling","created":"2024-09-05","cited_by_count":7,"area":null},{"id":"2408.00441","title":"Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2408.06345","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2512.20174","title":"Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2501.02235","title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","created":"2025-01-04","cited_by_count":4,"area":null},{"id":"2502.16976","title":"Task-Oriented 6-DoF Grasp Pose Detection in Clutters","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2504.04085","title":"DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning","created":"2025-04-05","cited_by_count":4,"area":null},{"id":"2601.12318","title":"Beyond Human Annotation: Recent Advances in Data Generation Methods for Document Intelligence","created":"2026-01-18","cited_by_count":4,"area":null},{"id":"2407.19178","title":"Power-LLaVA: Large Language and Vision Assistant for Power Transmission Line Inspection","created":"2024-07-27","cited_by_count":3,"area":null},{"id":"2408.04632","title":"Arctic-TILT. Business Document Understanding at Sub-Billion Scale","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2505.05446","title":"Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2507.00430","title":"MFH: Marrying Frequency Domain with Handwritten Mathematical Expression Recognition","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2412.19504","title":"Hear the Scene: Audio-Enhanced Text Spotting","created":"2024-12-27","cited_by_count":0,"area":null},{"id":"2501.02811","title":"First-place Solution for Streetscape Shop Sign Recognition Competition","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2502.00665","title":"Cross-Modal Synergies: Unveiling the Potential of Motion-Aware Fusion Networks in Handling Dynamic and Static ReID Scenarios","created":"2025-02-02","cited_by_count":0,"area":null},{"id":"2505.06038","title":"Document Image Rectification Bases on Self-Adaptive Multitask Fusion","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2507.08492","title":"D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2509.23273","title":"SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction","created":"2025-09-27","cited_by_count":0,"area":null},{"id":"2511.23150","title":"Cascaded Robust Rectification for Arbitrary Document Images","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.09118","title":"LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.20881","title":"MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.15903","title":"Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2603.00118","title":"Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.13429","title":"A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.26766","title":"JND-Guided Neural Watermarking with Spatial Transformer Decoding for Screen-Capture Robustness","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2603.29507","title":"Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.03339","title":"Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.19233","title":"Adaptive Slicing-Assisted Hyper Inference for Enhanced Small Object Detection in High-Resolution Imagery","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.19259","title":"Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.25178","title":"Lightweight Real-Time Rendering Parameter Optimization via XGBoost-Driven Lookup Tables","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2604.25188","title":"Image Classification via Random Dilated Convolution with Multi-Branch Feature Extraction and Context Excitation","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2604.27353","title":"Gait Recognition via Deep Residual Networks and Multi-Branch Feature Fusion","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.00885","title":"Multi-Branch Non-Homogeneous Image Dehazing via Concentration Partitioning and Image Fusion","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.14548","title":"Local Spatiotemporal Convolutional Network for Robust Gait Recognition","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.18173","title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.01602","title":"ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2609.13706","title":"Rank-Consistent Set Reasoning for Co-Salient Object Detection","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.14383","title":"Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}