{"total":91,"rows":[{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195,"area":null},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171,"area":null},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151,"area":null},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124,"area":null},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97,"area":null},{"id":"2104.11896","title":"M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers","created":"2021-04-24","cited_by_count":74,"area":null},{"id":"2112.12494","title":"LaTr: Layout-Aware Transformer for Scene-Text VQA","created":"2021-12-23","cited_by_count":72,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2205.08303","title":"MulT: An End-to-End Multitask Learning Transformer","created":"2022-05-17","cited_by_count":48,"area":null},{"id":"2306.01733","title":"DocFormerv2: Local Features for Document Understanding","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2107.05214","title":"Split, embed and merge: An accurate table structure recognizer","created":"2021-07-12","cited_by_count":42,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2208.12037","title":"Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task","created":"2022-08-24","cited_by_count":35,"area":null},{"id":"2111.15263","title":"Multi-modal Text Recognition Networks: Interactive Enhancements between Visual and Semantic Features","created":"2021-11-30","cited_by_count":34,"area":null},{"id":"2201.09168","title":"Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval","created":"2022-01-23","cited_by_count":34,"area":null},{"id":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29,"area":null},{"id":"2304.06447","title":"PDFVQA: A New Dataset for Real-World VQA on PDF Documents","created":"2023-04-13","cited_by_count":28,"area":null},{"id":"2209.05534","title":"PreSTU: Pre-Training for Scene-Text Understanding","created":"2022-09-12","cited_by_count":27,"area":null},{"id":"2112.05692","title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling","created":"2021-12-10","cited_by_count":26,"area":null},{"id":"2105.03236","title":"Towards Accurate Text-based Image Captioning with Content Diversity Exploration","created":"2021-04-23","cited_by_count":25,"area":null},{"id":"2306.03491","title":"SciCap+: A Knowledge Augmented Dataset to Study the Challenges of Scientific Figure Captioning","created":"2023-06-06","cited_by_count":24,"area":null},{"id":"2307.03948","title":"Reading Between the Lanes: Text VideoQA on the Road","created":"2023-07-08","cited_by_count":23,"area":null},{"id":"2307.16226","title":"ScribbleVC: Scribble-supervised Medical Image Segmentation with Vision-Class Embedding","created":"2023-07-30","cited_by_count":23,"area":null},{"id":"2105.04836","title":"Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules","created":"2021-05-11","cited_by_count":22,"area":null},{"id":"2303.01903","title":"Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering","created":"2023-03-03","cited_by_count":21,"area":null},{"id":"2305.11033","title":"Visual Question Answering: A Survey on Techniques and Common Trends in Recent Literature","created":"2023-05-18","cited_by_count":21,"area":null},{"id":"2305.04183","title":"OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese","created":"2023-05-07","cited_by_count":20,"area":null},{"id":"2407.16993","title":"LoFormer: Local Frequency Transformer for Image Deblurring","created":"2024-07-24","cited_by_count":20,"area":null},{"id":"2111.05547","title":"ICDAR 2021 Competition on Document VisualQuestion Answering","created":"2021-11-10","cited_by_count":19,"area":null},{"id":"2106.04630","title":"PAM: Understanding Product Images in Cross Product Category Attribute Extraction","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2307.07929","title":"DocTr: Document Transformer for Structured Information Extraction in Documents","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17,"area":null},{"id":"2212.01803","title":"Controllable Image Captioning via Prompting","created":"2022-12-04","cited_by_count":15,"area":null},{"id":"2301.07389","title":"Towards Models that Can See and Read","created":"2023-01-18","cited_by_count":15,"area":null},{"id":"2105.02626","title":"A First Look: Towards Explainable TextVQA Models via Visual and Textual Explanations","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2108.08965","title":"Localize, Group, and Select: Boosting Text-VQA by Scene Text Modeling","created":"2021-08-20","cited_by_count":14,"area":null},{"id":"2207.04675","title":"COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts","created":"2022-07-11","cited_by_count":13,"area":null},{"id":"2208.01813","title":"TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation","created":"2022-08-03","cited_by_count":12,"area":null},{"id":"2306.12795","title":"Learning Unseen Modality Interaction","created":"2023-06-22","cited_by_count":12,"area":null},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10,"area":null},{"id":"2108.02059","title":"Question-controlled Text-aware Image Captioning","created":"2021-08-04","cited_by_count":9,"area":null},{"id":"2105.08106","title":"Multi-Modal Image Captioning for the Visually Impaired","created":"2021-05-17","cited_by_count":8,"area":null},{"id":"2308.16383","title":"Separate and Locate: Rethink the Text in Text-based Visual Question Answering","created":"2023-08-31","cited_by_count":7,"area":null},{"id":"2309.14389","title":"Analyzing the Efficacy of an LLM-Only Approach for Image-based Document Question Answering","created":"2023-09-25","cited_by_count":7,"area":null},{"id":"2404.10652","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset and a Novel Multimodal Feature Fusion Method for Vietnamese Text Comprehension in Images","created":"2024-04-16","cited_by_count":7,"area":null},{"id":"2412.15523","title":"InstructOCR: Instruction Boosting Scene Text Spotting","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2310.09147","title":"Exploring Sparse Spatial Relation in Graph Inference for Text-Based VQA","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2511.17490","title":"Video-R4: Reinforcing Text-Rich Video Reasoning with Visual Rumination","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2211.12950","title":"Look, Read and Ask: Learning to Ask Questions by Reading Text in Images","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2404.00973","title":"VideoDistill: Language-aware Vision Distillation for Video Question Answering","created":"2024-04-01","cited_by_count":5,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2208.08104","title":"Understanding Attention for Vision-and-Language Tasks","created":"2022-08-17","cited_by_count":4,"area":null},{"id":"2209.06730","title":"MUST-VQA: MUltilingual Scene-text VQA","created":"2022-09-14","cited_by_count":4,"area":null},{"id":"2304.01603","title":"Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA","created":"2023-04-04","cited_by_count":4,"area":null},{"id":"2311.08622","title":"Multiple-Question Multiple-Answer Text-VQA","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2403.19080","title":"MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2507.04600","title":"DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2201.05017","title":"Towards Automated Error Analysis: Learning to Characterize Errors","created":"2022-01-13","cited_by_count":3,"area":null},{"id":"2302.01540","title":"DEVICE: Depth and Visual Concepts Aware Transformer for OCR-based Image Captioning","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2407.05750","title":"Large Language Models Understand Layout","created":"2024-07-08","cited_by_count":3,"area":null},{"id":"2101.09865","title":"ECOL-R: Encouraging Copying in Novel Object Captioning with Reinforcement Learning","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2203.12929","title":"Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2212.08283","title":"SceneGATE: Scene-Graph based co-Attention networks for TExt visual question answering","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2309.01380","title":"Understanding Video Scenes through Text: Insights from Text-based Video Question Answering","created":"2023-09-04","cited_by_count":2,"area":null},{"id":"2402.00453","title":"Instruction Makes a Difference","created":"2024-02-01","cited_by_count":2,"area":null},{"id":"2605.12952","title":"Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2111.03994","title":"NarrationBot and InfoBot: A Hybrid System for Automated Video Description","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1,"area":null},{"id":"2210.16174","title":"Multimodal Transformer for Parallel Concatenated Variational Autoencoders","created":"2022-10-28","cited_by_count":1,"area":null},{"id":"2308.00295","title":"Making the V in Text-VQA Matter","created":"2023-08-01","cited_by_count":1,"area":null},{"id":"2502.19202","title":"LiGT: Layout-infused Generative Transformer for Visual Question Answering on Vietnamese Receipts","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2510.06680","title":"TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2108.09717","title":"EKTVQA: Generalized use of External Knowledge to empower Scene Text in Text-VQA","created":"2021-08-22","cited_by_count":0,"area":null},{"id":"2111.06075","title":"Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture","created":"2021-11-11","cited_by_count":0,"area":null},{"id":"2112.09220","title":"Sim2Real Docs: Domain Randomization for Documents in Natural Scenes using Ray-traced Rendering","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2206.07981","title":"Multi-scale Cooperative Multimodal Transformers for Multimodal Sentiment Analysis in Videos","created":"2022-06-16","cited_by_count":0,"area":null},{"id":"2211.14450","title":"Text-Aware Dual Routing Network for Visual Question Answering","created":"2022-11-17","cited_by_count":0,"area":null},{"id":"2403.09288","title":"Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2410.14132","title":"ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering","created":"2024-10-18","cited_by_count":0,"area":null},{"id":"2506.03665","title":"ROSA: Addressing text understanding challenges in photographs via ROtated SAmpling","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2509.01259","title":"ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2605.11392","title":"Transformer Interpretability from Perspective of Attention and Gradient","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2609.07213","title":"Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic Perspective","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.13815","title":"Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-End","created":"2026-09-12","cited_by_count":0,"area":null}],"next_cursor":null}