{"total":14,"rows":[{"id":"2305.17415","title":"Exploring Better Text Image Translation with Multimodal Codebook","created":"2023-05-27","cited_by_count":23,"area":null},{"id":"2407.02894","title":"Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation","created":"2024-07-03","cited_by_count":14,"area":null},{"id":"2412.07147","title":"MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation","created":"2024-12-10","cited_by_count":12,"area":null},{"id":"2505.15282","title":"Exploring In-Image Machine Translation with Real-World Background","created":"2025-05-21","cited_by_count":7,"area":null},{"id":"2405.12669","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2305.05166","title":"E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation","created":"2023-05-09","cited_by_count":5,"area":null},{"id":"2308.03024","title":"Show Me the World in My Language: Establishing the First Baseline for Scene-Text to Scene-Text Translation","created":"2023-08-06","cited_by_count":5,"area":null},{"id":"2505.19714","title":"MT$^{3}$: Scaling MLLM-based Text Image Machine Translation via Multi-Task Reinforcement Learning","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2603.23896","title":"MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2602.21956","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation","created":"2026-02-25","cited_by_count":3,"area":null},{"id":"2507.18940","title":"LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2602.07014","title":"Vectra: A New Metric, Dataset, and Model for Visual Quality Assessment in E-Commerce In-Image Machine Translation","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2605.24675","title":"VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Translation","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2605.29476","title":"Comparative Evaluation of Machine Translation Systems on Images with Text","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}