{"total":16,"rows":[{"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":"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":"2309.04734","title":"Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering","created":"2023-09-09","cited_by_count":2,"area":null},{"id":"2505.05714","title":"TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries","created":"2025-05-09","cited_by_count":2,"area":null},{"id":"2603.10495","title":"IMTBench: A Multi-Scenario Cross-Modal Collaborative Evaluation Benchmark for In-Image Machine Translation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2603.09392","title":"ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2606.24333","title":"UniTranslator: A Unified Multi-modal Framework for End-to-end In-Image Machine Translation","created":"2026-06-23","cited_by_count":1,"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":"2601.00222","title":"LooC: Effective Low-Dimensional Codebook for Compositional Vector Quantization","created":"2026-01-01","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},{"id":"2609.37287","title":"VISTA-Bench: Benchmarking Multilingual Image Translation with Image-Specific Rubrics","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}