{"total":37,"rows":[{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2104.00332","title":"UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training","created":"2021-04-01","cited_by_count":64,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44,"area":null},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","cited_by_count":44,"area":null},{"id":"2109.05125","title":"MURAL: Multimodal, Multitask Retrieval Across Languages","created":"2021-09-10","cited_by_count":44,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2206.00621","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","created":"2022-06-01","cited_by_count":24,"area":null},{"id":"2309.01859","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","created":"2023-09-04","cited_by_count":24,"area":null},{"id":"2411.03769","title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","created":"2024-11-06","cited_by_count":19,"area":null},{"id":"2203.03047","title":"Recent Advances in Neural Text Generation: A Task-Agnostic Survey","created":"2022-03-06","cited_by_count":14,"area":null},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14,"area":null},{"id":"2306.08658","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","created":"2023-06-14","cited_by_count":11,"area":null},{"id":"2312.08984","title":"CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer","created":"2023-12-14","cited_by_count":10,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2310.14356","title":"Semantic and Expressive Variation in Image Captions Across Languages","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2107.00372","title":"Egocentric Image Captioning for Privacy-Preserved Passive Dietary Intake Monitoring","created":"2021-07-01","cited_by_count":7,"area":null},{"id":"2403.17545","title":"A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questions","created":"2024-03-26","cited_by_count":7,"area":null},{"id":"2102.07192","title":"Improved Bengali Image Captioning via deep convolutional neural network based encoder-decoder model","created":"2021-02-14","cited_by_count":6,"area":null},{"id":"2311.04192","title":"JaSPICE: Automatic Evaluation Metric Using Predicate-Argument Structures for Image Captioning Models","created":"2023-11-07","cited_by_count":6,"area":null},{"id":"2109.05218","title":"Bornon: Bengali Image Captioning with Transformer-based Deep learning approach","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2409.16646","title":"Cross-Lingual and Cross-Cultural Variation in Image Descriptions","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2109.07622","title":"Towards Zero-shot Cross-lingual Image Retrieval and Tagging","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2508.16204","title":"Competition and Attraction Improve Model Fusion","created":"2025-08-22","cited_by_count":4,"area":null},{"id":"2211.14451","title":"GLAMI-1M: A Multilingual Image-Text Fashion Dataset","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2302.04811","title":"A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2401.08100","title":"KTVIC: A Vietnamese Image Captioning Dataset on the Life Domain","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2210.16960","title":"Multilingual Multimodality: A Taxonomical Survey of Datasets, Techniques, Challenges and Opportunities","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2406.18254","title":"Improving the Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2512.00773","title":"DEJIMA: A Novel Large-scale Japanese Dataset for Image Captioning and Visual Question Answering","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2105.04971","title":"Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora","created":"2021-05-11","cited_by_count":0,"area":null},{"id":"2303.05983","title":"Accountable Textual-Visual Chat Learns to Reject Human Instructions in Image Re-creation","created":"2023-03-10","cited_by_count":0,"area":null},{"id":"2407.09495","title":"Image captioning in different languages","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2509.17365","title":"Pre-Trained CNN Architecture for Transformer-Based Image Caption Generation Model","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2601.10096","title":"Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text","created":"2026-01-15","cited_by_count":0,"area":null}],"next_cursor":null}