{"total":24,"rows":[{"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":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138,"area":null},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97,"area":null},{"id":"2110.01705","title":"Let there be a clock on the beach: Reducing Object Hallucination in Image Captioning","created":"2021-10-04","cited_by_count":76,"area":null},{"id":"2112.06558","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning","created":"2021-12-13","cited_by_count":27,"area":null},{"id":"2110.11767","title":"Exploiting Cross-Modal Prediction and Relation Consistency for Semi-Supervised Image Captioning","created":"2021-10-22","cited_by_count":23,"area":null},{"id":"2208.08965","title":"GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement","created":"2022-08-18","cited_by_count":20,"area":null},{"id":"2403.11491","title":"Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting","created":"2024-03-18","cited_by_count":20,"area":null},{"id":"2406.00644","title":"Ultrasound Report Generation with Cross-Modality Feature Alignment via Unsupervised Guidance","created":"2024-06-02","cited_by_count":17,"area":null},{"id":"2206.09378","title":"A Self-Guided Framework for Radiology Report Generation","created":"2022-06-19","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":"2210.08303","title":"Improving Radiology Summarization with Radiograph and Anatomy Prompts","created":"2022-10-15","cited_by_count":4,"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":"2507.10419","title":"Multiple Choice Learning of Low-Rank Adapters for Language Modeling","created":"2025-07-14","cited_by_count":2,"area":null},{"id":"2210.15146","title":"Towards Practicality of Sketch-Based Visual Understanding","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2403.17995","title":"Semi-Supervised Image Captioning Considering Wasserstein Graph Matching","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2502.10118","title":"Image Embedding Sampling Method for Diverse Captioning","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2506.03178","title":"LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2509.26208","title":"TSalV360: A Method and Dataset for Text-driven Saliency Detection in 360-Degrees Videos","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.15470","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2603.26804","title":"The Language of Touch: Translating Vibrations into Text with Dual-Branch Learning","created":"2026-03-26","cited_by_count":0,"area":null}],"next_cursor":null}