{"total":21,"rows":[{"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":"2205.12522","title":"Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset","created":"2022-05-25","cited_by_count":100,"area":null},{"id":"2205.01883","title":"All You May Need for VQA are Image Captions","created":"2022-05-04","cited_by_count":65,"area":null},{"id":"2305.13703","title":"MemeCap: A Dataset for Captioning and Interpreting Memes","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30,"area":null},{"id":"2104.08376","title":"Concadia: Towards Image-Based Text Generation with a Purpose","created":"2021-04-16","cited_by_count":15,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2109.05281","title":"COSMic: A Coherence-Aware Generation Metric for Image Descriptions","created":"2021-09-11","cited_by_count":9,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2109.11047","title":"Cross-Modal Coherence for Text-to-Image Retrieval","created":"2021-09-22","cited_by_count":5,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2311.09106","title":"\"We Demand Justice!\": Towards Social Context Grounding of Political Texts","created":"2023-11-15","cited_by_count":4,"area":null},{"id":"2503.10997","title":"RONA: Pragmatically Diverse Image Captioning with Coherence Relations","created":"2025-03-14","cited_by_count":3,"area":null},{"id":"2302.02124","title":"Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning","created":"2023-02-04","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":"2410.00659","title":"Multimodal Coherent Explanation Generation of Robot Failures","created":"2024-10-01","cited_by_count":1,"area":null},{"id":"2510.09390","title":"Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2109.00693","title":"AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification","created":"2021-09-02","cited_by_count":0,"area":null},{"id":"2207.02356","title":"Zero-shot Cross-Linguistic Learning of Event Semantics","created":"2022-07-05","cited_by_count":0,"area":null},{"id":"2404.10141","title":"ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis","created":"2024-04-15","cited_by_count":0,"area":null}],"next_cursor":null}