{"total":42,"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":"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":"2202.05786","title":"Multi-Modal Knowledge Graph Construction and Application: A Survey","created":"2022-02-11","cited_by_count":74,"area":null},{"id":"2108.01682","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","created":"2021-08-03","cited_by_count":41,"area":null},{"id":"2204.06347","title":"WikiDiverse: A Multimodal Entity Linking Dataset with Diversified Contextual Topics and Entity Types","created":"2022-04-13","cited_by_count":34,"area":null},{"id":"2107.11970","title":"Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph","created":"2021-07-26","cited_by_count":31,"area":null},{"id":"2305.13631","title":"EDIS: Entity-Driven Image Search over Multimodal Web Content","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2108.12126","title":"Automated Generation of Accurate \\& Fluent Medical X-ray Reports","created":"2021-08-27","cited_by_count":24,"area":null},{"id":"2103.05187","title":"Iterative Shrinking for Referring Expression Grounding Using Deep Reinforcement Learning","created":"2021-03-09","cited_by_count":20,"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":"2211.04872","title":"Visual Named Entity Linking: A New Dataset and A Baseline","created":"2022-11-09","cited_by_count":15,"area":null},{"id":"2109.02865","title":"Journalistic Guidelines Aware News Image Captioning","created":"2021-09-07","cited_by_count":14,"area":null},{"id":"2308.08325","title":"Visually-Aware Context Modeling for News Image Captioning","created":"2023-08-16","cited_by_count":12,"area":null},{"id":"2108.02050","title":"ICECAP: Information Concentrated Entity-aware Image Captioning","created":"2021-08-04","cited_by_count":11,"area":null},{"id":"2209.10474","title":"Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia","created":"2022-09-21","cited_by_count":10,"area":null},{"id":"2212.00843","title":"Focus! Relevant and Sufficient Context Selection for News Image Captioning","created":"2022-12-01","cited_by_count":10,"area":null},{"id":"2203.16763","title":"CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2207.13061","title":"NewsStories: Illustrating articles with visual summaries","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2301.02160","title":"ANNA: Abstractive Text-to-Image Synthesis with Filtered News Captions","created":"2023-01-05","cited_by_count":5,"area":null},{"id":"2406.17213","title":"Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2112.05917","title":"Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval","created":"2021-12-11","cited_by_count":3,"area":null},{"id":"2210.04806","title":"Generating image captions with external encyclopedic knowledge","created":"2022-10-10","cited_by_count":3,"area":null},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2510.23023","title":"UniAIDet: A Unified and Universal Benchmark for AI-Generated Image Content Detection and Localization","created":"2025-10-27","cited_by_count":2,"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":"2402.19404","title":"EAMA : Entity-Aware Multimodal Alignment Based Approach for News Image Captioning","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2403.05101","title":"Rule-driven News Captioning","created":"2024-03-08","cited_by_count":1,"area":null},{"id":"2405.11145","title":"Detecting Multimodal Situations with Insufficient Context and Abstaining from Baseless Predictions","created":"2024-05-18","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":"2304.13130","title":"Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2309.13601","title":"FaceGemma: Enhancing Image Captioning with Facial Attributes for Portrait Images","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2312.02188","title":"Video Summarization: Towards Entity-Aware Captions","created":"2023-12-01","cited_by_count":0,"area":null},{"id":"2403.06520","title":"How to Understand Named Entities: Using Common Sense for News Captioning","created":"2024-03-11","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},{"id":"2409.19960","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2410.18096","title":"$M^3EL$: A Multi-task Multi-topic Dataset for Multi-modal Entity Linking","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2412.11025","title":"From Simple to Professional: A Combinatorial Controllable Image Captioning Agent","created":"2024-12-15","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":"2509.01259","title":"ReCap: Event-Aware Image Captioning with Article Retrieval and Semantic Gaussian Normalization","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2512.23185","title":"EIR: Enhanced Image Representations for Medical Report Generation","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2603.10613","title":"MUNIChus: Multilingual News Image Captioning Benchmark","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2609.33441","title":"MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}