{"total":66,"rows":[{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424,"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":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113,"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":"2210.10488","title":"Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective","created":"2022-10-19","cited_by_count":41,"area":null},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40,"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":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27,"area":"lr"},{"id":"2205.10646","title":"Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2305.03668","title":"A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding","created":"2023-05-05","cited_by_count":18,"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":"2211.04872","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":"2211.15521","title":"G^3: Geolocation via Guidebook Grounding","created":"2022-11-28","cited_by_count":12,"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":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2402.11744","title":"Machine-Generated Text Localization","created":"2024-02-19","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":"2308.01126","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model","created":"2023-08-02","cited_by_count":10,"area":"mllm"},{"id":"2305.17202","title":"BIG-C: a Multimodal Multi-Purpose Dataset for Bemba","created":"2023-05-26","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":"2305.05432","title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","created":"2023-05-09","cited_by_count":8,"area":null},{"id":"2505.17476","title":"The Coherence Trap: When MLLM-Crafted Narratives Exploit Manipulated Visual Contexts","created":"2025-05-23","cited_by_count":8,"area":null},{"id":"2306.00931","title":"\"Let's not Quote out of Context\": Unified Vision-Language Pretraining for Context Assisted Image Captioning","created":"2023-06-01","cited_by_count":7,"area":"mllm"},{"id":"2306.06306","title":"DocumentCLIP: Linking Figures and Main Body Text in Reflowed Documents","created":"2023-06-09","cited_by_count":7,"area":"mllm"},{"id":"2509.15350","title":"Real, Fake, or Manipulated? Detecting Machine-Influenced Text","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2601.15316","title":"The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection","created":"2026-01-16","cited_by_count":6,"area":"lr"},{"id":"2207.13061","title":"NewsStories: Illustrating articles with visual summaries","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2410.23676","title":"Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach","created":"2024-10-31","cited_by_count":5,"area":"mllm"},{"id":"2509.12653","title":"Beyond Artificial Misalignment: Detecting and Grounding Semantic-Coordinated Multimodal Manipulations","created":"2025-09-16","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":"2212.04267","title":"Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval","created":"2022-12-08","cited_by_count":3,"area":"mllm"},{"id":"2308.10447","title":"Explore and Tell: Embodied Visual Captioning in 3D Environments","created":"2023-08-21","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":"2511.21002","title":"Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning","created":"2025-11-26","cited_by_count":3,"area":"rag"},{"id":"2305.04166","title":"UIT-OpenViIC: A Novel Benchmark for Evaluating Image Captioning in Vietnamese","created":"2023-05-07","cited_by_count":2,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"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":"2406.19054","title":"A look under the hood of the Interactive Deep Learning Enterprise (No-IDLE)","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2408.04331","title":"Enhancing Journalism with AI: A Study of Contextualized Image Captioning for News Articles using LLMs and LMMs","created":"2024-08-08","cited_by_count":1,"area":"mllm"},{"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":"2410.17810","title":"EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2603.09921","title":"WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2207.04174","title":"Towards Multimodal Vision-Language Models Generating Non-Generic Text","created":"2022-07-09","cited_by_count":0,"area":"mllm"},{"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":"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":"2409.03911","title":"The Role of Generative Systems in Historical Photography Management: A Case Study on Catalan Archives","created":"2024-09-05","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":"2504.11473","title":"Visual moral inference and communication","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2505.23358","title":"Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model","created":"2025-05-29","cited_by_count":0,"area":"mllm"},{"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":"2512.20042","title":"Beyond Vision: Contextually Enriched Image Captioning with Multi-Modal Retrieval","created":"2025-12-23","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}],"next_cursor":null}