{"total":40,"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":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"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":"2101.07396","title":"ArtEmis: Affective Language for Visual Art","created":"2021-01-19","cited_by_count":104,"area":null},{"id":"2104.00990","title":"Visual Semantic Role Labeling for Video Understanding","created":"2021-04-02","cited_by_count":60,"area":null},{"id":"2406.07502","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","created":"2024-06-11","cited_by_count":43,"area":null},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2106.01444","title":"SMURF: SeMantic and linguistic UndeRstanding Fusion for Caption Evaluation via Typicality Analysis","created":"2021-06-02","cited_by_count":18,"area":null},{"id":"2207.07243","title":"LineCap: Line Charts for Data Visualization Captioning Models","created":"2022-07-15","cited_by_count":17,"area":null},{"id":"2511.21025","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","created":"2025-11-26","cited_by_count":15,"area":null},{"id":"2202.08029","title":"Code Search based on Context-aware Code Translation","created":"2022-02-16","cited_by_count":14,"area":null},{"id":"2110.02623","title":"Is An Image Worth Five Sentences? A New Look into Semantics for Image-Text Matching","created":"2021-10-06","cited_by_count":13,"area":null},{"id":"2212.13196","title":"Biologically Inspired Design Concept Generation Using Generative Pre-Trained Transformers","created":"2022-12-26","cited_by_count":13,"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":"2407.18589","title":"HICEScore: A Hierarchical Metric for Image Captioning Evaluation","created":"2024-07-26","cited_by_count":12,"area":null},{"id":"2504.06666","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2105.14403","title":"Re-evaluating Word Mover's Distance","created":"2021-05-30","cited_by_count":10,"area":null},{"id":"2106.10887","title":"Trust It or Not: Confidence-Guided Automatic Radiology Report Generation","created":"2021-06-21","cited_by_count":9,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2401.16578","title":"Leveraging Professional Radiologists' Expertise to Enhance LLMs' Evaluation for Radiology Reports","created":"2024-01-29","cited_by_count":7,"area":null},{"id":"2502.04718","title":"Evaluating Text Style Transfer Evaluation: Are There Any Reliable Metrics?","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2101.07299","title":"Diagnostic Captioning: A Survey","created":"2021-01-18","cited_by_count":6,"area":null},{"id":"2104.13453","title":"Meta-evaluation of Conversational Search Evaluation Metrics","created":"2021-04-27","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":"2401.04518","title":"The Critique of Critique","created":"2024-01-09","cited_by_count":5,"area":null},{"id":"2411.06710","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","created":"2024-11-11","cited_by_count":5,"area":null},{"id":"2210.08859","title":"Social Biases in Automatic Evaluation Metrics for NLG","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2207.01733","title":"Are metrics measuring what they should? An evaluation of image captioning task metrics","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2207.09847","title":"Predicting Word Learning in Children from the Performance of Computer Vision Systems","created":"2022-07-07","cited_by_count":2,"area":null},{"id":"2102.05067","title":"The Role of the Input in Natural Language Video Description","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2108.06165","title":"Caption Generation on Scenes with Seen and Unseen Object Categories","created":"2021-08-13","cited_by_count":1,"area":null},{"id":"2108.12575","title":"Goal-driven text descriptions for images","created":"2021-08-28","cited_by_count":1,"area":null},{"id":"2204.09714","title":"Generative Pre-Trained Transformers for Biologically Inspired Design","created":"2022-03-31","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":"2505.02078","title":"LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning","created":"2025-05-04","cited_by_count":1,"area":null},{"id":"2105.09906","title":"Empirical Analysis of Image Caption Generation using Deep Learning","created":"2021-05-14","cited_by_count":0,"area":null},{"id":"2602.00393","title":"Brazilian Portuguese Image Captioning with Transformers: A Study on Cross-Native-Translated Dataset","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.05419","title":"Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2602.09225","title":"Barycentric alignment for instance-level comparison of neural representations","created":"2026-02-09","cited_by_count":0,"area":null}],"next_cursor":null}