{"total":32,"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":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2104.13225","title":"Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques","created":"2021-04-27","cited_by_count":32,"area":null},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2304.01662","title":"Cross-Domain Image Captioning with Discriminative Finetuning","created":"2023-04-04","cited_by_count":14,"area":null},{"id":"2103.03987","title":"Selective Replay Enhances Learning in Online Continual Analogical Reasoning","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2202.01107","title":"Keyword localisation in untranscribed speech using visually grounded speech models","created":"2022-02-02","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":"2305.03610","title":"The Role of Data Curation in Image Captioning","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2102.11506","title":"Comparative evaluation of CNN architectures for Image Caption Generation","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2305.14779","title":"Alt-Text with Context: Improving Accessibility for Images on Twitter","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2309.11710","title":"ContextRef: Evaluating Referenceless Metrics For Image Description Generation","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2110.12442","title":"Bangla Image Caption Generation through CNN-Transformer based Encoder-Decoder Network","created":"2021-10-24","cited_by_count":2,"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":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2406.08996","title":"Introducing Brain-like Concepts to Embodied Hand-crafted Dialog Management System","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2101.06803","title":"Narration Generation for Cartoon Videos","created":"2021-01-17","cited_by_count":1,"area":null},{"id":"2105.10131","title":"Visual representation of negation: Real world data analysis on comic image design","created":"2021-05-21","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":"2601.05269","title":"Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach","created":"2025-11-15","cited_by_count":1,"area":null},{"id":"2102.11994","title":"Characterization and recognition of handwritten digits using Julia","created":"2021-02-24","cited_by_count":0,"area":null},{"id":"2109.04949","title":"We went to look for meaning and all we got were these lousy representations: aspects of meaning representation for computational semantics","created":"2021-09-10","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":"2208.06117","title":"Facial Expression Recognition and Image Description Generation in Vietnamese","created":"2022-08-12","cited_by_count":0,"area":null},{"id":"2303.04053","title":"Describe me an Aucklet: Generating Grounded Perceptual Category Descriptions","created":"2023-03-07","cited_by_count":0,"area":null},{"id":"2511.04754","title":"Surprisal reveals diversity gaps in image captioning and different scorers change the story","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2606.09846","title":"CANVAS: Captioning Art with Narrative Visual-Audio AI Systems","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2607.21611","title":"A Systematic Survey on Image Description Techniques for STEM Domains","created":"2026-05-22","cited_by_count":0,"area":null}],"next_cursor":null}