{"total":18,"rows":[{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85,"area":null},{"id":"2107.14178","title":"ReFormer: The Relational Transformer for Image Captioning","created":"2021-07-29","cited_by_count":23,"area":null},{"id":"2104.08108","title":"Cross-Modal Retrieval Augmentation for Multi-Modal Classification","created":"2021-04-16","cited_by_count":20,"area":null},{"id":"2309.01961","title":"NICE: CVPR 2023 Challenge on Zero-shot Image Captioning","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2112.08459","title":"Rethinking Nearest Neighbors for Visual Classification","created":"2021-12-15","cited_by_count":6,"area":null},{"id":"2303.00703","title":"Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis","created":"2023-03-01","cited_by_count":5,"area":null},{"id":"2202.06633","title":"FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows","created":"2022-02-14","cited_by_count":4,"area":null},{"id":"2312.15720","title":"Set Prediction Guided by Semantic Concepts for Diverse Video Captioning","created":"2023-12-25","cited_by_count":4,"area":null},{"id":"2404.18413","title":"3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset","created":"2024-04-29","cited_by_count":4,"area":null},{"id":"2205.01813","title":"Diverse Image Captioning with Grounded Style","created":"2022-05-03","cited_by_count":3,"area":null},{"id":"2406.00334","title":"Image Captioning via Dynamic Path Customization","created":"2024-06-01","cited_by_count":3,"area":null},{"id":"2303.15016","title":"Borrowing Human Senses: Comment-Aware Self-Training for Social Media Multimodal Classification","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2502.15900","title":"Explaining the Success of Nearest Neighbor Methods in Prediction","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2105.03826","title":"A Hybrid Model for Combining Neural Image Caption and k-Nearest Neighbor Approach for Image Captioning","created":"2021-05-09","cited_by_count":0,"area":null},{"id":"2107.09285","title":"Neural Abstructions: Abstractions that Support Construction for Grounded Language Learning","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2508.14045","title":"From Image Captioning to Visual Storytelling","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2603.22946","title":"Caption Generation for Dongba Paintings via Prompt Learning and Semantic Fusion","created":"2026-03-24","cited_by_count":0,"area":null}],"next_cursor":null}