{"total":25,"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":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2103.16564","title":"Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning","created":"2021-03-30","cited_by_count":68,"area":null},{"id":"2110.15358","title":"Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language","created":"2021-10-28","cited_by_count":55,"area":null},{"id":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25,"area":null},{"id":"2112.06482","title":"ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition","created":"2021-12-13","cited_by_count":24,"area":null},{"id":"2108.02359","title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning","created":"2021-08-05","cited_by_count":18,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2112.11739","title":"A Survey of Natural Language Generation","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2310.15676","title":"Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2208.04215","title":"Boosting Video-Text Retrieval with Explicit High-Level Semantics","created":"2022-08-08","cited_by_count":8,"area":null},{"id":"2106.10658","title":"Exploring Semantic Relationships for Unpaired Image Captioning","created":"2021-06-20","cited_by_count":6,"area":null},{"id":"2209.09543","title":"FACT: Learning Governing Abstractions Behind Integer Sequences","created":"2022-09-20","cited_by_count":6,"area":null},{"id":"2405.02766","title":"Beyond Unimodal Learning: The Importance of Integrating Multiple Modalities for Lifelong Learning","created":"2024-05-04","cited_by_count":5,"area":null},{"id":"2108.06458","title":"Cross-Modal Graph with Meta Concepts for Video Captioning","created":"2021-08-14","cited_by_count":4,"area":null},{"id":"2210.16431","title":"DiMBERT: Learning Vision-Language Grounded Representations with Disentangled Multimodal-Attention","created":"2022-10-28","cited_by_count":4,"area":null},{"id":"2502.16733","title":"Coreset Selection via LLM-based Concept Bottlenecks","created":"2025-02-23","cited_by_count":2,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null},{"id":"2211.10992","title":"How to Describe Images in a More Funny Way? Towards a Modular Approach to Cross-Modal Sarcasm Generation","created":"2022-11-20","cited_by_count":1,"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":"2109.03529","title":"RefineCap: Concept-Aware Refinement for Image Captioning","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2201.09153","title":"An Integrated Approach for Video Captioning and Applications","created":"2022-01-23","cited_by_count":0,"area":null},{"id":"2301.02440","title":"An Image captioning algorithm based on the Hybrid Deep Learning Technique (CNN+GRU)","created":"2023-01-06","cited_by_count":0,"area":null},{"id":"2302.04676","title":"Stacked Cross-modal Feature Consolidation Attention Networks for Image Captioning","created":"2023-02-08","cited_by_count":0,"area":null},{"id":"2303.10766","title":"Multi-modal reward for visual relationships-based image captioning","created":"2023-03-19","cited_by_count":0,"area":null}],"next_cursor":null}