{"total":23,"rows":[{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109,"area":null},{"id":"2204.13631","title":"Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly","created":"2022-04-28","cited_by_count":89,"area":null},{"id":"2110.00413","title":"Detecting Harmful Memes and Their Targets","created":"2021-09-24","cited_by_count":78,"area":null},{"id":"2102.00529","title":"Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers","created":"2021-01-31","cited_by_count":64,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"area":null},{"id":"2107.09106","title":"Separating Skills and Concepts for Novel Visual Question Answering","created":"2021-07-19","cited_by_count":24,"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":"2211.12328","title":"A survey on knowledge-enhanced multimodal learning","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2104.03435","title":"Multimodal Fusion Refiner Networks","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2104.00285","title":"CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning","created":"2021-04-01","cited_by_count":6,"area":null},{"id":"2201.02010","title":"Self-Training Vision Language BERTs with a Unified Conditional Model","created":"2022-01-06","cited_by_count":6,"area":null},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2203.03441","title":"Multi-Modal Attribute Extraction for E-Commerce","created":"2022-03-07","cited_by_count":5,"area":null},{"id":"2107.13054","title":"Exceeding the Limits of Visual-Linguistic Multi-Task Learning","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2207.01772","title":"Vision-and-Language Pretraining","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2207.13242","title":"Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2112.11244","title":"Hateful Memes Challenge: An Enhanced Multimodal Framework","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2212.06655","title":"The Hateful Memes Challenge Next Move","created":"2022-12-13","cited_by_count":1,"area":null},{"id":"2103.11011","title":"Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals","created":"2021-03-19","cited_by_count":0,"area":null}],"next_cursor":null}