{"total":14,"rows":[{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156,"area":null},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54,"area":null},{"id":"2206.07173","title":"Measuring Representational Harms in Image Captioning","created":"2022-06-14","cited_by_count":36,"area":null},{"id":"2201.05299","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","created":"2022-01-14","cited_by_count":13,"area":null},{"id":"2311.04067","title":"Multitask Multimodal Prompted Training for Interactive Embodied Task Completion","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2304.14623","title":"Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2401.14626","title":"Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2211.14835","title":"CLID: Controlled-Length Image Descriptions with Limited Data","created":"2022-11-27","cited_by_count":4,"area":null},{"id":"2309.00215","title":"Towards Addressing the Misalignment of Object Proposal Evaluation for Vision-Language Tasks via Semantic Grounding","created":"2023-09-01","cited_by_count":2,"area":null},{"id":"2211.03314","title":"CLOP: Video-and-Language Pre-Training with Knowledge Regularizations","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2212.00770","title":"On Utilizing Relationships for Transferable Few-Shot Fine-Grained Object Detection","created":"2022-12-01","cited_by_count":0,"area":null},{"id":"2403.17702","title":"The Solution for the CVPR 2023 1st foundation model challenge-Track2","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2406.19316","title":"Enhanced Data Transfer Cooperating with Artificial Triplets for Scene Graph Generation","created":"2024-06-27","cited_by_count":0,"area":null}],"next_cursor":null}