2026-10-14T17:10:36Z https://www.scidb.cn/oai

10.57760/sciencedb.j00240.0008p 2026-08-21T11:47:21Z

2026-08-21 Text Semantic Collaborative Filtering and Region-Aware Scene Text Video Question Answering doi:10.57760/sciencedb.j00240.0008p en This dataset is the open-source deliverable accompanying the paper Text Semantic Collaborative Filtering and Region-Aware Scene-Text Video Question Answering. It mainly consists of two core components: 1) the complete experimental code for the proposed text-semantic collaborative key-frame selection and text-region-aware method presented in the paper; 2) key original derived data generated based on three public datasets including M4-ViteVQA, RoadTextVQA and NewsVideoQA, which cover key-frame selection results, scene-text matching outputs and experimental evaluation metrics. The open release of this dataset aims to provide benchmarks for algorithm reproduction and experimental support for researchers in the fields of scene-text video question answering, video key-frame selection, scene-text understanding and multimodal video understanding. scene text video question answering; key frame selection; visual attention guidance; multimodal video understanding Fang Chengyang Zhang Nan Jiang Wenhui Liu Xuelin Fang Yuming PUBLIC https://api.github.com/licenses/mit dataset Science Data Bank