@article{vitexqaamultiframetemporalperceptiondata, title = {ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering}, author = {Zhentao Guo and Chen Duan and Tongkun Guan and Zining Wang and Kai Zhou and Pengfei Yan}, year = {2026}, eprint = {2606.24602}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.24602}, }