Understanding causal event relationships and achieving fine-grained temporal grounding in videos remain challenging for vision-language models. Existing methods either compress video tokens to reduce temporal resolution, or treat videos as unsegmented streams, which obscures fine-grained event boundaries and limits the modeling of causal dependencies. We propose TEMPURA (Temporal Event Masked Prediction and Understanding for Reasoning in Action), a two-stage training framework that enhances video temporal understanding. TEMPURA first applies masked event prediction reasoning to reconstruct missing events and generate step-by-step causal explanations from dense event annotations, drawing inspiration from effective infilling techniques. TEMPURA then learns to perform video segmentation and dense captioning to decompose videos into non-overlapping events with detailed, timestamp-aligned descriptions. We train TEMPURA on VER, a large-scale dataset curated by us that comprises 1M training instances and 500K videos with temporally aligned event descriptions and structured reasoning steps. Experiments on temporal grounding and highlight detection benchmarks demonstrate that TEMPURA outperforms strong baseline models, confirming that integrating causal reasoning with fine-grained temporal segmentation leads to improved video understanding.
View on arXiv@article{cheng2025_2505.01583,
title={ TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action },
author={ Jen-Hao Cheng and Vivian Wang and Huayu Wang and Huapeng Zhou and Yi-Hao Peng and Hou-I Liu and Hsiang-Wei Huang and Kuang-Ming Chen and Cheng-Yen Yang and Wenhao Chai and Yi-Ling Chen and Vibhav Vineet and Qin Cai and Jenq-Neng Hwang },
journal={arXiv preprint arXiv:2505.01583},
year={ 2025 }
}