TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos
Videos are unique in their integration of temporal elements, including camera, scene, action, and attribute, along with their dynamic relationships over time. However, existing benchmarks for video understanding often treat these properties separately or narrowly focus on specific aspects, overlooking the holistic nature of video content. To address this, we introduce TUNA, a temporal-oriented benchmark for fine-grained understanding on dense dynamic videos, with two complementary tasks: captioning and QA. Our TUNA features diverse video scenarios and dynamics, assisted by interpretable and robust evaluation criteria. We evaluate several leading models on our benchmark, providing fine-grained performance assessments across various dimensions. This evaluation reveals key challenges in video temporal understanding, such as limited action description, inadequate multi-subject understanding, and insensitivity to camera motion, offering valuable insights for improving video understanding models. The data and code are available atthis https URL.
View on arXiv@article{kong2025_2505.20124,
title={ TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos },
author={ Fanheng Kong and Jingyuan Zhang and Hongzhi Zhang and Shi Feng and Daling Wang and Linhao Yu and Xingguang Ji and Yu Tian and Victoria W. and Fuzheng Zhang },
journal={arXiv preprint arXiv:2505.20124},
year={ 2025 }
}