TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos

TL;DR

TUNA is a new benchmark designed to evaluate fine-grained temporal understanding in dense dynamic videos through captioning and QA tasks, highlighting key challenges and guiding future improvements.

Contribution

It introduces a comprehensive, multi-faceted benchmark for dense dynamic videos, addressing the holistic temporal understanding often overlooked in existing datasets.

Findings

Models struggle with detailed action descriptions.

Multi-subject understanding remains limited.

Camera motion sensitivity is inadequate.

Abstract

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 at https://friedrichor.github.io/projects/TUNA.